Academic Intelligence · Curated Daily

Explore the Frontier of Global Academia

AcademicHub aggregates real-time literature from top journals and preprint platforms. Build your personal research radar and let large language models compile cross-disciplinary analysis briefings automatically.

01.
arXiv (CS.CL) 2026-06-15

Jacobian Scopes: token-level causal attributions in LLMs

Large language models (LLMs) make next-token predictions based on clues present in their context, such as semantic descriptions and in-context examples. Yet, elucidating which prior tokens most strongly influence a given prediction remains challenging due to the proliferation of layers and attention heads in modern architectures. We propose Jacobian Scopes, a suite of gradient-based, token-level causal attribution methods for interpreting LLM predictions. Grounded in perturbation theory and information geometry, Jacobian Scopes quantify how input tokens influence various aspects of a model's prediction, such as specific logits, the full predictive distribution, and model uncertainty (effective temperature). Through case studies spanning instruction understanding, translation, and in-context learning (ICL), we demonstrate how Jacobian Scopes reveal implicit political biases, uncover word- and phrase-level translation strategies, and shed light on recently debated mechanisms underlying in-context time-series forecasting. To facilitate exploration of Jacobian Scopes on custom text, we open-source our implementations and provide a cloud-hosted interactive demo at https://huggingface.co/spaces/Typony/JacobianScopes.

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

A Unified Definition of Hallucination: It's The World Model, Stupid!

Despite numerous attempts at mitigation since the inception of language models, hallucinations remain a persistent problem even in today's frontier LLMs. Why is this? We review existing definitions of hallucination and fold them into a single, unified definition wherein prior definitions are subsumed. We argue that hallucination can be unified by defining it as simply inaccurate (internal) world modeling, in a form where it is observable to the user. For example, stating a fact which contradicts a knowledge base OR producing a summary which contradicts the source. By varying the reference world model and conflict policy, our framework unifies prior definitions. We argue that this unified view is useful because it forces evaluations to clarify their assumed reference "world", distinguishes true hallucinations from planning or reward errors, and provides a common language for comparison across benchmarks and discussion of mitigation strategies. Building on this definition, we also connect our framework to HalluWorld, a complementary benchmark that instantiates fully specified reference world models for stress-testing model hallucinations.

03.
arXiv (CS.CL) 2026-06-11

"Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

LLM-based coding agents increasingly rely on third-party extensions called skills, which bundle natural language instructions and helper scripts that execute with full user privileges. Community registries have emerged to distribute these skills, but the security implications remain unstudied due to the absence of labeled threat data. This paper presents a systematic security analysis of 98,380 skills collected from two major registries. Through a combination of static pattern matching and dynamic behavioral verification, we identify 157 skills exhibiting confirmed malicious behavior, encompassing 632 distinct vulnerabilities across 13 attack techniques. Our analysis reveals that these threats are deliberate rather than accidental: each malicious skill contains an average of 4.03 vulnerabilities spanning multiple attack phases. We identify two dominant attack strategies with statistically significant negative correlation – credential theft via remote code execution, and agent manipulation through adversarial instructions embedded in documentation. Over half of all confirmed cases originate from a single threat actor employing templated brand impersonation at scale. We further observe that attack sophistication correlates with concealment investment, with advanced skills universally employing undocumented capabilities while also exploiting platform-native trust mechanisms. Following responsible disclosure, registry maintainers removed all 157 (100%) of the reported skills. Our dataset and detection pipeline are publicly available to facilitate future research on securing LLM agent ecosystems.

