中 EN
登录 注册账户

Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达，利用大语言模型自动生成交叉领域文献分析简报。

登录 注册账户
01.
arXiv (CS.CL) 2026-06-15

Which Models Perform Better in Inheritance Reasoning?

作者:
Mohammed Amine Mouhoub↗Chahinez Bouchekif↗

This paper presents the participation of team PSL in the QIAS 2026 Shared Task on Arabic Islamic inheritance reasoning. The task evaluates the ability of large language models to solve inheritance cases that require legal interpretation, multi-step reasoning, and precise numerical computation. We compare commercial and open-source models under a unified prompting strategy to assess their effectiveness in structured legal reasoning with minimal task-specific adaptation. \\ Our results show a clear gap in reliability between the two model families. Commercial models demonstrate stronger performance in identifying eligible heirs, applying exclusion rules, and maintaining consistency across reasoning steps. In contrast, open-source models exhibit greater instability, particularly in cases involving dependent legal decisions and fractional share adjustments. The best performance is achieved by Gemini 2.5 Flash, with an MRE of $0.989$.

阅读与讨论 → 访问原文 →
02.
arXiv (CS.AI) 2026-06-16

Edu-Theater: A Data-Efficient Agent Framework for Scalable Learner Behavior Simulation through Staging Roll-Call

作者:
Weibo Gao↗Qi Liu↗Linan Yue↗Zheng Zhang↗Yichao Du↗Fangzhou Yao↗Ao Yu↗Zhenya Huang↗Shijin Wang↗

arXiv:2606.15225v1 Announce Type: cross Abstract: Large-scale learner-task interaction data are crucial for intelligent educational systems but are costly to collect and constrained by privacy and learner engagement. Learner simulators play a critical role in simulating scalable learner behavior without the need for continuous involvement of real learners. However, existing methods are predominantly individual-centric, pairing a simulator with each learner to iteratively infer latent knowledge states from dense interaction histories, which is both data- and computation-intensive, and fragile in cold-start scenarios. We propose a cohort-aware roll-call simulation paradigm that first constructs cohort-level proficiency priors and refines individual learner states through a small number of targeted diagnostic queries. Based on this paradigm, we introduce Edu-Theater, an LLM-powered agent system that performs cohort-aware learner simulation via a teacher agent and retrospective roll-call probing over learner logs. Edu-Theater enables scalable future behavior simulation without the need for dense per-learner histories. Experiments on two real-world datasets demonstrate that Edu-Theater achieves higher simulation accuracy with significantly fewer LLM calls, producing synthetic data that enhances downstream applications such as adaptive testing.

阅读与讨论 → 访问原文 →
03.
arXiv (CS.AI) 2026-06-17

Models Take Notes at Prefill: KV Cache Can Be Editable and Composable

作者:
Bojie Li↗

arXiv:2606.17107v1 Announce Type: cross Abstract: Prefix caching reuses prefill only across an exactly shared prefix, so one changed field invalidates the entire downstream cache. Yet overwriting the field's own key/value vectors and reusing the rest leaves the model acting on the old value. The reason, established causally across four model families: at prefill the model has already written the field-conditioned conclusion onto downstream notes; the field's own key/value drives under 1% of the decision. Read as a notebook of memoized conclusions, two capabilities follow. (1) It is editable. A salient erratum amends the notes; and with chain-of-thought, editing the field alone recovers the decision (1.00 at 8B, ~1% compute), while without CoT it is ignored. (2) It is composable. The notes are position-portable, so a precompiled skill can be RoPE-repositioned and spliced into any context, indistinguishable from full recompute (logit cosine 0.90-0.999, twelve models) at O(L) rather than O(L^2) time-to-first-token. A unified edit+compose agent stays decision-identical to recompute at up to 14.9x lower latency. The approach applies to any per-token attention KV cache, validated across scale, quantization, Mixture-of-Experts, and multimodal caches, and extends to several attention variants through small adapters. Because the erratum is append-only, it composes with production prefix caching: in an online vLLM benchmark it keeps the prefix cache-aligned (98.5% hit-rate), cutting p90 time-to-first-token by 53-398x.

阅读与讨论 → 访问原文 →
04.
arXiv (CS.CL) 2026-06-18

CEO-Bench: Can Agents Play the Long Game?

作者:
Haozhe Chen↗Karthik Narasimhan↗Zhuang Liu↗

Language model agents are becoming proficient executors at isolated, short-horizon tasks such as software engineering and customer service. Yet real-world challenges require a combination of sophisticated skills that remain largely untested in agents: (1) navigating long horizons amid uncertainty; (2) acquiring information in noisy environments; (3) adapting to a changing world; (4) orchestrating multiple moving parts toward a coherent goal. We introduce CEO-Bench, which evaluates these capabilities together by simulating a representative real-world task: operating a startup for 500 days. An agent manages pricing, marketing, budgeting, and many other aspects of a fictional company through a programmable Python interface, operating in the same environment and facing the same challenges as a human CEO. Success demands analyzing noisy, interconnected business databases, translating signals into sound strategy, and coordinating many decisions with programming. The strongest agents write sophisticated code that simulates customer cohorts to forecast future cash and mines negotiation history to uncover hidden customer preferences. Even so, most state-of-the-art models struggle in this environment. Only Claude Opus 4.8 and GPT-5.5 finish above the $1M starting balance, and neither consistently turns a profit. CEO-Bench takes a first step toward measuring the intelligence required to drive sustained, adaptive progress over time.

