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.AI) 2026-06-12

Examining the Usage of Generative AI Models in Student Learning Activities for Software Programming

作者:
Rufeng Chen↗Shuaishuai Jiang↗Jiyun Shen↗AJung Moon↗Lili Wei↗

arXiv:2511.13271v2 Announce Type: replace-cross Abstract: The rise of Generative AI (GenAI) tools like ChatGPT has created new opportunities and challenges for computing education. Existing research has primarily focused on GenAI's ability to complete educational tasks and its impact on student performance, often overlooking its effects on knowledge gains. In this study, we investigate how GenAI assistance compares to conventional online resources in supporting knowledge gains across different proficiency levels. We conducted a controlled user experiment with 24 undergraduate students of two different levels of programming experience (beginner, intermediate) to examine how students interact with ChatGPT while solving programming tasks. We analyzed task performance, conceptual understanding, and interaction behaviors. Our findings reveal that generating complete solutions with GenAI significantly improves task performance, especially for beginners, but does not consistently result in knowledge gains. Importantly, usage strategies differ by experience: beginners tend to rely heavily on GenAI toward task completion often without knowledge gain in the process, while intermediates adopt more selective approaches. We find that both over-reliance and minimal use result in weaker knowledge gains overall. Based on our results, we call on students and educators to adopt GenAI as a learning rather than a problem solving tool. Our study highlights the urgent need for guidance when integrating GenAI into programming education to foster deeper understanding.

阅读与讨论 → 访问原文 →
02.
arXiv (CS.LG) 2026-06-18

Stochastic Thermodynamics and SDE-based Generative Models

作者:
Yaowen Zhang↗

arXiv:2606.18290v1 Announce Type: cross Abstract: SDE-based generative models, including diffusion models and the Schrödinger bridge, have found broad applications in signal processing tasks such as speech enhancement, image restoration, and time-series generation. This note presents a modeling framework for such models within the context of stochastic thermodynamics. The main results of this note are trajectory-level definitions of work, heat, and entropy production, along with a generalized Jarzynski identity and a second-law-like inequality. The proposed framework extends the original Jarzynski setup to accommodate time-dependent bath temperature and nonconservative driving forces. This thermodynamic perspective may deepen our understanding of diffusion models and the Schrödinger bridge from a nonequilibrium statistical mechanics viewpoint.

阅读与讨论 → 访问原文 →
03.
arXiv (quant-ph) 2026-06-19

Applications of quantum annealing to magnetic dipole hyperfine structure constants: First results beyond energies for atoms

作者:
Boni Paul↗Subimal Deb↗Per J\"onsson↗J\"orgen Ekman↗Bhanu Pratap Das↗

arXiv:2606.20166v1 Announce Type: new Abstract: We report the first results of the magnetic dipole hyperfine structure (HFS) constants of neutral $\mathrm{Li}$, Li-like $\mathrm{Be}$, neutral $\mathrm{Na}$, and Na-like $\mathrm{Mg}$ using a modified version of the Quantum Annealer Eigensolver (QAE) algorithm on D-Wave's quantum hardware. The results are benchmarked against relativistic configuration interaction with multiconfiguration Dirac Hartree-Fock (MCDHF) calculations using the General-purpose Relativistic Atomic Structure Package (GRASP), and simulated annealing. In our modified QAE, a zooming-and-sigma-annealing approach with a floating-point encoding scheme is adopted to estimate the ground-state eigenvalue and eigenvector of the relativistic Dirac-Coulomb Hamiltonian matrices ($H_{\mathrm{DC}}$) constructed from 11 or fewer configuration state functions (CSFs). For calculations with extended correlation orbital sets, we applied a CSF truncation scheme, retaining only CSFs (up to 12) that make significant contributions to the ground-state wavefunction. Our modified QAE precision is kept limited to three decimal places (up to 10 qubits). Hardware demonstrations on the D-Wave quantum processing unit (QPU) yielded results that were completely consistent with GRASP (at the chosen precision) in determining the magnetic dipole HFS constants, with accuracy varying across systems and $H_{\mathrm{DC}}$ matrix dimensions.