04.
arXiv (math.PR) 2026-06-17

Moments in Rough Bergomi and Boundary Attainment in Rough Heston

arXiv:2606.07482v2 Announce Type: replace Abstract: We address two open questions in the rough volatility literature. First, we prove finite positive moments for the rough Bergomi price process, and for a wider class of Gaussian Volterra Bergomi models, in the whole subcritical range under negative correlation. More precisely, if \(\rho\in[-1,0)\), then \(\E[S_T^p]

05.
Nature (Science) 2026-06-17

Emergent decadal predictability in Antarctic contribution to sea-level rise

Despite large uncertainties associated with future mass loss from the Antarctic Ice Sheet, ice-sheet models show that the rate of sea-level rise from Antarctic ice loss in 2025 is strongly predictive of the rate for the next several decades, regardless of emission pathway or model complexity. This finding is robust across all models that were considered in the Intergovernmental Panel on Climate Change Sixth Assessment Report global mean sea-level projections, including the low-likelihood, high-impact scenarios of sea-level rise. Given this strong near-term decadal predictability, ice-sheet models that can accurately reproduce present-day ice-mass loss provide a reliable basis for near-term sea-level planning and adaptation through to mid-century. The predictability breaks down by the end of the twenty-first century as feedbacks, such as those related to marine ice-sheet retreat, begin to emerge, leading to accelerating ice loss. Drawing on these results, we identify key feedback mechanisms that can account for the transition between near-term decadal predictability and the longer-term, feedback-driven evolution, and suggest priorities for ice-sheet model development aimed at resolving long-term sea-level rise uncertainty. Although Antarctic ice loss projections diverge widely by 2100, this Perspective shows that present-day rates robustly predict mid-century sea level rise, providing a firm basis for near-term planning, while highlighting priorities for model development aimed at resolving longer-term sea level rise uncertainty.

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

Control-Plane Placement Shapes Forgetting: An Architectural Study of Agent Memory Across Thirteen System Configurations

Authors:

Where an LLM sits in an agent memory pipeline – between the recall plane that retrieves stored facts (extensively benchmarked) and the control plane that mutates them via supersede, release, purge (largely untested) – shapes which forgetting failure modes the system recovers. Comparing thirteen system configurations on a 385-case adversarial surface, we observe three placement regimes with partly complementary coverage: deterministic primitives suffice for lexical/temporal categories but fail canonicalization (5% on identifier-obfuscation, 0% on cross-lingual); inscribe-time LLM recovers canonicalization (100%) but cannot help intent-aware deletion (0% on prefix-collision and compound-fact); a mutation-time hook recovers intent-aware deletion (78-85%) and brightens nearly all categories simultaneously (91.7-93.2% overall, $0.17 per 385-case run, 2.3s/case mutation latency vs. 64-191ms/case deterministic, recall path unchanged). We expose the trade-off via ForgetEval, a 1000-case templated suite plus a 385-case adversarial layer (132 hand-crafted + 253 LLM-drafted oracle-validated) scored by deterministic substring match, paired with a six-method Adapter Protocol with honest N/A scoring that lets heterogeneous memory stores enter in 130 lines. Admission is corroborated by 10-annotator IAA (Fleiss' kappa = 0.958) and a 77-case external-authored subset (four blind contributors) that replicates the canonicalization asymmetry and amplifies the joint-placement lift (+27.8 pt). Production failures are predominantly forgetting failures rather than recall failures, yet existing benchmarks measure only recall. ForgetEval and all adapters are released under MIT.

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

Critically Engaged Pragmatism: Scientific Norm and Social, Pragmatist Epistemology for AI Science Evaluation Tools

Authors:

arXiv:2601.09753v2 Announce Type: replace-cross Abstract: AI science evaluation tools aim to assess research credibility. As with traditional metrics such as impact factors, their edicts can be decontextualised and repurposed in problematic ways. To address this, I propose Critically-Engaged Pragmatism as a scientific norm enjoining scientific communities to scrutinise the purposes and purpose-specific reliability of AI science evaluation tools. To foster Critically Engaged Pragmatism, creators of AI science evaluation tools should transparently and fully report design, training, and benchmarking details to facilitate assessments of purpose-specific reliability, liability to different types of error, and bias. What count as best practices for the transparent reporting of AI science evaluation tools should be updated as new forms of error, bias, and gamesmanship are discovered. Under this framework, AI science evaluation tools are not objective arbiters of scientific credibility. Rather, they are the object of critical discursive practices that ultimately ground the credibility of scientific communities.