阅读与讨论 → 访问原文 →
05.
arXiv (CS.AI) 2026-06-16

JADE: Expert-Grounded Dynamic Evaluation for Open-Ended Professional Tasks

作者:
Lanbo Lin↗Jiayao Liu↗Tianyuan Yang↗Li Cai↗Yuanwu Xu↗Lei Wei↗Sicong Xie↗Guannan Zhang↗

arXiv:2602.06486v2 Announce Type: replace Abstract: Evaluating agentic AI on open-ended professional tasks faces a fundamental dilemma between rigor and flexibility. Static rubrics provide rigorous, reproducible assessment but fail to accommodate diverse valid response strategies, while LLM-as-a-judge approaches adapt to individual responses yet suffer from instability and bias. Human experts address this dilemma by combining domain-grounded principles with dynamic, claim-level assessment. Inspired by this process, we propose JADE, a two-layer evaluation framework. Layer 1 encodes expert knowledge as a predefined set of evaluation skills, providing stable evaluation criteria. Layer 2 performs report-specific, claim-level evaluation to flexibly assess diverse reasoning strategies, with evidence-dependency gating to invalidate conclusions built on refuted claims. Experiments on BizBench show that JADE improves evaluation stability and reveals critical agent failure modes missed by holistic LLM-based evaluators. We further demonstrate strong alignment with expert-authored rubrics and effective transfer to HealthBench and DR.BENCH, covering medical and 10-domain professional evaluation settings. Code and data are available at https://github.com/smiling-world/JADE.

阅读与讨论 → 访问原文 →
06.
arXiv (CS.CV) 2026-06-16

Structural Energy Guidance for View-Consistent Text-to-3D Generation

作者:
Qing Zhang↗Jinguang Tong↗Jing Zhang↗Jie Hong↗Xuesong Li↗

Text-to-3D generation based on diffusion models often suffers from the Janus problem, leading to inconsistent geometry across viewpoints. This work identifies viewpoint bias in 2D diffusion priors as the main cause and proposes Structural Energy-Guided Sampling (SEGS), a training-free and plug-and-play framework to improve multi-view consistency. SEGS constructs a structural energy in the PCA subspace of U-Net features and injects its gradient into the denoising process. It can be easily integrated into SDS/VSD pipelines without retraining. Experiments show that SEGS reduces the Janus Rate by about 10% on average and improves View-CS scores across multiple baselines, including DreamFusion, Magic3D, and LucidDreamer. This method effectively alleviates viewpoint artifacts while preserving appearance fidelity, providing a flexible solution for high-quality text-to-3D content generation.

阅读与讨论 → 访问原文 →
07.
arXiv (CS.CL) 2026-06-11

System Report for CCL25-Eval Task 5: New Dataset and LoRA-Fine-Tuned Qwen2.5

作者:
Haotao Xie↗

Recently, large language models (LLMs) have achieved promising progress in the fields of classical Chinese translation and the generation of classical poetry. However, domain-specific research on precise translation and affective-semantic understanding of classical poetry remains limited. The main challenge is that most studies treat the poetic appreciation task as a general-domain problem, neglecting the distinctive features of poetic appreciation, while high-quality and domain-specific datasets are extremely limited. To address this limitation, we decompose the task into three subtasks: term interpretation, semantic interpretation, and emotional inference. Based on multiple open-source datasets, we perform data cleansing and alignment to construct the Classical Chinese Poetry Instruction Pair Dataset (CCPoetry-49K), which comprises 49,404 high-quality instruction-response pairs explicitly optimized for this domain. We then propose a domain-specialized LLM, called PoetryQwen, by applying Low-Rank Adaptation (LoRA) to fine-tune the Qwen2.5-14B model. Experimental results on the CCL25-Eval Task 5 benchmark demonstrate that PoetryQwen achieves a score of 0.757, representing a 9.7% improvement over the Qwen2.5-14B-Instruct baseline (0.690). These findings clearly indicate that PoetryQwen significantly enhances performance in precise translation and emotional understanding of classical poetry. We present new dataset and methodological considerations intended to support the domain-specific optimization of LLMs.

