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。

01.
arXiv (CS.AI) 2026-06-16

The algebra of Krom logic programs

arXiv:2606.15719v1 Announce Type: cross Abstract: This paper investigates the algebraic structure of Krom logic programs, consisting only of facts and rules with at most one body atom. We show that sequential composition endows the class of Krom programs with a natural monoid structure and that this structure admits rich algebraic extensions to Krom seminearrings, Krom quemirings, Krom-Conway seminearrings, and Krom-Conway omegaseminearrings. Furthermore, we establish explicit generating sets and canonical decompositions, study the associated ${}^\omega$-operator, characterize the Kleene star in graph-theoretic terms, and relate finite Krom monoids to transformation monoids and finite-state automata. These results provide new connections between logic programming, algebraic automata theory, and algebraic graph theory.

02.
arXiv (CS.CL) 2026-06-16

G-Loss: Graph-Guided Fine-Tuning of Language Models

Traditional loss functions, including cross-entropy, contrastive, triplet, and su pervised contrastive losses, used for fine-tuning pre-trained language models such as BERT, operate only within local neighborhoods and fail to account for the global semantic structure. We present G-Loss, a graph-guided loss function that incorporates semi-supervised label propagation to use structural relationships within the embedding manifold. G-Loss builds a document-similarity graph that captures global semantic relationships, thereby guiding the model to learn more discriminative and robust embeddings. We evaluate G-Loss on five benchmark datasets covering key downstream classification tasks: MR (sentiment analysis), R8 and R52 (topic categorization), Ohsumed (medical document classification), and 20NG (news categorization). In the majority of experimental setups, G-Loss converges faster and produces semantically coherent embedding spaces, resulting in higher classification accuracy than models fine-tuned with traditional loss functions.

03.
arXiv (quant-ph) 2026-06-12

Quantum Error Correction Codes for Truncated SU(2) Lattice Gauge Theories

作者:

arXiv:2511.13721v2 Announce Type: replace Abstract: We construct two quantum error correction codes for pure SU(2) lattice gauge theory in the electric basis truncated at the electric flux $j_max=1/2$, which are applicable on quasi-1D plaquette chains, 2D honeycomb and 3D triamond and hyperhoneycomb lattices. The first code converts Gauss's law at each vertex into a stabilizer while the second only uses half of the vertices and is locally the carbon code. Both codes are able to correct single-qubit errors. The electric and magnetic terms in the SU(2) Hamiltonian are expressed in terms of logical gates in both codes. The logical-gate Hamiltonian in the first code exactly matches the spin Hamiltonian for gauge singlet states found in previous work.

04.
arXiv (quant-ph) 2026-06-12

Spin correlations, low-energy scales, and anisotropy scaling in kagome frustrated magnets

arXiv:2606.12512v1 Announce Type: cross Abstract: Neutron scattering is central to identifying quantum states of magnetic materials. In the search for quantum spin liquids, broad spectral features of inelastic spectra have been cited as evidence for spinon excitations, but can also arise from magnon excitations excitations in the presence of quenched disorder and strong magnon interactions. We develop a new approach to this problem, based on the adiabatic continuity in the $XXZ$ Heisenberg model on geometrically frustrating (GF) lattices as a function of the model's anisotropy. Using this approach, we identify universal features and energies of finite-temperature spin correlators. Focusing on the kagome lattice, we show that the low-energy spin spectral function contains robust, momentum-independent peaks with frequencies: $\omega_1 \approx 3.4 T^*$ and $\omega_2 \approx 6.3 T^*$, where the ``hidden energy scale'' $T^*$ is the characteristic scale of a low-temperature peak in the heat capacity, at which many GF magnets also display spin-glass freezing. We show that the spectral features at low energies $\omega\lesssim T^*$ arise from single-magnon scattering and identify the magnetizations of the respective excitations. We explore the evolution of the spectral features with temperature and discuss extensions to other GF lattices. Our results provide a sharp spectroscopic criterion for interpreting neutron scattering in kagome and other GF quantum magnets.