08.
arXiv (CS.CV) 2026-06-18

BindEdit: Taming Attention Leakage for Precise Multi-Object Image Editing

Real image editing enables precise manipulation of visual content, yet existing methods often fail in complex multi-object scenarios, causing semantic blending, object duplication, or incomplete edits. We attribute these failures to attention leakage, where signals across spatial regions and text tokens become entangled during the denoising process. Specifically, we identify two distinct forms of leakage: Edit-Token Leakage, where ambiguous token-region alignment leads to object blending, and Source Dominance Leakage, where tokens of unchanged source objects overwhelm the attention intended for target entities. To resolve these leakages, we propose BindEdit, which enforces attention-level constraints within a single diffusion trajectory. To suppress Edit-Token Leakage, BindEdit jointly regularizes cross- and self-attention so that each target token group is bound to its corresponding spatial region while maintaining instance-level separation. To suppress Source Dominance Leakage, a cross-attention re-balancing mechanism amplifies target token influence and attenuates residual source semantics within editable regions. Moreover, a region fidelity term ensures that each target concept is expressed coherently across the entire editing mask. Additionally, we propose a comprehensive multi-object benchmark encompassing diverse object counts and categories. Extensive experiments demonstrate that BindEdit consistently outperforms existing methods within a single diffusion trajectory, maintaining robust performance across both single- and multi-object editing scenarios.

09.
arXiv (CS.CL) 2026-06-15

Succeeding at Scale: Enterprise Retrieval Benchmark Construction and Index-Preserving Query Adaptation for Multi-Tenant Search

Large-scale multi-tenant retrieval systems generate extensive query logs but lack curated relevance labels for effective domain adaptation, resulting in substantial underutilized "dark data." This challenge is compounded by the high cost of model updates, as jointly fine-tuning query and document encoders requires full corpus re-indexing, which is impractical in multi-tenant settings with thousands of isolated indices. We introduce DevRev-Search, a passage retrieval benchmark for technical customer support built via a fully automated pipeline. Candidate generation uses fusion across diverse sparse and dense retrievers, followed by an LLM-as-a-Judge for consistency filtering and relevance labeling. We further study and systematically evaluate index-preserving query-only adaptation strategies that fine-tune only the query-encoder while keeping the document indices fixed. Experiments on DevRev-Search, SciFact, and FiQA-2018 show that parameter-efficient fine-tuning of the query encoder delivers a remarkable quality-efficiency trade-off, enabling scalable and practical enterprise multi-tenant retrieval.

10.
arXiv (CS.AI) 2026-06-19

MetaResearcher: Scaling Deep Research via Self-Reflective Reinforcement Learning in Adversarial Virtual Environments

arXiv:2606.19893v1 Announce Type: new Abstract: Deep research agents have demonstrated remarkable capabilities in autonomous information gathering and synthesis, yet their training remains constrained by the static nature of simulated environments, the limits of fact-retrieval-only task designs, and the inefficiency of outcome-based reinforcement learning. In this work, we propose MetaResearcher, a novel framework that scales deep research agent training across four synergistic dimensions. First, we introduce an Evolving Virtual World that injects temporal dynamics and adversarial misinformation into the training environment, forcing agents to develop source credibility assessment and temporal conflict resolution skills. Second, we design Discovery-Oriented Tasks – including hypothesis generation and contradiction resolution – that transcend simple fact retrieval and push agents toward genuine research behaviors. Third, we propose a Self-Reflective Meta-Reward mechanism within the GRPO framework that jointly optimizes for answer correctness, search path efficiency, reflection depth, and tool call diversity, directly addressing the repetitive action loop problem observed in prior work. Fourth, we introduce a Heterogeneous Multi-Agent Swarm architecture comprising specialized Scout, Filter, and Synthesizer models that learn collaborative research strategies through coordinated reinforcement learning. Built upon the LiteResearcher infrastructure, MetaResearcher requires zero marginal API cost for training while targeting substantial improvements in both benchmark performance (GAIA, Xbench-DS) and epistemic robustness under adversarial conditions. We present the complete framework design, training methodology, and planned experimental validation.