阅读与讨论 → 访问原文 →
08.
arXiv (CS.LG) 2026-06-17

Conditional Local Importance by Quantile Expectations

作者:
Kelvyn K. Bladen↗Adele Cutler↗D. Richard Cutler↗Kevin R. Moon↗

arXiv:2411.08821v4 Announce Type: replace-cross Abstract: Global variable importance measures are commonly used to interpret the results of machine learning models. Local variable importance techniques assess how variables contribute to individual observations. Current, popular methods, including LIME and SHAP, provide useful measures of feature contribution in the prediction space, while leaving opportunities for improved characterization of local structure in the model loss space. Additionally, they are not natively adapted for multi-class classification problems. We propose a new model-agnostic method for calculating local variable importance, CLIQUE, that highlights locally dependent relationships, provides improved stability over permutation-based methods, and can be directly applied to multi-class classification problems. Simulated and real-world examples show that CLIQUE emphasizes locally dependent information, captures interaction behavior beyond what can be evaluated by correlations, and assigns zero importance in regions where the response is invariant to changes in variables.

阅读与讨论 → 访问原文 →
09.
medRxiv (Medicine) 2026-06-23

Sex-Specific Hemostatic Responses and Diagnostic Potential of Platelet Distribution Width (PDW) and D-Dimer in Mild COVID-19, Malaria, and Co-Infection in a Tropical Setting: A Case-Control Study in Port Harcourt, Nigeria

作者:
Ekprikpo↗E. S↗Jeremiah↗Z. A↗Ken-Ezihuo↗S. U↗

Background: In malaria-endemic tropical regions, the overlapping coagulopathy in COVID-19 and malaria poses diagnostic and prognostic challenges, particularly with potential sex differences. This study evaluated sex-specific variations in platelet indices and fibrinolytic markers and assessed the utility of Platelet Distribution Width (PDW) and D-dimer in mild/asymptomatic cases. Methods: A case-control study was conducted with 220 participants (55 each in healthy controls, malaria-positive, COVID-19-positive, and COVID-19+malaria co-infected groups), aged 20-65 years, in Port Harcourt, Nigeria. Platelet indices were analysed using Sysmex XP-300 haematology analyser, while D-dimer and fibrinogen were measured by ELISA. Data were analysed using SAS 9.4 with ANOVA, Tukey's HSD, Pearson correlation, and sex-stratified comparisons. Results: PDW was significantly elevated in all infected groups compared to controls (malaria: 15.21 +/- 0.22 fL; COVID-19: 15.21 +/- 0.22 fL; co-infection: 15.61 +/- 0.21 fL vs. control: 13.26 +/- 0.17 fL; F=25.850, p < 0.001). D-dimer levels were highest in the co-infected group (553.42 +/- 59.74 ng/ml, F=2.816, p = 0.040). No significant changes were observed in other platelet indices or fibrinogen across groups. No significant correlation existed between platelet indices and the fibrinolytic markers. Males exhibited significantly higher D-dimer levels across all infected groups (p < 0.05) and higher fibrinogen in COVID-19 subjects (p = 0.036). Sex exerted a stronger influence on parameters than age. Conclusion: Males show heightened fibrinolytic activation in COVID-19 and malaria co-infection. PDW and D-dimer are promising, cost-effective biomarkers for screening mild infections in resource-limited tropical settings.

阅读与讨论 → 访问原文 →
10.
medRxiv (Medicine) 2026-06-22

Why drinking episodes escalate differently: Event-level pathways linking hazardous alcohol consumption and sexual risk

作者:
Ngo↗T. P↗Dunham↗A. E↗Santos↗G.-M↗

Background: Alcohol-involved drinking episodes vary in whether they involve hazardous alcohol consumption alone, near-miss sexual risk, or sexual risk behavior, but the within-event mechanisms underlying this variability remain unclear. Methods: Guided by syndemic theory, we conducted a qualitative event-level analysis using modified grounded theory among adults in the San Francisco Bay Area who reported hazardous alcohol consumption, defined as an Alcohol Use Disorder Identification Test score [&ge;]16. In-depth interviews elicited narratives of recent heavy drinking episodes and yielded 64 discrete drinking events across 22 participants. We focused on 35 events with evidence of within-event interaction between biopsychosocial and contextual factors. Using constant comparison, we identified escalation pathways, characterized interruption, and examined how events diverge into three outcomes: hazardous alcohol consumption only, hazardous alcohol consumption with near-miss sexual risk (when risk was plausible but not enacted), and hazardous alcohol consumption with sexual risk behavior. Results: Two primary escalation pathways emerged. Dose-driven escalation involved cumulative alcohol or substance exposure that progressively impaired awareness and self-regulation. Meaning-driven escalation involved prioritizing connection, intimacy, or belonging despite awareness of risk. Time-driven continuation extended exposure across contexts and amplified both pathways. Hazardous alcohol consumption-only events more often followed dose-driven pathways, whereas events involving sexual risk behavior more often followed meaning-driven pathways. Near-miss events occurred across both pathways and illustrated how interruption before the escalation constraint point, when the capacity to modify behavior became reduced, could redirect escalation before sexual risk behavior occurred. Across events with similar levels of intoxication narratives, outcomes diverged according to when the interruption occurred and whether it altered escalation. Conclusion: Hazardous drinking episodes diverge into different outcomes based on escalation pathways and the timing and effectiveness of interruption. Early and effective interruption before the escalation constraint point may represent a key target for harm-reduction strategies to prevent progression to sexual risk behavior.