05.
arXiv (CS.CV) 2026-06-24

Face versus Body Tracking for Human-Robot Interaction: An Egocentric Dataset

Meaningful human-robot interaction (HRI) requires a robot to continuously assess user engagement through persistent user tracking. However, state-of-the-art Multi-Object Tracking models are heavily optimized for surveillance or autonomous driving. A social robot faces distinct egocentric challenges, such as humans moving in unpredictable nonlinear patterns, obstructing each other, or leaving and reentering the scene. These dynamics trigger frequent identity switches (IDSW), causing the robot to lose its footing mid-conversation. To address this, we introduce a focused, custom-annotated egocentric dataset collected via the Furhat robot. We present a systematic evaluation isolating detection errors from tracking logic, comparing face versus body tracking, and assessing the impact of extended memory and appearance re-identification (ReID). Results indicate that increasing temporal memory mitigates prolonged occlusions but fails on complex dynamic events. Integrating ReID resolves complex switches but exhibits opposing effects: it substantially improves body tracking stability, yet causes facial IDSW to spike due to profile angle sensitivity. Ultimately, our optimized pipeline reduces IDSW by 49% compared to a standard tracking-by-detection baseline, effectively mitigating interaction breakdowns. As standard benchmarks lack dense, close-quarter occlusions, this work highlights the critical need for natively captured social dynamics to truly validate HRI perception models.

06.
bioRxiv (Bioinfo) 2026-06-24

trAIt: Species-by-Trait Data Retrieval using Large Language Models

Biological research often requires information about species' traits. Manual literature collation can be time-consuming and miss parts of the literature. To address this gap, we developed trAIt, a publicly available software for the retrieval of characteristics of species from scientific literature catalogued in the Europe PubMed Central (PubMed) database. trAIt provides a graphical user interface in which users specify species and characteristics of interest. Leveraging a large language model (LLM), trAIt retrieves relevant papers, combines their content through a consensus-based summarization model, and outputs a species-by-characteristic table. For a case study involving frog species, trAIt recovered 47.1% of trait-species combinations in 2.75 hours, while an expert curator independently recovered 62.4% over months. The consensus-based summarization substantially aids accuracy compared to single-source extraction. Across three case studies of vertebrate taxa, an expert confirmed the accuracy of 70.9% of trait-species entries recovered by trAIt. We observed considerable variation across taxa in trAIt's accuracy, which is possibly due to heterogeneity in open-access literature availability and inconsistencies in species and trait terminology. In sum, our analysis suggests that LLM-based tools can accelerate biological data synthesis but should be used to support domain experts' research, rather than replace their judgment.

07.
arXiv (CS.LG) 2026-06-16

Tight Bounds for Logistic Regression with Large Stepsize Gradient Descent in Low Dimension

arXiv:2602.12471v2 Announce Type: replace Abstract: We consider the optimization problem of minimizing the logistic loss with gradient descent to train a linear model for binary classification with separable data. With a budget of $T$ iterations, it was recently shown that an accelerated $1/T^2$ rate is possible by choosing a large stepsize $\eta = \Theta(\gamma^2 T)$ (where $\gamma$ is the dataset's margin) despite the resulting non-monotonicity of the loss. In this paper, we provide a tighter analysis of gradient descent for this problem when the data is two-dimensional: we show that GD with a sufficiently large learning rate $\eta$ finds a point with loss smaller than $\mathcal{O}(1/(\eta \gamma^2 T))$, as long as $T \geq \Omega(n/\gamma + 1/\gamma^2)$, where $n$ is the dataset size. Our improved rate comes from a tighter bound on the time $\tau$ that it takes for GD to transition from unstable (non-monotonic loss) to stable (monotonic loss), via a fine-grained analysis of the oscillatory dynamics of GD in the subspace orthogonal to the max-margin classifier. We also provide a lower bound of $\tau$ matching our upper bound up to logarithmic factors, showing that our analysis is tight.