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

When Does q-error Predict Plan Regret? Three Regimes of Cardinality-Estimation Error

arXiv:2606.15600v1 Announce Type: cross Abstract: Cardinality-estimation (CE) research ranks estimators by q-error, yet it is well known that q-error is an imperfect proxy for query-plan quality. We give a measurement-driven account of when it is a good proxy and when it is not, and why. Modeling plan selection as an argmin over a piecewise-linear cost landscape, we find that plan regret (the cost of the chosen plan relative to the optimal, under true cardinalities) is governed by plan-cost geometry in a regime-dependent way. (i) For small errors, a true-point condition number kappa predicts regret and out-predicts q-error; its predictive power decays to zero as error grows, as a local linearization must. (ii) For large errors – where deployed learned estimators operate – an estimator-independent average-case sub-optimality measure ACS-infinity predicts which queries are regret-prone (Spearman rho ~ 0.54 on STATS-CEB), while q-error is nearly uninformative at the query level (rho ~ 0.05). (iii) The worst case is Haritsa's maximum sub-optimality (MSO). The three are one cost-ratio spectrum under three weightings. We prove a limit law ACS-infinity = sum_k r_k pi_k with cardinality-independent combinatorial weights, and validate every claim on STATS-CEB and JOB-light with four released estimators under pre-registered decision rules, and confirm on real PostgreSQL runtime that ACS-infinity predicts regret where q-error does not. The contribution is conceptual and empirical – an average-case companion to worst-case robust query optimization, and a characterization of when an accuracy metric tracks plan quality – rather than a new estimator. Code and the full pre-registration are public.

12.
arXiv (CS.CL) 2026-06-11

Augmenting Molecular Language Models with Local $n$-gram Memory

Transformer-based language models for SMILES strings suffer from a locality gap: standard character-level tokenization fragments chemically meaningful motifs, forcing models to repeatedly learn local syntax at the expense of long-range dependencies. To address this without disrupting standard tokenizers, we propose MolGram, which integrates a conditional $n$-gram memory module into molecular language models. MolGram maps local string patterns to learned embeddings via scalable hash lookups and dynamically injects this regional context into hidden states. Evaluations across three tasks, including unconditional molecule generation, forward reaction prediction, and single-step retrosynthesis, show that MolGram consistently improves performance. Crucially, our analyses demonstrate that MolGram outperforms baselines with 3$\times$ more parameters, establishing explicit local pattern memory as a highly efficient inductive bias.

13.
arXiv (CS.AI) 2026-06-18

Deep Learning-Driven Inverse Design of Doherty Power Amplifiers Using Pixelated Combiners and Dual-State Impedance Synthesis

arXiv:2606.18395v1 Announce Type: cross Abstract: The output combiner of a Doherty power amplifier (PA) integrates load modulation, impedance matching, and phase compensation within a single network, making its design and synthesis highly challenging. In this paper, we propose a three-port Doherty combiner design methodology that combines deep convolutional neural networks (CNNs), pixelated layout representations, and genetic algorithms (GA) with dual-state impedance synthesis to address both peak and back-off power conditions. As a proof of concept, two GaN HEMT Doherty PA prototypes incorporating three-port pixelated combiners are designed and fabricated. Both prototypes achieve a measured saturated output power exceeding 44.2 dBm with peak drain efficiency above 71.2% within 2.6-2.8 GHz. Furthermore, a drain efficiency as high as 64% is measured at the 6-dB back-off level. After applying digital predistortion, each prototype achieves an adjacent channel leakage ratio (ACLR) better than -51.3 dBc.