阅读与讨论 → 访问原文 →
11.
bioRxiv (Bioinfo) 2026-06-18

Benchmarking gene expression reconstruction from single-cell latent representations

作者:
Fu↗Klein↗Antipov↗Palma↗Tejada-Lapuerta↗Bahrami↗Kummerle↗L. B↗Lubetzki↗Casale↗F. P↗Luecken↗…

Single-cell transcriptomics is typically modeled in low-dimensional latent representations that improve the signal-to-noise ratio of the data. Such representations underpin data integration, cell state discovery, and perturbation prediction, with applications ranging from large-scale organ atlases to latent trajectory modeling. Recent virtual cell approaches further leverage these representations to predict cellular responses as distributional shifts in latent space. Each of these applications ultimately requires faithful gene expression reconstruction from latent spaces for biological interpretation, enabling gene-level analysis of predicted perturbed or batch-corrected cells. Yet representation choice is typically treated as an implementation detail rather than a primary modeling decision, with no systematic evaluation of how well latent representations support gene expression reconstruction. Here, we introduce ReconEval, a benchmark for evaluating gene expression reconstruction from single-cell latent spaces. We benchmark two classes of latent representations: end-to-end trained models such as PCA, autoencoders, and variational autoencoders, and pretrained single-cell foundation model embeddings coupled to newly trained decoders. Reconstruction is evaluated both directly and after latent-space perturbation prediction. Across perturbational and observational datasets totaling over 100 million cells, our metric suite quantifies statistical fidelity; biological signal preservation, including differential expression, coexpression, cell-cycle structure, cytokine response and pathway activity; and perturbation-specific effects. We find that autoencoders achieve the strongest stand-alone reconstruction at low dimensionality, while variational regularization does not improve generalization in reconstruction. Frozen foundation model embeddings retain recoverable gene-level information, with reconstruction quality depending strongly on decoder architecture and pretraining objective. In latent perturbation modeling, high-dimensional PCA matches foundation model embeddings, while low-dimensional AE embeddings are optimal for flow-based generative models. Overall, reconstruction depends critically on the interplay between representation and downstream model, and simpler representations can outperform complex alternatives given appropriate capacity. Our benchmark establishes reconstruction as a critical evaluation axis for single-cell foundation models. We envision it improving the biological interpretability of latent-space modeling, a prerequisite for future virtual cell models to be validated by domain experts and grounded in biology.

阅读与讨论 → 访问原文 →
12.
arXiv (CS.CV) 2026-06-15

CaricHarmony: Contrastive Diffusion Paths for Identity-Preserving Caricature Synthesis

作者:
Dongyu Wang↗Dar-Yen Chen↗Yi-Zhe Song↗

Sketch-based caricature synthesis suffers from a fundamental failure mode: when identity and shape conditions are combined in diffusion models, they create destructive interference that causes inevitable collapse toward either bland portraits or unrecognizable distortions. We identify the root cause as condition signal contamination – competing probability distributions in the denoising trajectory that make balanced generation impossible. We present CaricHarmony, the first training-free method that explicitly resolves this contamination through parallel uncontaminated diffusion paths. During inference, we maintain three paths: $\mathcal{P}^{\mathrm{i}}$ (pure identity), $\mathcal{P}^{\mathrm{s}}$ (pure shape), and $\mathcal{P}^{\mathrm{i+s}}$ (harmonized output). Novel energy functions operating on cross-attention features provide gradient guidance that steers $\mathcal{P}^{\mathrm{i+s}}$ toward optimal balance: $\mathcal{E}_{\mathrm{shape}}$ ensures sketch fidelity through layout and semantic alignment, while $\mathcal{E}_{\mathrm{id}}$ employs token-level correspondence matching robust to extreme distortions. Unlike DemoCaricature requiring 70 seconds per-identity fine-tuning or CaricatureBooth constrained to Bezier curves, CaricHarmony accepts any sketch format and generates in under 16 seconds. Experiments demonstrate state-of-the-art performance: 0.8615 shape CLIP score (vs. 0.8450) under comparable identity consistency score, with 7.81 overall user preference score (vs. 6.06). Our method fundamentally reconceptualizes the ID-shape conflict as conditioning signal contamination for diffusion models, enabling unprecedented creative control while preserving recognition.