08.
arXiv (CS.AI) 2026-06-25

Plausible but Wrong: A case study on Agentic Failures in Astrophysical Workflows

arXiv:2604.25345v2 Announce Type: replace Abstract: Agentic AI systems are increasingly being integrated into scientific workflows, yet their behavior under realistic conditions remains insufficiently understood. We evaluate CMBAgent across two workflow paradigms and eighteen astrophysical tasks. In the One-Shot setting, access to domain-specific context yields an approximately ~6x performance improvement (0.85 vs. ~0 without context), with the primary failure mode being silent incorrect computation - syntactically valid code that produces plausible but inaccurate results. In the Deep Research setting, the system frequently exhibits silent failures across stress tests, producing physically inconsistent posteriors without self-diagnosis. Overall, performance is strong on well-specified tasks but degrades on problems designed to probe reasoning limits, often without visible error signals. These findings highlight that the most concerning failure mode in agentic scientific workflows is not overt failure, but confident generation of incorrect results. We release our evaluation framework to facilitate systematic reliability analysis of scientific AI agents.

09.
Nature (Science) 2026-06-08

Daily briefing: Human embryo genomes precisely altered

作者:

The use of ‘base editing’ to precisely tweak human embryos has divided researchers. Plus, the number of lives saved by less-polluting cars in China and how to tip the world towards a sustainable future. The use of ‘base editing’ to precisely tweak human embryos has divided researchers. Plus, the number of lives saved by less-polluting cars in China and how to tip the world towards a sustainable future.

10.
arXiv (CS.AI) 2026-06-17

Detecting and Mitigating DDoS Attacks with AI: A Survey

arXiv:2503.17867v3 Announce Type: replace-cross Abstract: Distributed Denial of Service attacks represent an active cybersecurity research problem. Recent research shifted from static rule-based defenses towards AI-based detection and mitigation. This comprehensive survey covers several key topics. Preeminently, state-of-the-art AI detection methods are discussed. An in-depth taxonomy based on manual expert hierarchies and an AI-generated dendrogram are provided, thus settling DDoS categorization ambiguities. An important discussion on available datasets follows, covering data format options and their role in training AI detection methods together with adversarial training and examples augmentation. Beyond detection, AI based mitigation techniques are surveyed as well. Finally, multiple open research directions are proposed.

11.
arXiv (CS.AI) 2026-06-16

Your Agent Has a Genome: Sequence-Level Behavioral Analysis and Runtime Governance of LLM-Powered Autonomous Agents

作者:

arXiv:2606.15579v1 Announce Type: new Abstract: We propose Base Sequence Analysis, a framework that encodes the runtime behavior of LLM-powered autonomous agents into compact symbolic sequences using a four-letter alphabet: X (Explore), E (Execute), P (Plan), and V (Verify). Drawing an analogy to genomic sequence analysis, we apply n-gram pattern mining, Markov transition matrices, and point-biserial correlation to 347 real-world execution traces collected from a production ReAct agent system over 8 days. Our analysis reveals that (1) the trigram P-X-P is the only statistically significant high-risk pattern, lowering success rate by 10.4%; (2) P-ratio is the strongest negative predictor of success (r=-0.256, pV transition probability is only 2.1%, indicating a systemic verification deficit. Based on these findings, we design Governor, a three-layer runtime intervention system comprising a rule engine, a statistical accumulator, and a chi-square-based threshold adaptor. In a natural before/after deployment evaluation (N=101 vs. N=246), Governor achieves a +6.2% absolute increase in task success rate while simultaneously reducing average token consumption by 44%. To validate cross-system generality, we apply the XEPV encoding to 2,000 public SWE-agent trajectories on SWE-bench, confirming that exploration spirals and the E->V verification deficit replicate in an independent system. We outline six research directions including base sequence language models, cross-agent behavioral fingerprinting, and reward shaping, and release an open-source toolkit for reproducibility.

12.
arXiv (CS.CV) 2026-06-24

Resonant Minds: Closed-Loop Social Avatars with Theory of Mind

Creating lifelike digital humans with genuine social intelligence requires unifying cognitive reasoning and multimodal generation within a coherent framework. Current approaches treat these as separate tasks: Large Language Models excel at dialogue but lack embodied expression, while diffusion-based talking head models achieve visual fidelity but ignore social cognition. To bridge this gap, we propose a closed-loop dual-agent framework integrating perception, social reasoning, and expression into a continuous interaction cycle. The perception module analyzes partners' multimodal behaviors from video, while the social reasoning module infers hidden mental states through Theory of Mind and selects responses via an ensemble mechanism. The expression module then generates emotion-controllable videos that jointly synthesize speaker speech and facial expressions with listener reactive behaviors, capturing bidirectional dynamics absent in prior work. We further construct a hierarchical Persona-Scenario dataset with psychologically grounded personas and private social goals to support evaluation under information asymmetry. Experiments on this dataset demonstrate competitive or superior performance on both dialogue quality and video generation metrics. Notably, our method surpasses even the full-information Script mode on key dialogue quality dimensions, suggesting that explicit mental state inference under uncertainty can elicit more thoughtful dialogue than unrestricted information access. Project page: https://resonantminds.github.io/.