阅读与讨论 → 访问原文 →
04.
arXiv (CS.AI) 2026-06-24

Beyond Trajectory Imitation: Strategy-Guided Policy Optimization for LLM Reasoning

作者:
Tianyuan Shi↗Canbin Huang↗Bei Li↗Xin Chen↗Xiaojun Quan↗Jingang Wang↗Qifan Wang↗

arXiv:2606.24064v1 Announce Type: new Abstract: Distilling reasoning capabilities from strong to weak language models typically involves imitating specific solution trajectories, effectively transferring what to answer rather than how to reason. This trajectory-level imitation encourages memorization of instance-specific steps rather than acquisition of transferable problem-solving skills, limiting generalization to novel problems. We propose Strategy-Guided Policy Optimization (SGPO), which replaces instance-level trajectory imitation with reusable strategy distillation. SGPO extracts structured strategy descriptions from strong-model responses and, for each problem, constructs both autonomous and strategy-guided trajectories to enable direct comparison of the model's behavior with and without strategic guidance. The framework then addresses two key questions. For how to distill, a token-level forward-KL objective selectively transfers the distributional shift induced by strategy conditioning into the unguided policy, with proximal constraints ensuring stability. For when to distill, adaptive instance-level weighting strengthens guidance when autonomous exploration falls short and reduces it as the model's own competence grows. Experiments on four mathematical benchmarks across two model families show that SGPO consistently outperforms SFT, on-policy RL, and hybrid-policy baselines, improving the average score by 2.2 points over the strongest baseline on Qwen2.5-7B-Instruct. Analysis reveals that the forward-KL objective provides an inherently selective distillation signal that outperforms direct trajectory imitation, and that strategy distillation exhibits complementary scaling with base model capability.

阅读与讨论 → 访问原文 →
05.
arXiv (CS.AI) 2026-06-24

RIFT-Bench: Dynamic Red-teaming For Agentic AI Systems

作者:
Yarin Yerushalmi Levi↗Roy Betser↗Amit Giloni↗Lidor Erez↗Itay Gershon↗Oren Rachmil↗Sindhu Padakandla↗Roman Vainshtein↗

arXiv:2606.23927v1 Announce Type: new Abstract: Agentic AI systems powered by large language models (LLMs) are rapidly evolving into autonomous decision-making systems, exposing attack vectors beyond those of traditional LLM vulnerabilities. Existing security evaluations are often tied to specific implementations or domains, limiting unified comparison across heterogeneous systems. To address this gap, we introduce RIFT-Bench, a graph representation-driven methodology for dynamic red-teaming that enables unified evaluations across diverse agentic architectures. Building on a novel hierarchical representation, RIFT-Bench operates in two automated phases: Discovery, which extracts system structure, and Scanning, which deploys adaptive adversarial attacks and produces a comprehensive evaluation report. It evaluates the examined system itself, leveraging a broad set of dynamically adaptable adversarial probes across diverse attack vectors and objectives. We demonstrate the effectiveness of the proposed evaluation pipeline across 45 agentic systems spanning a diverse range of implementations, showing that the approach generalizes effectively to heterogeneous agentic architectures. Beyond systems and attacks, RIFT-Bench also supports direct evaluation of mitigation strategies. These key capabilities make RIFT-Bench a scalable foundation for security evaluation of agentic AI systems.

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

MAF: Multimodal Adaptive Few-shot Prompting for Sentiment Analysis with MLLMs

作者:
Hangling Xie↗

Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in understanding complex multimodal content. However, their performance in sentiment analysis exhibits acute sensitivity to prompt design, rendering static, uniformly applied prompts inherently suboptimal for capturing the nuanced multimodal cues that vary across inputs. To address this limitation, we propose a Multimodal Adaptive Few-Shot Prompting (MAF) framework, which dynamically retrieves and integrates query-relevant demonstrations to elicit the sentiment reasoning capabilities of MLLMs in a context-sensitive manner. MAF constructs a demonstration retrieval module that holistically encodes facial expressions, scene context, and textual semantics, with a lip movement amplitude detection mechanism introduced for accurate speaker identification in multi-person scenarios. Departing from conventional fixed-weight fusion, a lightweight coefficient generation network is trained to output query-conditioned fusion weights in real time, enabling weighted aggregation of multimodal similarity scores to retrieve the top-K most informative demonstrations. Prediction stability is further enhanced through majority voting over multiple candidate outputs generated by the MLLM. Extensive experiments on public benchmark datasets demonstrate that MAF achieves substantial and consistent performance improvements over the corresponding backbone variants and remains competitive with strong multimodal sentiment-analysis baselines.

阅读与讨论 → 访问原文 →
07.
arXiv (CS.CL) 2026-06-16

Do LLMs Reliably Identify Correct Information Units in Aphasic Discourse?