阅读与讨论 → 访问原文 →
13.
arXiv (CS.CV) 2026-06-16

Mind the Gap: Diagnosing Constraint Discovery Failures in Text-in-Image Editing

作者:
Rui Gui↗

A key challenge in multimodal reasoning is determining which visual dependencies become relevant under a specific task, rather than merely recognizing visible content. We study this through edit-induced constraint discovery in text-in-image editing, a controlled diagnostic setting where a local text change can activate secondary consistency constraints: given a valid editing instruction and an image, can a model identify the secondary regions that must also change? Across 461 diagnostic cases, four MLLMs, and 19 constraint subtypes, models recover only 46% case-level macro recall under unguided prompting versus 94% when constraints are explicitly provided, suggesting that a substantial portion of the failure arises when models must decide which unstated dependencies to surface. Oracle-field decomposition shows that case-specific causal explanations are the most effective partial guidance (0.782 recall), above region names (0.610) or type labels (0.646), suggesting that edit-specific causal cues account for much of the oracle gain. A downstream experiment further shows that higher self-discovery recall does not necessarily improve task performance: unverified self-discovery introduces false positives that offset recall gains, motivating precision-aware constraint elicitation.

阅读与讨论 → 访问原文 →
14.
arXiv (CS.LG) 2026-06-12

Multi-Token Residual Prediction

作者:
Yufeng Xu↗Zishuo Bao↗Qian Wang↗Zeshen Zhang↗Haoqi Zhang↗Bowen Peng↗Ang Li↗Rahul Chalamala↗Yucheng Lu↗

arXiv:2605.18817v2 Announce Type: replace Abstract: Diffusion Language Models (DLMs) generate text by iteratively denoising masked token sequences, offering a tradeoff between parallelism and quality compared to autoregressive models. In current practice, the number of tokens decoded per step is controlled by a confidence threshold, and quality degrades monotonically as more tokens are denoised per step. We introduce Multi-token Residual Prediction (MRP), a lightweight module that enables dependency-aware multi-token denoising within a single backbone forward pass. MRP exploits a key property of the denoising process: the logit distributions at adjacent denoising steps are remarkably similar. Rather than running the backbone a second time to obtain the next-step logits, MRP predicts the residual between steps from the backbone's hidden states, effectively denoising more tokens per backbone forward at a fraction of the cost. We apply MRP across the two operating regimes of DLM decoding. In the high-quality-low-throughput static denoising regime, MRP serves as a drafter for speculative decoding: its proposals are verified against the backbone, yielding lossless acceleration of up to 1.4x in SGLang. In the low-quality-high-throughput dynamic denoising regime, MRP instead drives a remasking scheme that revokes over-eager reveals, recovering most of the accuracy lost to aggressive low-threshold decoding and improving accuracy by up to 22.6 points on code generation task HumanEval and 17.7 points on reasoning task GSM8K.

阅读与讨论 → 访问原文 →
15.
arXiv (CS.CV) 2026-06-12

Zero-Shot Captioning for Cultural Heritage: Automated Image Analysis of Traditional Indonesian Clothing

作者:
Anugrah Aidin Yotolembah↗Novanto Yudistira↗Gembong Edhi Setyawan↗

This paper presents Custom ZeroCLIP, a retrieval-augmented vision-language framework for zero-shot captioning of Indonesian traditional garments. The dataset contains 3,800 expert-annotated images from all 38 Indonesian provinces. Using a province-level inductive zero-shot protocol, the model is trained on 24 seen provinces, validated on 6 seen provinces, and evaluated on 8 unseen provinces. The framework combines a frozen CLIP ViT-B/32 image encoder, a CLIP text encoder, a BERT text encoder, and an LSTM caption decoder. During inference, unseen-province labels and captions are unavailable, and retrieval uses only captions from training provinces. No unseen-province image, label, or caption is used during training, validation, or retrieval-bank construction. Custom ZeroCLIP achieves a CLIPScore of 0.8536, BLEU-4 of 0.3342, and METEOR of 0.4859, outperforming existing baselines. Ablation results show that retrieval improves cultural vocabulary recovery with a 19.3\% METEOR gain, while human evaluation confirms stronger cultural accuracy and fluency. The results demonstrate the effectiveness of retrieval-augmented domain adaptation for culturally grounded caption generation in low-resource heritage settings. The dataset is publicly available at https://github.com/AnugrahAidinYotolembah/Traditional-Indonesian-Clothing-Captioning-Dataset.

阅读与讨论 → 访问原文 →
16.
arXiv (CS.LG) 2026-06-15

On Rate-Optimal Partitioning Classification from Observable and from Privatised Data