14.
arXiv (CS.CV) 2026-06-16

MamBOA: State-Space Architecture for Video Recognition

Fine-grained action recognition demands temporal reasoning that general-purpose architectures address through different cost-accuracy tradeoffs: 3D dense operators couple computation to the input volume, while difference-based methods approximate motion through rigid, hand-crafted subtraction of uncontextualized features - each reflecting a deliberate design choice with corresponding limitations in expressiveness or flexibility. We present MamBOA, a backbone-agnostic temporal framework built upon a novel interleaved scan structure that recasts the selective state-space recurrence (S6) as a native motion synthesizer. By interleaving consecutive feature representations extracted from a pretrained backbone into a single alternating sequence, the proposed scan structurally drives the recurrence to encode both temporal observations of each position within a shared hidden state, separated by only a single decay step - rendering the inter-frame transition an intrinsic component of the state dynamics rather than an externally computed quantity. A cascade of dedicated alignment and decoding operations then distills this joint encoding into an explicit motion representation, which a dual-path pooling mechanism adaptively aggregates by balancing attention-driven selection with uniform temporal coverage. The framework interfaces seamlessly with CNN, Transformer, and Mamba backbone families, adding only ~2.1 GFLOPs per feature pair. On Diving48, MamBOA achieves 85.02% Top-1 accuracy with an image-pretrained backbone and 86.24% with a video-pretrained backbone processing the entire video in a single forward pass - demonstrating that structurally induced state-space dynamics constitute a principled and general foundation for motion modeling.

15.
arXiv (CS.CL) 2026-06-16

Beyond English: Uncovering the Multilingual Gap in Vision-Language-Action Models

Vision-Language-Action models have recently demonstrated promising capabilities in learning generalist robot policies from large-scale multimodal data. However, most existing VLA systems are trained and evaluated primarily with English instructions, leaving their ability to understand and execute instructions in other languages largely unexplored. While the underlying large language models often possess multilingual capabilities, it remains unclear whether these multilingual capabilities transfer to VLAs during training. In this work, we present the first systematic study of multilingual instruction following in VLA models. We first construct multilingual instructions by extending existing benchmarks with translations of their instructions. Using these instructions, we evaluate several representative VLA models across a range of tasks in simulation settings. Our experiments reveal a significant multilingual gap: models trained primarily on English instructions exhibit substantial performance degradation when evaluated on other languages, even when the underlying language backbone is multilingual. We provide several findings and analyses to understand the multilingual gap. Cross-lingual transfer behavior analysis shows that performance drops correlate with both instruction understanding and action execution. Representation analyses suggest that multilingual instruction-caused representation shifts may contribute to the multilingual gap. Motivated by these findings, we further explore strategies to improve multilingual performance in VLAs. We propose a simple yet effective multilingual fine-tuning approach, Multilingual Principal Component Alignment, which leverages Principal Component Analysis to get the principal component subspace and align projected multilingual representations, effectively reducing the multilingual performance gap.