作者:
Jason M Pittman↗Yesenia Medina-Santos↗Anton Phillips Jr↗Brielle C. Stark↗

Correct Information Units (CIUs) are central to discourse assessment in aphasia because they quantify communicative informativeness rather than linguistic form alone. However, CIU scoring is time intensive and requires trained raters. This study examined whether instruction-tuned large language models (LLMs) can reliably perform token-level CIU classification from aphasic discourse transcripts. Sixteen picture-description transcripts elicited with the Cat Rescue stimulus were annotated for CIU status according to Nicholas and Brookshire (1993). The sample spanned four severity strata: control, mild, moderate, and severe aphasia. Four publicly available instruction-tuned LLMs were benchmarked under zero-shot and two few-shot prompting conditions across five stratified random seeds. Performance was evaluated against consensus human labels using accuracy, precision, recall, F1, and Cohen's kappa. Zero-shot prompting was insufficient across models. In contrast, few-shot prompting yielded substantial gains and produced competitive performance for three viable models. Mean few-shot F1 scores ranged from 0.776 to 0.817 across Llama-3.1-8B, Qwen2.5-7B, and Mistral-7B, with no significant differences between fixed global and per-chunk local example selection. Phi-3-mini was unstable and did not yield reliable performance. Viable models showed high recall but lower precision, suggesting systematic over-classification of tokens as CIUs. Performance also varied by discourse severity, with the weakest results in more severe aphasia. Few-shot LLM prompting can support automated CIU identification without gradient-based task training, but agreement with human annotation remains insufficient for fully autonomous use. These findings support LLM-based CIU scoring as a promising human-in-the-loop component of discourse assessment systems.

阅读与讨论 → 访问原文 →
08.
arXiv (CS.AI) 2026-06-12

ARROW: Augmented Replay for RObust World models

作者:
Abdulaziz Alyahya↗Abdallah Al Siyabi↗Markus R. Ernst↗Luke Yang↗Levin Kuhlmann↗Gideon Kowadlo↗

arXiv:2603.11395v3 Announce Type: replace-cross Abstract: Continual reinforcement learning challenges agents to acquire new skills while retaining previously learned ones with the goal of improving performance in both past and future tasks. Most existing approaches rely on model-free methods with replay buffers to mitigate catastrophic forgetting; however, these solutions often face significant scalability challenges due to large memory demands. Drawing inspiration from neuroscience, where the brain replays experiences to a predictive World Model rather than directly to the policy, we present ARROW (Augmented Replay for RObust World models), a model-based continual RL algorithm that extends DreamerV3 with a memory-efficient, distribution-matching replay buffer. Unlike standard fixed-size FIFO buffers, ARROW maintains two complementary buffers: a short-term buffer for recent experiences and a long-term buffer that preserves task diversity through intelligent sampling. We evaluate ARROW on two challenging continual RL settings: Tasks without shared structure (Atari), and tasks with shared structure, where knowledge transfer is possible (Procgen CoinRun variants). Compared to model-free and model-based baselines with replay buffers of the same-size, ARROW demonstrates substantially less forgetting on tasks without shared structure, while maintaining comparable forward transfer. Our findings highlight the potential of model-based RL and bio-inspired approaches for continual reinforcement learning, warranting further research.

阅读与讨论 → 访问原文 →
09.
arXiv (CS.CV) 2026-06-16

Post-Launch Capability Expansion of Vision-Language Models via Prompting for On-Orbit Spacecraft Inspection

作者:
Nicholas A. Welsh↗Lennon J. Shikhman↗Monty Nehru Attazs↗Seemanthini K. Putane↗Van Minh Nguyen↗Ryan T. White↗