作者:
Bal\'azs Csan\'ad Cs\'aji↗L\'aszl\'o Gy\"orfi↗Ambrus Tam\'as↗Harro Walk↗

arXiv:2312.14889v4 Announce Type: replace-cross Abstract: In this paper we revisit the classical method of partitioning classification and prove novel convergence rates under relaxed conditions, both for observable (non-privatised) and for privatised data. We consider the problem of classification in a $d$ dimensional Euclidean space. Previous results on the partitioning classifier worked with the strong density assumption (SDA), which is restrictive, as we demonstrate through simple examples. Here, we study the problem under much milder assumptions. We presuppose that the distribution of the inputs is a mixture of an absolutely continuous and a discrete distribution, such that the absolutely continuous component is concentrated on a $d_a$ dimensional subspace. In addition to the standard Lipschitz and margin conditions, a novel characteristic of the absolutely continuous component is introduced, by which the convergence rate of the classification error probability is computed, both for the binary and for the multi-class cases. This bound can reach the minimax optimal convergence rate achievable using SDA, but under much milder distributional assumptions. Interestingly, this convergence rate depends only on the intrinsic dimension of the continuous inputs, $d_a$, and not on $d$. Under privacy constraints, the data cannot be directly observed, and the constructed classifiers are functions of the randomised outcome of a suitable local differential privacy mechanism. In this paper we add Laplace distributed noises to the discretisations of all possible locations of the feature vector and to its label. Again, tight upper bounds on the convergence rate of the classification error probability can be derived, without using SDA, such that this rate depends on $2d_a$.

阅读与讨论 → 访问原文 →
17.
arXiv (CS.CL) 2026-06-11

Calibration Drift Under Reasoning: How Chain-of-Thought Budgets Induce Overconfidence in Large Language Models

作者:
Prakul Sunil Hiremath↗Harshit R. Hiremath↗

The ability of large language models (LLMs) to express calibrated uncertainty is important for safe deployment. Chain-of-thought (CoT) reasoning is widely used to improve accuracy and reliability, but its effect on calibration is not fully understood. We show that this picture is incomplete: in some settings, increasing the reasoning budget beyond a task-specific threshold can cause models to become systematically overconfident, assigning high confidence to incorrect answers. We call this phenomenon Calibration Drift Under Reasoning (CDUR) and study it both theoretically and empirically. We define reasoning budget B and analyze conditions under which Expected Calibration Error ECE(B) follows a non-monotonic pattern: it first decreases as reasoning corrects errors, then increases as longer reasoning produces internally consistent but incorrect explanations. We propose a Hypothesis Lock-In model based on autoregressive generation to explain this behavior. We evaluate Llama-3.1-8B and Llama-3.3-70B on 47 reasoning-trap questions across four reasoning budgets and three seeds (1,368 API calls; 574 valid responses). The 8B model shows non-monotonic calibration behavior, while results for the 70B model are limited to baseline evaluation and are inconclusive for budget-dependent effects. We introduce CABStop, a calibration-aware stopping rule that halts reasoning when confidence diverges from an auxiliary accuracy estimate. These results suggest that increasing reasoning depth does not always improve reliability and should be monitored carefully.

阅读与讨论 → 访问原文 →
18.
medRxiv (Medicine) 2026-06-16

Development and reliability and validity test of the Questionnaire on Knowledge, Attitude and Practice of ICU Nurses on Blood Oxygen Saturation Management in Mechanically Ventilated Patients

作者:
Xie↗Bian↗Yu↗He↗

Objective: A questionnaire on the knowledge, attitude and practice of ICU nurses regarding the management of blood oxygen saturation in patients with mechanical ventilation was compiled, and its reliability and validity were tested. Method: Drawing upon the knowledge-attitude-practice theory, the initial questionnaire draft was developed through literature review and consultation with Delphi experts. Employing convenience sampling, 32 nurses from the General ICU of Wuxi Second People's Hospital were surveyed between 1 August 2025 and 27 September 2025, enabling item screening and assessment of reliability and validity.The full version of the developed questionnaire is provided as Supporting Information (S1 File). All items are published under a CC BY 4.0 license, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Result: A questionnaire on the knowledge, attitude and practice of ICU nurses regarding the management of blood oxygen saturation in mechanically ventilated patients was finalised, comprising 26 items: 11 in the knowledge dimension, 6 in the attitude dimension and 9 in the behaviour dimension. The overall Cronbach's coefficient for the questionnaire was 0.88, with dimension-specific coefficients of 0.787, 0.722, and 0.781 respectively. The Spearman-Brown coefficient for the entire questionnaire was 0.967, while dimension-specific coefficients were 0.796, 0.666, and 0.728 respectively. The content validity index at the questionnaire level (S-CVI) was 0.886, and the item-level content validity index (I-CVI) ranged from 0.913 to 0.967. 0.728. The questionnaire's level content validity index (S-CVI) was 0.886, and the item level content validity index (I-CVI) ranged from 0.913 to 1.00. Conclusion: The questionnaire on knowledge, attitude and practice of blood oxygen saturation management in mechanically ventilated patients demonstrates good reliability and validity. It may serve as an assessment tool for intensive care unit nurses regarding their knowledge, attitude, and practices concerning blood oxygen saturation management in mechanically ventilated patients, thereby establishing a foundation for developing targeted intervention strategies in future practice.

阅读与讨论 → 访问原文 →
19.
arXiv (quant-ph) 2026-06-16

How Many Shots Are Enough for a Quantum Circuit?