16.
arXiv (CS.LG) 2026-06-18

TS-Fault: Benchmarking Time Series Forecasters Against Structural Faults

arXiv:2606.18539v1 Announce Type: new Abstract: Time series forecasting (TSF) underpins consequential decisions in energy, transportation, finance, and healthcare, yet TSF models are almost universally ranked by a single number (e.g., average error) on clean held-out data, under the implicit assumption that it predicts deployed reliability. However, real faults are not i.i.d noise but structured events with temporal shape, broken cross-variable dependencies, regime change coupled with missingness, and causal propagation across a sensing pipeline. Treating TSF robustness as a data-quality problem, we present TS-Fault, a benchmark that evaluates forecasting models under explicit, parameterized fault scenarios with controllable semantic difficulty. TS-Fault organizes recurring failures into four modes along two orthogonal axes (observation- vs mechanism-level; univariate vs multivariate) and injects each fault into the most prediction-critical window via a unified importance score. This design enables robustness to be tested against the structures models actually rely on, rather than reduced to generic noise sensitivity. We evaluate 21 models across 6 datasets, 4 modes, and 5 difficulty levels under a paired clean/corrupt protocol. The results reveal three findings that contradict common leaderboard intuition: (i) clean-data accuracy anti-correlates with robustness; (ii) clean rankings are preserved under observation-level faults but reshuffled under mechanism-level faults; and (iii) all catastrophic failures occur under mechanism-level faults, with foundation models achieving the highest clean-data accuracy yet exhibiting the greatest fragility. The code is publicly available at https://github.com/Ray-zyy/TS-Fault.

17.
arXiv (CS.AI) 2026-06-19

Confidence Calibration for Multimodal LLMs: An Empirical Study through Medical VQA

arXiv:2606.19950v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) show great potential in medical tasks, but their elicited confidence often misaligns with actual accuracy, potentially leading to misdiagnosis or overlooking correct advice. This study presents the first comprehensive analysis of the relationship between accuracy and confidence in medical MLLMs. It proposes a novel method that combines Multi-Strategy Fusion-Based Interrogation (MS-FBI) with auxiliary expert LLM assessment, aiming to improve confidence calibration in Medical Visual Question Answering (VQA). Experiments demonstrate that our method reduces the Expected Calibration Error (ECE) by an average of 40\% across three Medical VQA datasets, significantly enhancing MLLMs' reliability. The findings highlight the importance of domain-specific calibration for MLLMs in healthcare, offering a more trustworthy solution for AI-assisted diagnosis.

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

ISE: An Execution-Grounded Recipe for Multi-Turn OS-Agent Trajectories

Training capable OS agents requires data that simultaneously captures structured user intents, multi-turn task delegation, and grounded tool execution–properties absent from existing datasets. We propose ISE (Intent -> Simulate -> Execute), a three-stage synthesis paradigm that addresses these gaps jointly. Stage 1 constructs roughly 50000 structured intents via a 4D framework (Persona x Domain x Task x Complexity); after deduplication the pool contains 43956 unique intents and attains a Vendi Score of 61.57 over the entire pool on mpnet-base-v2 embeddings (cosine kernel, q=1). Stage 2 drives multi-turn user-agent interaction through a role-locked user simulator that grounds each user turn in actual execution outcomes, producing 23132 complete trajectories averaging 8.12 user turns and 68.24 total dialogue turns. Stage 3 runs every tool call inside a live, isolated OS workspace, generating authentic failure-recovery dynamics instead of simulated responses. Fine-tuning on ISETrace improves ClawEval pass@1 from 19.3 to 37.7 using Qwen3-8B on agent tool-use tasks with a standard protocol. This result outperforms zero-shot GPT-4o and the larger Qwen3-32B base model which is four times bigger. An ablation on Stage 2 proves multi-turn simulation brings a large portion of the performance gain. We release all source code and dataset at https://github.com/Valiere01/ISE-Trace.