Spaceborne inspection systems often deploy perception models prior to launch, after which updating model weights or expanding fixed label sets becomes operationally impractical. While supervised models can be integrated pre-flight, adding new semantic capabilities in orbit requires retraining and re-uploading parameters. We investigate whether prompt-driven vision–language models can enable post-launch semantic expansion, allowing new spacecraft components to be specified via natural-language prompts without modifying onboard weights. We evaluate zero-shot instance segmentation of spacecraft components under a strictly frozen, single-pass inference protocol on a test set of $129$ images of previously unseen satellites. Under fixed global thresholds and no post-processing, SAM3 achieves $0.385$ mAP@$0.5$ and $0.267$ mAP@$0.5{:}0.95$. Performance is strongly scale-dependent: large structural elements like spacecraft bodies ($0.639$ AP@$0.50$) and solar arrays ($0.598$ AP@$0.5$) localize reliably, while relatively small appendages like antennas ($0.221$ AP@$0.5$) and thrusters ($0.081$ AP@$0.5$) remain difficult. Prompt formulation influences performance, with structured prompts incorporating spatial and geometric descriptors yielding up to $82%$ improvement over short category-name prompts. The model operates within the memory and compute envelope of contemporary embedded GPUs, suggesting prompt-driven grounding can provide a practical mechanism for post-launch semantic extension of dominant spacecraft structures while highlighting limitations of zero-shot localization for fine-scale components under orbital domain shift.

阅读与讨论 → 访问原文 →
10.
arXiv (CS.LG) 2026-06-16

Beyond Defensive Reporting: Machine Learning for Active Anti-Money Laundering Control in Insurance

作者:
Dara Goldar↗Geir Kjetil Ferkingstad Sandve↗Martin Jullum↗

arXiv:2606.16663v1 Announce Type: new Abstract: Money laundering through insurance claims poses a threat to insurers both through fraudulent payouts and reputational and regulatory risk. Despite this, little research has examined how such laundering can be prevented. This paper examines whether machine learning can help insurers flag suspicious claims before payout, shifting the focus from passive reporting to active prevention. Using production data from a major Norwegian insurer, we train gradient-boosted decision tree models to detect claims later reported to authorities for suspected money laundering. Because fraud and laundering may share behavioural patterns, we also examine whether insurance fraud labels can serve as an auxiliary training signal. We compare different learning setups using the Budget-Weighted Capture Rate, a metric introduced in this paper to measure how many laundering cases are captured when only a small share of claims can be manually reviewed. The results show that incorporating fraud-related investigation labels substantially improves laundering detection. The best-performing model captures nearly two-thirds of laundering cases within the top-ranked 2 to 6 percent of claims selected for investigation. To our knowledge, this is the first empirical study of machine learning for money laundering detection in insurance claims.

阅读与讨论 → 访问原文 →
11.
arXiv (CS.CL) 2026-06-16

A Practical Evaluation Method for Long-Form Simultaneous Speech-to-Speech Translation

作者:
Yulin Xue↗Siqi Ouyang↗Lei Li↗

Simultaneous speech-to-speech translation (SimulS2ST) enables real-time cross-lingual communication, but existing evaluation has focused largely on short or pre-segmented speech rather than long-form, continuous input. Prior approaches are difficult to reproduce and make assumptions that do not hold for end-to-end systems. We present a practical evaluation method for long-form SimulS2ST. Given source speech, pre-segmented source transcripts, and reference translations, we run automatic speech recognition (ASR) and forced alignment on the generated target speech to recover token-level timestamps, then apply a sentence-embedding-based aligner to match the target text to its corresponding source sentences. This enables sentence-level computation of latency and quality metrics, including YAAL and xCOMET, which are then aggregated into final system-level scores. Experiments on representative SimulS2ST systems show that the method is effective in practice and reveal that current systems suffer from substantial latency accumulation on long speech.

阅读与讨论 → 访问原文 →
12.
arXiv (math.PR) 2026-06-24

The Zeta Tail Distribution: A Novel Event-Count Model

作者:
Michael R. Powers↗

arXiv:2506.17496v3 Announce Type: replace-cross Abstract: We introduce the Zeta Tail$\left(a\right)$ probability distribution as a new model for random damage-event counts in risk analysis. Although a natural analogue of the Geometric$\left(p\right)$ distribution, Zeta Tail$\left(a\right)$ has received little attention in the scholarly literature. In the present work, we show this distribution to be reasonably tractable by deriving various fundamental properties, including moments, generating functions, and reliability functions. We then assess its usefulness as an alternative to Geometric$\left(p\right)$, both theoretically and through application to a set of meteorological data. Finally, we discuss conceptual differences between employing the Zeta Tail$\left(a\right)$ model conditionally (i.e., given observed data with certain known characteristics) and unconditionally (i.e., for arbitrary, as yet unobserved data).