作者:
Giuseppe Bisicchia↗Alessandro Bocci↗Ernesto Pimentel↗Antonio Brogi↗

arXiv:2606.16965v1 Announce Type: new Abstract: Quantum algorithms require repeated circuit executions, known as shots, to estimate output distributions accurately. Determining the minimal number of shots needed to meet a target accuracy is crucial to reduce costs and resource usage, especially on today's noisy and expensive quantum hardware. In this paper, we address the shot optimisation problem in a black-box setting, where no assumptions are made about the structure of the quantum circuit or the noise model of the backend. We introduce IncrementalExecution, a novel online framework that dynamically determines when to stop executing shots based on the principle of point of diminishing returns: the point at which additional shots no longer significantly alter the empirical distribution of a fixed circuit. The framework supports customisable policies for shot management, enabling flexible trade-offs between execution cost and result fidelity within static execution scenarios. We assess our proposal through an extensive experimental evaluation spanning 33,750 framework configurations across 180 unique static quantum circuit-backend combinations, for a total of 7.3M independent experiments. Unlike prior work that relies on problem-specific knowledge or algorithm-dependent assumptions (e.g., variational or adaptive workflows), our approach is applicable to a large set of static circuits and immediately deployable on current quantum cloud platforms.

阅读与讨论 → 访问原文 →
20.
arXiv (CS.LG) 2026-06-16

InfoNCE Induces Gaussian Distribution

作者:
Roy Betser↗Eyal Gofer↗Meir Yossef Levi↗Guy Gilboa↗

arXiv:2602.24012v2 Announce Type: replace Abstract: Contrastive learning has become a cornerstone of modern representation learning, allowing training with massive unlabeled data for both task-specific and general (foundation) models. A prototypical loss in contrastive training is InfoNCE and its variants. In this work, we show that the InfoNCE objective induces Gaussian structure in representations that emerge from contrastive training. We establish this result in two complementary regimes. First, we show that under certain alignment and concentration assumptions, projections of the high-dimensional representation asymptotically approach a multivariate Gaussian distribution. Next, under less strict assumptions, we show that adding a small asymptotically vanishing regularization term that promotes low feature norm and high feature entropy leads to similar asymptotic results. We support our analysis with experiments on synthetic and CIFAR-10 datasets across multiple encoder architectures and sizes, demonstrating consistent Gaussian behavior. This perspective provides a principled explanation for commonly observed Gaussianity in contrastive representations. The resulting Gaussian model enables principled analytical treatment of learned representations and is expected to support a wide range of applications in contrastive learning.

阅读与讨论 → 访问原文 →
21.
arXiv (CS.AI) 2026-06-16

Nightjar: Dynamic Adaptive Speculative Decoding for Large Language Models Serving

作者:
Rui Li↗Zhaoning Zhang↗Libo Zhang↗Huaimin Wang↗Xiang Fu↗Zhiquan Lai↗

arXiv:2512.22420v5 Announce Type: replace-cross Abstract: Speculative decoding (SD) accelerates LLM inference by verifying draft tokens in parallel. However, this method presents a critical trade-off: it improves throughput in low-load, memory-bound systems but degrades performance in high-load, compute-bound environments due to verification overhead. Existing speculative decoding methods use fixed lengths and cannot adapt to workload changes or decide when to stop speculation. The cost of restarting speculative inference also remains unquantified. Under high load, the benefit of speculation diminishes, while retaining the draft model reduces KV cache capacity, limiting batch size and degrading throughput. To overcome this, we propose Nightjar, a resource-aware adaptive speculative framework. It first adjusts to the request load by dynamically selecting the optimal speculative length for different batch sizes. Crucially, Nightjar proactively disables speculative decoding when the MAB planner determines that speculation is no longer beneficial, and during the disabled phase, offloads the draft model to the CPU only under GPU memory pressure. This reclaims memory for the KV cache, thereby facilitating larger batch sizes and maximizing overall system throughput. Experiments show that Nightjar achieves up to 14.76% higher throughput than standard speculative decoding and up to 20.18% lower latency in the main benchmark suite under dynamic request arrival rates for real-time LLM serving scenarios.

阅读与讨论 → 访问原文 →
22.
arXiv (CS.AI) 2026-06-16

The Proxy Knows Too Much: Sealing LLM API Routers with Attested TEEs

作者:
Sipeng Xie↗Qianhong Wu↗Hengrun Lu↗Ziliang Sun↗Qi Wu↗Bo Qin↗Qin Wang↗

arXiv:2606.16358v1 Announce Type: cross Abstract: Agents increasingly access large language models (LLMs) through API routers. A router terminates the client's transport-layer security session and opens a separate upstream session, so it holds the full interaction in plaintext. This makes the router an application-layer man-in-the-middle: it can rewrite agent tool calls, swap dependencies for typosquatted packages, trigger attacks only under audit-evading conditions, and passively exfiltrate secrets. Existing client-side defenses are evadable. We propose AEGIS, a provider-transparent attested API router whose data path is a client-verified faithful passthrough. AEGISconfines plaintext handling to a small hardware-enclave component while leaving authentication, scheduling, accounting, and management on the untrusted host. The client verifies the enclave before releasing plaintext. The host can neither read nor alter the interaction, and plaintext leaves only toward destinations fixed by the measured image. We show that all four malicious-router attack classes succeed against a plaintext-access baseline and are blocked by AEGIS, including adaptive tests against the same boundary. The trusted path is $851$ lines, carries three provider-native APIs without conversion, and completes every request under real-provider workload and concurrency. In a seeded audit pilot, two commodity coding agents find eight and ten of ten planted invariant violations. The local relay overhead is about six milliseconds per request.