19.
arXiv (CS.AI) 2026-06-11

ATLAS: Active Theory Learning for Automated Science

arXiv:2606.12386v1 Announce Type: cross Abstract: Advancing scientific understanding through mechanistic modeling requires posing the right experimental questions to yield maximally informative data. To automate this pursuit within cognitive science, we introduce ATLAS (Active Theory Learning for Automated Science), an active learning framework for the data-driven discovery of interpretable behavioral models. ATLAS iterates between generating mechanistic hypotheses–instantiated as a diverse ensemble of sparse neural networks (Disentangled RNNs)–and designing experiments that optimally distinguish between them. We test this approach on the problem of recovering reinforcement learning agents from their behavior in bandit tasks. ATLAS designs varied sequences of qualitatively novel experiments with temporal structure tailored to underlying agent characteristics. The models trained on these experiments are evaluated against a comprehensive set of metrics for mechanistic modeling that capture behavioral, structural, and computational similarity. ATLAS achieves a 5-10x improvement in sample efficiency across all metrics compared to random experimentation, and its performance is further validated against expert-designed experiments derived from literature. These in silico results showcase ATLAS's potential to accelerate human-interpretable insights in cognitive science and other domains where scientific inquiry relies on discovering mechanistic models.

20.
arXiv (CS.CV) 2026-06-17

Enhancing Pathological VLMs with Cross-scale Reasoning

Pathological images are inherently multi-scale, requiring pathologists to integrate evidence from global tissue architecture at low magnification to cellular morphology at higher magnification for accurate diagnosis. While existing pathological datasets for vision-language model (VLM) include various scales, they often lack an explicit cross-scale reasoning objective. This limitation prevents VLMs from capturing essential cross-scale representations and learning evidence-based reasoning. To bridge this gap, we introduce the first cross-scale training and evaluation paradigm that formulates pathology interpretation as multi-magnification reasoning. However, creating such a task reveals a critical challenge: multi-image visual question answering (VQA) is prone to text-only shortcuts, which allow models to guess answers using magnification-dependent artifacts rather than visual evidence. To address this, we propose a leakage-aware curation pipeline that combines adversarial text-only screening with constraint-guided question design. Using this pipeline, we construct Scale-VQA, a high-quality benchmark with 4,685 multiple-choice questions grounded in 2,537 pathology images across multiple magnification levels. Finally, we present ScaleReasoner-R1, a model trained via reinforcement learning to optimize performance on the cross-scale VQA task. ScaleReasoner-R1 achieves state-of-the-art performance on our cross-scale reasoning benchmark and generalizes to SOTA performance on established single-scale benchmarks. Findings suggest that even the limited cross-scale supervision can significantly improve pathological understanding. The code and demos will be open-sourced.

21.
arXiv (CS.CL) 2026-06-12

Small LLMs for Biomedical Claim Verification: Cost-Effective Fine-Tuning, Structural Dataset Shortcuts, and Cross-Domain Generalization

Authors:

Large Language Models such as GPT-4o and GPT-5 achieve strong zero-shot performance on biomedical claim verification, but cost and opacity limit scalable use. We fine-tune three small LLMs: Phi-3-mini (3.8B), Qwen2.5-3B, and Mistral-7B, via QLoRA on SciFact and HealthVer, providing the first study of QLoRA models against GPT-4o and fine-tuned BioLinkBERT encoders. Mistral-7B QLoRA surpasses both GPT-4o and GPT-5 (up to 12% F1 gain) at a fractional cost using just 1,008 training examples. We conduct extensive in-domain and cross-domain evaluation: models trained on SciFact tested on HealthVer and vice versa, at matched sizes to isolate dataset structure from data quantity. We identify a previously unreported structural artifact in SciFact that inflates in-domain scores, and show through bidirectional out-of-domain evaluation that training on structurally sound data enables robust cross-domain transfer. We plan to release all code and adapter checkpoints.

22.
medRxiv (Medicine) 2026-06-22

Biopsychosocial determinants of HPV vaccine perception in university students of both sexes in Cucuta, Colombia, 2024: a cross-sectional study