阅读与讨论 → 访问原文 →
13.
arXiv (CS.LG) 2026-06-18

Generative models for decision-making under distributional shift

作者:
Xiuyuan Cheng↗Yunqin Zhu↗Yao Xie↗

arXiv:2604.04342v2 Announce Type: replace Abstract: Many data-driven decision problems are formulated using a nominal distribution estimated from historical data, while performance is ultimately determined by a deployment distribution that may be shifted, context-dependent, partially observed, or stress-induced. This tutorial presents modern generative models, particularly flow- and score-based methods, as mathematical tools for constructing decision-relevant distributions. From an operations research perspective, their primary value lies not in unconstrained sample synthesis but in representing and transforming distributions through transport maps, velocity fields, score fields, and guided stochastic dynamics. We present a unified framework based on pushforward maps, continuity, Fokker-Planck equations, Wasserstein geometry, and optimization in probability space. Within this framework, generative models can be used to learn nominal uncertainty, construct stressed or least-favorable distributions for robustness, and produce conditional or posterior distributions under side information and partial observation. We also highlight representative theoretical guarantees, including forward-reverse convergence for iterative flow models, first-order minimax analysis in transport-map space, and error-transfer bounds for posterior sampling with generative priors. The tutorial provides a principled introduction to using generative models for scenario generation, robust decision-making, uncertainty quantification, and related problems under distributional shift.

阅读与讨论 → 访问原文 →
14.
arXiv (CS.AI) 2026-06-16

DualGauge: Automated Joint Security-Functionality Benchmarking of Specification-Only Code Generation by LLMs and Coding Agents

作者:
Rupam Patir↗Keyan Guo↗Suvadra Barua↗Abhijeet Pathak↗Dinesh Gudimetla↗Jiawei Guo↗Hongxin Hu↗Haipeng Cai↗

arXiv:2511.20709v2 Announce Type: replace-cross Abstract: Large language models (LLMs) and LLM-based coding agents are now used to generate code from natural-language specifications, yet ensuring such code is both functionally correct and secure remains a challenge. We present DualGauge, the first fully automated framework for jointly evaluating correctness and security of specification-only code generation, supported by DualGauge-Bench, a language-agnostic benchmark of 307 coding tasks each paired with functional and security tests derived from the same specification. Evaluating 10 representative LLMs across Python, C++, and JavaScript, we find that functional correctness substantially overestimates reliable code generation: even the strongest model remains below 15% joint security-functionality success in every language. Common model-side factors–scale, extended thinking, quantization, instruction tuning, and code specialization–do not reliably improve joint performance, suggesting secure-and-correct code generation does not simply emerge from stronger coding capability. Evaluation of 3 leading agentic coding systems (Codex, OpenHands, and Claude Code) shows that iterative scaffolding provides no advantage over direct (LLM-based) generation on specification-only tasks. A qualitative audit reveals failures concentrate at the output contract boundary and in guards that exist but are insufficient–patterns that only joint benchmarking reliably exposes.

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

InstantForget: Update-Free Backdoor Unlearning with Inference-Time Feature Reset

作者:
Zhenyu Yu↗

arXiv:2606.15730v1 Announce Type: cross Abstract: Backdoor unlearning aims to remove a malicious trigger behavior from a deployed model while preserving clean utility. We study the update-free inference-time setting, where model parameters remain frozen. First, we audit a common projection assumption under oracle paired clean and triggered features. Projection succeeds mainly on BadNets and leaves WaNet, Blended, and SIG at 0.683, 0.888, and 0.941 ASR on CIFAR-10 ResNet-18. This failure is not explained by spectral compactness, spatial locality, or subspace misalignment. It is predicted by a logit-triplet gap involving the target margin, target-logit drop, and non-target logit rise. We then introduce InstantForget, a clean-calibrated gated reset that flags anomalous features with a Mahalanobis score and moves only flagged features toward a neutral non-target representation. With one fixed operating point selected on held-out triggered validation, InstantForget reduces average ASR to 0.071 across four non-adaptive CIFAR-10 triggers without triggered samples or parameter updates at deployment. It also reaches 0.981 detection AUROC and transfers to six of eight tested backbones. Reported failures under WaNet, ModelNet10 point blend, two backbone geometries, and adaptive feature-compactness attacks define the method's scope.