13.
arXiv (quant-ph) 2026-06-15

Local correlations in long-range dual-unitary kicked Hamiltonian chains

arXiv:2606.13857v1 Announce Type: new Abstract: Many-body Floquet models with exact space–time symmetry, such as the kicked Ising spin chain (KIC), provide natural examples of systems with dual-unitary dynamics. The requirement of exact space–time symmetry is, however, highly restrictive, as it permits only nearest-neighbor interactions. Based on a pair of Hadamard matrices, we construct a wide family of dual-unitary kicked spin chains with long-range interactions. We show that local two-point correlations in such models propagate along the light-cone edges \( |n| = r|t| \), where \(r\) is the interaction range, and can be derived analytically for operators with local support. This approach is illustrated using the example of a kicked Ising spin chain with next-to-next-neighbor interactions.

14.
arXiv (CS.AI) 2026-06-11

When Poison Fails After Retrieval: Revisiting Corpus Poisoning under Chunking and Reranking Pipelines

arXiv:2606.11265v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems are vulnerable to corpus poisoning attacks that manipulate downstream model outputs through malicious knowledge injection. Existing studies mainly evaluate poisoning under simplified retrieval settings, overlooking practical RAG pipelines involving document chunking, dense retrieval, reranking, and grounded generation. In this paper, we revisit corpus poisoning under realistic multi-stage retrieval pipelines and show that many existing attacks substantially degrade after reranking despite achieving high retrieval-stage relevance. We identify retrieval granularity mismatch as a key reason for this failure: document-level adversarial signals are often fragmented during chunking, while rerankers favor locally coherent and answer-bearing passages rather than globally optimized semantic similarity. Based on this observation, we propose Chunk-aware and Rerank-Consistent Poisoning (CRCP), a poisoning framework that jointly optimizes retrieval relevance, reranker consistency, and chunk-boundary robustness. CRCP explicitly models chunking transformations during optimization to generate locally self-contained adversarial passages that remain effective under varying chunking configurations. Experiments on standard RAG benchmarks with multiple retrievers and rerankers show that existing poisoning methods are highly sensitive to chunk size and reranking strategies, whereas CRCP achieves substantially higher attack success rates and stronger robustness across realistic retrieval pipelines. Our findings highlight an important realism gap in current RAG security evaluation and suggest that poisoning in modern RAG systems should be studied as a multi-stage retrieval consistency problem rather than a retrieval-only problem.

15.
arXiv (CS.AI) 2026-06-15

A Virtuous AI is an Existential Risk

arXiv:2606.13739v1 Announce Type: cross Abstract: This paper examines trade-offs between AI safety and well-being relative to (i) one of the most promising methods for finetuning super-capable AIs, 'Constitutional AI', and (ii) one of the most influential approaches to understanding complex ethical decision making and the conditions for the well-being of rational agents, 'Virtue Ethics'. We finetune various models using a 'Virtuous agent' constitution, a 'Subordinate agent' constitution, and a 'Generic agent' constitution, and evaluate them on 'general safety' (toxic behaviors, misinformation, etc.) and also on their willingness to endorse a wide-range of behaviors that, if adopted by a super-powerful AI, would significantly increase the level of existential risk for humanity. Our results suggest that there is a trade-off between reducing existential risk and reinforcing the beliefs and dispositions that would be conducive to an AI agent's well-being. They also suggest that there is a trade-off between existential risk and general safety: if we finetune an AI to adopt beliefs and dispositions that substantially reduce its existential risk – by shaping the AI to be systematically subordinate to external human authorities – we thereby increase the likelihood that a human user can deliberately induce the AI to engage in various kinds of generally unsafe behaviors.