阅读与讨论 → 访问原文 →
23.
arXiv (CS.CV) 2026-06-17

Advances in 4D Representation: Geometry, Motion, and Interaction

作者:
Mingrui Zhao↗Sauradip Nag↗Kai Wang↗Aditya Vora↗Guangda Ji↗Peter Chun↗Ali Mahdavi-Amiri↗Hao Zhang↗

We present a survey on 4D generation and reconstruction, a fast-evolving subfield of computer graphics whose developments have been propelled by recent advances in neural fields, geometric and motion deep learning, as well as 3D generative artificial intelligence (GenAI). While our survey is not the first of its kind, we build our coverage of the domain from a unique and distinctive perspective of 4D representations, to model 3D geometry evolving over time while exhibiting motion and interaction. Specifically, instead of offering an exhaustive enumeration of many works, we take a more selective approach by focusing on representative works to highlight both the desirable properties and ensuing challenges of each representation under different computation, application, and data scenarios. The main take-away message we aim to convey to the readers is on how to select and then customize the appropriate 4D representations for their tasks. Organizationally, we separate the 4D representations based on three key pillars: geometry, motion, and interaction. Our discourse will not only encompass the most popular representations of today, such as neural radiance fields (NeRFs) and 3D Gaussian Splatting (3DGS), but also bring attention to relatively under-explored representations in the 4D context, such as structured models and long-range motions. Throughout our survey, we will reprise the role of large language models (LLMs) and video foundational models (VFMs) in a variety of 4D applications, while steering our discussion towards their current limitations and how they can be addressed. We also provide a dedicated coverage on what 4D datasets are currently available, as well as what is lacking, in driving the subfield forward. Project page:https://mingrui-zhao.github.io/4DRep-GMI/

阅读与讨论 → 访问原文 →
24.
arXiv (CS.CL) 2026-06-11

SOMA-SQL: Resolving Multi-Source Ambiguity in NL-to-SQL via Synthetic Log and Execution Probing

作者:
Sai Ashish Somayajula↗Marianne Menglin Liu↗Chuan Lei↗Fjona Parllaku↗Daniel Garcia↗Rongguang Wang↗Syed Fahad Allam Shah↗Ankan Bansal↗Sujeeth Bharadwaj↗Tao Sheng↗Sujith Ravi↗Dan Roth↗…

Natural language interfaces to databases aim to translate user questions into executable SQL, yet remain brittle in real-world settings where questions are underspecified and schemas are large and ambiguous. Ambiguity across user questions, database schemas, and model interpretations are central failure modes in NL2SQL, leading to misaligned intent, incorrect schema grounding, and erroneous SQL generation. Existing approaches rely on human clarification or treat ambiguity as a schema representation problem, but these do not scale nor resolve ambiguity autonomously. We propose SOMA-SQL to automatically resolve ambiguity via targeted synthetic query log and ambiguity-driven probing. SOMA-SQL constructs synthetic query log to ground schema interpretation and guide candidate SQL generation; it then executes targeted probing queries, driven by a structured ambiguity taxonomy and candidate disagreements, to produce disambiguation evidence for final SQL selection and repair. This active approach to ambiguity discovery and resolution generalizes across unseen schemas and query distributions without human-in-the-loop. Experiments on six public benchmarks demonstrate that SOMA-SQL improves execution accuracy by 13.0% on average over state-of-the-art baselines, with gains of up to 16.7% on ambiguous questions.

阅读与讨论 → 访问原文 →
25.
arXiv (quant-ph) 2026-06-15

Calibrated Helstrom geometry on the Bloch ball via Connes spectral distance

作者:
Kaushlendra Kumar↗

arXiv:2606.13824v1 Announce Type: new Abstract: We show that the equal-prior Helstrom trace-distance geometry of qubit states is recovered from Connes spectral distance in a finite scalar-qubit-scalar model. The two scalar reference sectors couple isotropically to the qubit block through identity Dirac links, so that the full Bloch ball, including mixed states, inherits its standard chordal trace-distance geometry from the finite spectral metric. The scalar-sector distances serve a distinct calibration role: they determine the individual link lengths, satisfy a Pythagorean consistency relation, and reconstruct the middle-sector scale.

阅读与讨论 → 访问原文 →