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

Context-Aware Multimodal Claim Verification in Spoken Dialogues

作者:
Chaewan Chun↗Delvin Ce Zhang↗Dongwon Lee↗

Every day, millions absorb claims from podcasts and streams that no fact-checker ever sees. Spoken misinformation is built through conversation, where credibility comes not from facts alone but from how claims are framed, reinforced, or left unchallenged across turns. Yet fact-checking has focused on isolated text, leaving dialogue audio under-studied. We introduce MAD2, a new Multi-turn Audio Dialogues benchmark for spoken claim verification, containing 1,000 two-speaker dialogues with 3,368 check-worthy claims and approximately 10 hours of audio, and propose calibrated multimodal fusion of a context-aware audio encoder and a dialogue-aware text model. Across settings, adding dialogue context improves verification, but the gains depend on scenario type. Using only preceding context often matches offline performance, supporting live-moderation settings, and audio contributes most when transcript-based models are destabilized by additional context. Overall, conversational structure matters more for verification than misinformation framing.

阅读与讨论 → 访问原文 →
18.
arXiv (CS.AI) 2026-06-11

\texttt{Range-Arithmetic}: Verifiable Deep Learning Inference on an Untrusted Party

作者:
Ali Rahimi↗Babak H. Khalaj↗Mohammad Ali Maddah-Ali↗

arXiv:2505.17623v2 Announce Type: replace-cross Abstract: Verifiable computing (VC) has gained prominence in decentralized machine learning systems, where resource-intensive tasks like deep neural network (DNN) inference are offloaded to external participants due to blockchain limitations. This creates a need to verify the correctness of outsourced computations without re-execution. We propose \texttt{Range-Arithmetic}, a novel framework for efficient and verifiable DNN inference that transforms non-arithmetic operations, such as rounding after fixed-point matrix multiplication and ReLU, into arithmetic steps verifiable using sum-check protocols and concatenated range proofs. Our approach avoids the complexity of Boolean encoding, high-degree polynomials, and large lookup tables while remaining compatible with finite-field-based proof systems. Experimental results show that our method not only matches the performance of existing approaches, but also reduces the computational cost of verifying the results, the computational effort required from the untrusted party performing the DNN inference, and the communication overhead between the two sides.

阅读与讨论 → 访问原文 →
19.
PLOS Computational Biology 2026-06-01

A statistical framework for comparing epidemic forests

作者:
Cyril Geismar↗

by Cyril Geismar, Peter J. White, Anne Cori, Thibaut Jombart Inferring who infected whom in an outbreak is essential for characterising transmission dynamics and guiding public health interventions. However, this task is challenging due to limited surveillance data and the complexity of immunological and social interactions. Instead of a single definitive transmission tree, epidemiologists often consider multiple plausible trees forming epidemic forests. Various inference methods and assumptions can yield different epidemic forests, yet no formal test exists to assess whether these differences are statistically significant. We propose such a framework using a chi-square test and permutational multivariate analysis of variance (PERMANOVA). We assessed each method’s ability to distinguish simulated epidemic forests generated under different offspring distributions. While both methods achieved perfect specificity for forests with 100+ trees, PERMANOVA consistently outperformed the chi-square test in sensitivity across all epidemic and forest sizes. Implemented in the R package mixtree, we provide the first statistical framework to robustly compare epidemic forests.

阅读与讨论 → 访问原文 →
20.
arXiv (CS.CL) 2026-06-19

Quantifying Aleatoric Uncertainty of In-Context Learning for Robust Measure of LLM Prediction Confidence

作者:
Jinseok Chung↗Minkyoung Song↗Hyunji Jung↗Namhoon Lee↗

In-Context Learning (ICL) allows LLMs to adapt to new tasks from a few demonstrations, but its reliability remains a concern: predictions are highly sensitive to both prompt design and the model's ability to understand the context, obscuring whether failures arise from data properties or model limitations. Uncertainty decomposition-separating aleatoric from epistemic sources-is particularly crucial in this setting, yet existing methods, designed for standard generation tasks, fail to capture the unique dynamics of ICL. To address this, we introduce a concept of self-function vectors, built upon Bayesian views and the mechanistic interpretability of ICL. These vectors leverage internal model representations to model the latent concept learned during in-context prompting, thereby enabling a direct estimation of aleatoric uncertainty within a Bayesian framework and circumventing the reliance on brittle input or decoding manipulations. Given the lack of established benchmarks and suitable evaluation protocols, we also propose the first and rigorous evaluation protocol, in which data is manipulated in controlled ways so as to quantify aleatoric uncertainty precisely and separately from epistemic uncertainty. With this new evaluation framework, initially grounded in synthetic tasks for conceptual development and subsequently extended to real-world datasets, we show that our proposed methodology can measure uncertainty of LLM predictions made under ICL more reliably than existing alternative methods. Moreover, we show it can be used as a practical tool for trustworthy-related applications, such as hallucination detection. Our findings pave a new direction for connecting the quantitative view of uncertainty with the mechanistic understanding of model behavior.