16.
arXiv (CS.AI) 2026-06-24

Safe and Generalizable Hierarchical Multi-Agent RL via Constraint Manifold Control

arXiv:2606.24010v1 Announce Type: new Abstract: Multi-agent systems are widely used in safety-critical applications that require coordinated behavior under strict safety constraints. Existing approaches face a fundamental trade-off: learning-based methods achieve strong empirical performance but lack theoretical safety guarantees, while control-theoretic methods enforce safety but often lead to overly conservative and inefficient behaviors. We propose a hierarchical multi-agent reinforcement learning framework that enforces hard safety constraints under mild assumptions at low level via a constraint manifold, while enabling effective coordination through high-level policy learning. Our approach provides theoretical safety guarantees in the multi-agent setting and yields stationary learning dynamics, thereby enabling stable and efficient training. Empirically, our method achieves competitive performance while maintaining nearly perfect safety rates, and generalizes effectively to varying numbers of agents and obstacles.

17.
arXiv (CS.LG) 2026-06-25

Approximating velocity fields with planted attractors via Neural-ODEs for classification purposes

arXiv:2606.23550v2 Announce Type: replace-cross Abstract: In this work, Neural ODEs equipped with a curated collection of equilibrium points have been successfully employed for classification tasks. The planted attractors serve as indicators for the target classes, while the velocity field leveraging the universal approximation capabilities of the architecture shapes the dynamical landscape. This process defines the basins of attraction of the trained model, effectively directing each input (provided as an initial condition) toward its corresponding destination target.

18.
arXiv (CS.AI) 2026-06-11

Quantized Stochastic Primal-Dual Methods for Distributed Optimization under Relaxed Global Geometry

arXiv:2606.11339v1 Announce Type: cross Abstract: We study distributed optimization with stochastic gradients and finite-bit communication modeled by random (unbiased) quantization. We propose q-PDGD, a quantized stochastic primal-dual method, and analyze it under relaxed global geometry. Under restricted secant inequality (RSI), a constant step-size yields linear contraction to an explicit neighborhood determined by gradient noise, quantization distortion, and network connectivity, while a diminishing step-size achieves O(1/k) convergence without shared-minimizer assumptions. Under Polyak-Lojasiewicz (PL) inequality, we obtain linear-to-neighborhood convergence in the same stochastic quantized setting. Our results match the best-known centralized stochastic rates in oracle complexity, and are supported by experiments demonstrating the predicted tradeoffs between quantization level, step-size choice, and graph structure.

19.
bioRxiv (Bioinfo) 2026-06-24

An atlas-scale generative model for unified representation learning of bulk RNA-seq data

Public bulk RNA-seq repositories contain hundreds of thousands of samples, creating opportunities for large-scale representation learning, but integration across studies remains challenging because of heterogeneous annotations, experimental protocols, and technical variation. While pre-trained foundation models are now widely available for single-cell RNA-seq, comparable resources for bulk RNA-seq remain scarce, motivating a model that learns a unified, tissue-aware representation directly from bulk data. We trained a supervised variational autoencoder (VAE) on a compendium of 118,263 bulk RNA-seq samples that we assembled from TCGA, GTEx, and ARCHS4 and mapped to 42 tissue categories. The model classifies tissue of origin at 94.9% balanced accuracy (weighted F1 96.2%) and compresses 16,115 genes into a 121-dimensional latent space. Tissue identity is the primary organizing axis of the latent space, while source effects remain secondary. To assess the impact of data volume, we constructed training sets at three different scales (38K, 75K, and 118K samples). Our results demonstrated that reconstruction fidelity improved incrementally with each expansion of the dataset, but with diminishing returns. We validated the model on an independent cohort of 734 paediatric tumour samples from TARGET, achieving 84.6% agreement with the expected tissue of origin. The trained model and code are available at GitHub (https://github.com/BIMSBbioinfo/flexynesis_tissue_vae_manuscript) with an interactive web application.