阅读与讨论 → 访问原文 →
21.
bioRxiv (Bioinfo) 2026-06-24

Statistical tests for bivariate spatial association across multi-omics data with disjoint coordinates

作者:
Hawinkel↗Hu↗Velten↗Maere↗

Spatial biology has entered a new era of multimodal profiling, with multiple, high-dimensional spatial omics types being measured on consecutive tissue slices, or co-assayed on the same slice. Interest then lies in statistical testing for spatial association between the features of the different modalities, to gain insight in biological processes. One major challenge is the multitude of bivariate combinations, leading to high computational demands. Another difficulty is the difference in spatial resolution between technologies, implying no one-to-one matching between the measurement spots of the two modalities, even after alignment. As a result, common statistical measures such as joint distributions and correlations are not defined, and tests need to rely on spatial vicinity only. Moreover, we argue that many existing bivariate association tests address an inappropriate null hypothesis, or make inappropriate assumptions, both implying absence of spatial autocorrelation in any of the features and leading to misleading conclusions. As a remedy, we modify tests for the detection of spatially variable genes (Moran's I, Gaussian processes and generalized additive models (splines)) to derive bivariate tests across modalities with non-overlapping coordinate sets and provide variance estimators that do account for spatial autocorrelation. We develop inference methods for single sections as well as for replicated experiments with multiple sections, and compare their performance in nonparametric and parametric simulations. Finally, we apply the newly developed methods to two co-assayed spatial transcriptomics and metabolomics datasets from mouse and human. The full suite of tests is available from github.com/sthawinke/sbivar as the R-package sbivar.

阅读与讨论 → 访问原文 →
22.
arXiv (CS.LG) 2026-06-17

Evaluating Open-Source LLMs for Multi-Label ATT&CK Technique Classification on CTI Reports

作者:
Ahmed Ryan↗Saad Sakib Noor↗Md Erfan↗Shaswata Mitra↗Sudip Mittal↗Md Rayhanur Rahman↗

arXiv:2606.18166v1 Announce Type: cross Abstract: Classifying Cyber Threat Intelligence (CTI) using MITRE Adversarial Tactics, Techniques, and Common Knowledge (ATT&CK) is essential for proactive defense, but historically required extensive human effort. Pre-Large Language Model (LLM) automation sped up this process, but could not resolve the complex language and multi-step attack patterns found in unstructured CTI reports. LLMs addressed previous limitations by using contextual reasoning to understand unstructured text. However, current evaluations rely on simplified, single-technique sentences that ignore the complexity of real-world CTI reports, which often leads to inflated performance results. Consequently, the baseline performance of open-source LLMs on complex unstructured CTI reports remains unevaluated. To address this gap, we constructed a ground-truth dataset of 2,076 human-annotated sentences (1,281 technique-positive, 795 negative) from 83 complex unstructured CTI reports. These sentences were mapped to 114 unique ATT&CK techniques using a six-phase annotation process, achieving \k{appa} = 0.68 inter-annotator agreement. Using this dataset, we evaluated seven open-source LLMs ranging from 8B to 236B parameters across prompt strategy and temperature configurations. The highest-performing LLM achieved a micro-averaged F1 score of 0.22, establishing the empirical baseline for multi-label ATT&CK classification on complex unstructured CTI. Parameter size showed a statistically significant positive correlation with F1 score. Prompt strategy and temperature produced no statistically significant gains across model configurations. These results indicate that current open-source LLMs are insufficient for production-grade ATT&CK classification. The dataset, benchmark, and findings provide a reproducible foundation for future CTI research.