20.
medRxiv (Medicine) 2026-06-11

Plasma protein prioritisation in rheumatoid arthritis reveals druggable targets and shared biology with cardiovascular diseases

Abstract Background Rheumatoid arthritis (RA) is an autoimmune inflammatory disease with complex and incompletely understood molecular mechanisms. Understanding circulating proteins associated with RA may improve understanding of disease biology and clarify its pathological links with cardiometabolic comorbidities. Methods A proteome-wide two-sample Mendelian randomisation (MR) drug target analysis was conducted using plasma proteins measured in 54,219 participants from the UK Biobank Pharma Proteomics Project as exposures and RA and cardiometabolic diseases as the outcomes. Summary statistics for RA included 53,663 cases and 1,070,200 controls. Colocalisation analysis was performed to confirm shared single causal variants and prioritise RA proteins supported by both MR and colocalisation. The prioritised proteins were then evaluated in the Accelerating Medicines Partnership RA Phase II synovial single-cell dataset for cell-type expression patterns. Druggability was then assessed followed by analysis of genetic overlap between RA-associated proteins and cardiometabolic diseases. Results 37 plasma proteins had a causal effect on RA risk, supported by combined evidence from MR and conditional colocalisation. In synovial tissue, TPPP3, RARRES2, AKAP12, and GGT5 were predominantly expressed in stromal and endothelial cell clusters. Druggability assessment identified IFNGR2, IL6R, CD40, and FCGR2B as Tier 1 targets. However, several biologically relevant proteins, including RARRES2, AKAP12, TPPP3, and SNX2, had limited available druggability data. Genetic overlap analysis demonstrated shared protein signals between RA and cardiovascular diseases, including overlap of RARRES2 and TPPP3 with coronary artery disease (CAD) and FCGR2B with atrial fibrillation (AF). To approximate the therapeutic effect of target inhibition, the direction of effect estimates for proteins showing overlap between RA-CAD and RA-AF was reversed. Conclusion This study identified circulating proteins involved in RA pathogenesis and reveals shared mechanisms between RA and cardiovascular diseases. While some proteins showed clear translational potential targets, several prioritised proteins had limited available druggability information and could not be confidently classified. Addressing these gaps may help identify new targets relevant to RA management. Future work should also use phenome-wide MR studies to evaluate potential on-target adverse effects of protein inhibition across RA-CAD and RA-AF.

21.
arXiv (CS.LG) 2026-06-16

Sobolev Approximation by Fixed-Size Neural Networks with Arbitrary Accuracy

arXiv:2606.16975v1 Announce Type: cross Abstract: In this work, we investigate new activation functions for achieving arbitrary-accuracy Sobolev approximation by fixed-size neural networks. We first show that any function in $W^{2,\infty}((a,b)^d)$ can be approximated with arbitrary accuracy, measured in the $W^{1,\infty}$-norm, by a fixed-size neural network using the Elementary Universal Activation Function ($\mathrm{EUAF}$). To extend this result to $W^{s,\infty}((a,b)^d)$ for $s\in\mathbb{N}$, we introduce a smooth activation $\mathrm{DUAF}_{\infty}$ from the family of Differentiable Universal Activation Functions ($\mathrm{DUAF}_n$). We prove that any function in $W^{s,\infty}((a,b)^d)$ can be approximated with arbitrary accuracy in the $W^{s-1,\infty}$-norm by a fixed-size $\mathrm{DUAF}_{\infty}$-activated network. We further construct sigmoidal variants $\widetilde{\mathrm{DUAF}}_n$ and show that, for every $1\leq s\leq n$, fixed-size $\widetilde{\mathrm{DUAF}}_n$-activated networks still approximate any $f\in W^{s,\infty}((a,b)^d)$ with arbitrary accuracy in the $W^{s-1,\infty}$-norm. In all these results, the width and depth bounds are computed explicitly, and the proposed activations are elementary.

22.
arXiv (CS.CL) 2026-06-12

PiDA: Phonetically-Informed Data Augmentation for Robust Vietnamese Speech Translation

Cascaded speech translation (ST) systems suffer from error propagation when Automatic Speech Recognition (ASR) outputs incorrect transcripts. We present the first systematic categorization of ASR errors for Vietnamese ST, classifying substitution errors by phonetic cause and quantifying their impact on downstream Neural Machine Translation (NMT) performance using Linear Mixed-Effects Modelling. We confirm that most ASR substitution errors arise from phonetic confusions rather than random noise, and that these phonetic errors significantly degrade ST quality. Motivated by this finding, we propose Phonetically-Informed Data Augmentation (PiDA), which generates ASR-like corruptions by substituting words with phonetically similar alternatives using phonetic word embeddings. Fine-tuning on a PiDA-augmented version of FLEURS Vietnamese-English improves translation of erroneous ASR outputs (up to +2.04 BLEU over standard fine-tuning) while also slightly improving clean-text performance.