阅读与讨论 → 访问原文 →
23.
medRxiv (Medicine) 2026-06-15

Anti-Platelet Factor 4 Antibody Clonal Heterogeneity and MGUS Status in HIT

作者:
Kanack↗Mauch↗Kohlhagen↗Coker↗Murray↗Padmanabhan↗

Background Monoclonal gammopathy of thrombotic significance (MGTS) is a recently described chronic prothrombotic condition characterized by monoclonal anti-PF4 antibodies that are detected above the polyclonal antibody background in patient sera (i.e. present as monoclonal gammopathy of undetermined significance, MGUS). Due to conflicting data in the published literature on antibody clonality in heparin-induced thrombocytopenia (HIT), we evaluated clonality and abundance of anti-PF4 antibodies in HIT, including investigating whether an MGUS, if present in HIT, represents the causative anti-PF4 antibody. Methods Blood samples from 15 patients with HIT were subject to Platelet Factor 4-dependent antigen-based and functional tests. The unmanipulated serum antibody repertoire and isolated anti-PF4 antibodies were subjected to mass spectrometric evaluation. Results Two of the 15 HIT patients had an IgG MGUS. Notably, anti-PF4 antibodies were not synonymous with the MGUS antibody in either of the two patients. Eight of the 15 patients demonstrated monoclonal anti-PF4 antibodies, however, none of the anti-PF4 antibodies were detectable as an MGUS upon evaluation of the entire serum antibody repertoire, reflecting their low abundance. In the seven patients with multiple anti-PF4 antibodies, non-monoclonality was confirmed by analysis of deglycosylated antibody heavy chains. Conclusions Anti-PF4 HIT antibodies are monoclonal in approximately 50% of HIT patients, however, antibody abundance is low such that they are not detectable over the polyclonal IgG background (i.e. are MGUS-negative), differentiating HIT from MGTS. This observation helps explain the transient nature of HIT relative to the persistent prothrombotic state seen in MGTS.

阅读与讨论 → 访问原文 →
24.
arXiv (CS.LG) 2026-06-17

When the Next Step Is Not One Step: Distribution-Aware Execution Modeling for Concurrent Go Programs

作者:
Kaviru Hapuarachchi↗

arXiv:2606.17508v1 Announce Type: new Abstract: Training a model to predict the next step in a concurrent program is harder than it looks: two runs of the same program from the same trace prefix can produce different next events, both valid, because the scheduler is nondeterministic. A model trained against a single label is learning to guess one outcome of a random process. We turn this around and use the nondeterminism as a training signal. We run each program many times, aggregate the observed next events into an empirical distribution, and fine-tune a 7B model to match that distribution with a KL objective. On 798 held-out predictions drawn from real production Go bugs (CockroachDB, Kubernetes, gRPC, etcd), fine-tuning on fewer than a thousand traces reaches 36.2% accuracy, ahead of Gemini 3.5 Flash used zero-shot (34.8%) and the same model without fine-tuning (28.6%). Distribution training matches cross-entropy on accuracy (35.8% vs. 36.2%) while reducing Expected Calibration Error from 0.205 to 0.169. We also derive a formal goroutine-leak signature for a class of select-blocked goroutines where P(GoUnblock)=0 holds by scheduler semantics, not by learning. We release the dataset, trained adapters, and all tooling.

阅读与讨论 → 访问原文 →
25.
Nature (Science) 2026-06-24

Chiral laser gyroscopes breaking the lock-in limit

作者:
Yuan-Hao Mao↗

Ring laser gyroscopes (RLGs) measure rotation via the Sagnac effect: a slight difference in the frequency of the two counter-propagating beams within the resonator. However, at low rotation rates, an intrinsic limitation in RLGs, known as the lock-in phenomenon, counteracts this effect, precluding the widespread adoption of RLGs as motion sensors. Past efforts to avoid this phenomenon include mechanical dithering1 and magneto-optic non-reciprocity techniques2. Such techniques require external components that limit the miniaturization of RLGs. Here we present a self-biased method that overcomes this limitation through chiral spontaneous symmetry breaking and nonlinear frequency pulling in a He–20Ne RLG without inserted elements. Supported by a theoretical model that reveals phase transition conditions with spontaneous symmetry breaking and the dynamics of bistable chiral states, our experiments demonstrate deterministic chirality switching synchronized with rotation direction. Remarkably, the chiral RLG has a linear frequency response at near-zero rotation rates, achieving an open-loop bias instability of 2.2 × 10−2 degrees per hour at a 10 s integration time. Our work presents a strategy for the development of all-solid-state, high-precision and miniaturized laser gyroscopes, which could be used for the exploration of the interplay of nonlinear dynamics and spontaneous symmetry breaking in photonic systems. Ring laser gyroscope lock-in has been eliminated using spontaneous symmetry breaking in a He–Ne laser, enabling accurate near-zero rotation sensing without external components, improving miniaturization and precision.

阅读与讨论 → 访问原文 →