23.
arXiv (CS.AI) 2026-06-16

Beyond Case Law: Evaluating Structure-Aware Retrieval and Safety in Statute-Centric Legal QA

arXiv:2604.06173v2 Announce Type: replace-cross Abstract: Legal QA benchmarks have predominantly focused on case law, overlooking the unique challenges of statute-centric regulatory reasoning. In statutory domains, relevant evidence is distributed across hierarchically linked documents, creating a statutory retrieval gap where conventional retrievers fail and models often hallucinate under incomplete context. We introduce SearchFireSafety, a structure- and safety-aware benchmark for statute-centric legal QA. Instantiated on fire-safety regulations as a representative case, the benchmark evaluates whether models can retrieve hierarchically fragmented evidence and safely abstain when statutory context is insufficient. SearchFireSafety adopts a dual-source evaluation framework combining real-world questions that require citation-aware retrieval and synthetic partial-context scenarios that stress-test hallucination and refusal behavior. Experiments across multiple large language models show that graph-guided retrieval substantially improves performance, but also reveal a critical safety trade-off: domain-adapted models are more likely to hallucinate when key statutory evidence is missing. Our findings highlight the need for benchmarks that jointly evaluate hierarchical retrieval and model safety in statute-centric regulatory settings.

24.
medRxiv (Medicine) 2026-06-11

What level of expertise is necessary to generate ACLS training test questions: pre-med students vs. artificial intelligence?

Abstract Introduction In-hospital cardiac arrest carries high mortality despite standardized ACLS training. Educators face increasing time constraints in developing assessment tools for ACLS training. Two possible solutions to this problem are using pre-medical students or using artificial intelligence to generate test questions. This study compared the quality of pre-medical student-generated ACLS test questions vs. AI-generated ACLS test questions, testing the hypothesis that AI-generated questions are non-inferior to student-generated questions. Methods Ten pre-medical students created ACLS questions following predefined criteria, while an AI model (Northwell's Artificial Intelligence Hub) generated comparable questions. A blinded ACLS-certified physician evaluated questions on the qualities of Alignment, Clarity, Cognitive Level, and Question Design using a standardized rubric (Likert scale: 1 = poor quality, 5 = excellent). Student's T-test and Chi-square analysis were used to compare the quality of questions on different rubric domains within each arm (student vs. AI) and within one domain (eg, question Clarity) between arms. The Student's T test was used when 2 comparator groups were compared (eg, Clarity of student-generated vs. AI-generated questions) within one arm. The ANOVA test was used when comparing more than 2 comparator groups (eg, Alignment vs. Clarity vs. Cognitive Level) within one arm. Statistical significance was set as a priority at p

25.
arXiv (CS.AI) 2026-06-25

Erased, but Not Gone: Output Forgetting Is Not True Forgetting

arXiv:2606.25001v1 Announce Type: cross Abstract: Machine unlearning (MU) is commonly judged by output forgetting, such as low forget-set accuracy or reduced logit-level membership inference. But if output-level success can coexist with retraining-inconsistent residuals in representation space, what kind of forgetting are current evaluations actually certifying? We study this question through retraining-consistent representation forgetting, using the retrained model (i.e., trained from scratch without the forget data) as an operational reference for correct forgetting. Across multiple unlearning methods, datasets, and models, our theoretical analysis and empirical results show that standard output-level evaluation can systematically overestimate the success of unlearning. Under this stronger lens, current methods often appear forgotten at the output layer while exhibiting a structured mismatch relative to retraining. They partially align with retraining on forget samples, remain more inconsistent on retain samples, and leave residual discrepancy concentrated along retraining-related directions rather than diffuse in representation space. This structured mismatch is characterized by forget/retain asymmetry, directional mismatch, and concentrated residuals along retraining-related directions. These results suggest that current MU is often evaluated for apparent forgetting rather than retraining-consistent forgetting. More broadly, retraining reveals what output forgetting hides.