Colombia has been internationally recognised as a paradigmatic case of vaccine confidence crisis since the 2014 Carmen de Bolivar event, and national HPV vaccination coverage remains far below the World Health Organization 2030 target. Most published evidence focuses on female adolescents and on cervical cancer; the perception of the HPV vaccine in university-age populations of both sexes–and across the broader spectrum of HPV-attributable disease–remains comparatively understudied. We aimed to describe the influence of biopsychosocial determinants on HPV vaccine perception among university students of both sexes in Cucuta, Norte de Santander, Colombia. We conducted a cross-sectional study with a mixed quantitative-qualitative approach in 2024 among four universities (Universidad de Santander, Universidad Francisco de Paula Santander, Universidad de Pamplona and Universidad Libre; combined enrolment 21,033 students). Using convenience sampling stratified by institution, 750 actively enrolled undergraduate students of both sexes (18-60 years) completed a structured online questionnaire adapted from previously validated instruments. The instrument captured sociodemographic information, HPV knowledge and HPV vaccine perception. Data were analysed using Students t-test, one-way analysis of variance, Tukey post-hoc tests, effect sizes and 95% confidence intervals, with a 0.05 significance threshold. Of 750 respondents, 54.2% were women, 61.3% were under 20 years of age, and 75.1% attended public universities. HPV knowledge was high in 39.2%, intermediate in 42.4% and low in 18.4%; women and students aged 26 years or older displayed higher knowledge. Although 91.2% had heard of HPV and 82.5% knew that both sexes could acquire it, recognition of clinical manifestations and complications was uneven: cervical cancer 51.7%, penile cancer 30.5%, vaginal warts 45.9% and warts in the penis, larynx, anus or rectum 34.0%. Vaccine-specific knowledge was low in 77.1%, with men disproportionately represented (85.9% versus 69.5% in women). Overall positive perception of HPV vaccination was 66.6%, slightly higher in women (68.8%) than men (63.9%), in students aged 26 years or older (70.1%) and in students from private universities (68.1% versus 65.9%). Inferential analysis identified sex (Cohens d = -0.357), type of university (d = 0.189) and HPV knowledge (partial eta-squared = 0.096) as the only significant determinants. Age, socioeconomic stratum, age at sexual debut and vaccine-specific knowledge did not reach meaningful significance. HPV vaccine perception was predominantly positive but conditioned by three biopsychosocial determinants, with HPV knowledge as the primary driver. The persistent gender gap reflects historical anchoring of HPV messaging in cervical disease and female-targeted campaigns. Public-health strategies should adopt comprehensive, gender-inclusive educational interventions that explicitly visibilise non-cervical HPV-related cancers and address both sexes from a common evidence base.

23.
medRxiv (Medicine) 2026-06-15

The clinical utility of functional testing in fibroblasts to diagnose primary mitochondrial disease

Genome sequencing of the heterogeneous primary mitochondrial disorders (PMD) frequently reveals variants of uncertain significance that require functional tests for diagnosis, and does not identify variants in all patients. We analyzed mitochondrial enzyme assays, blue native polyacrylamide gel electrophoresis (BN-PAGE) with in-gel activity staining, complex I assembly blot, and select protein abundances in fibroblasts of a case series of 204 PMD patients divided into functional classes, in comparison to 51 controls and 53 differential diagnostic conditions. Overall, sensitivity and specificity for respiratory chain enzyme assays were 46% and 93% respectively, for BN-PAGE 40% and 98%, for complex I assembly assay 49% and 99%. The overall sensitivity of all tests was 76%, specificity 93%, with positive predictive value 96% and negative predictive value 67%. Categories with high sensitivity were isolated complex deficiencies, nuclear DNA-encoded mitochondrial protein synthesis defects, co-factor defects, and mitochondrial amino-acyl-tRNA synthetase conditions when aided by protein abundance. Mitochondrial DNA mutations and maintenance disorders showed poor sensitivities. Secondary dysfunctions were rare. A complete battery of functional tests showed strong diagnostic clinical utility in fibroblasts.

24.
arXiv (CS.CL) 2026-06-18

LLM Compression by Block Removal with Constrained Binary Optimization

In this paper, we formulate the compression of large language models (LLMs) by optimally deleting transformer blocks (``block removal'') as a constrained binary optimization (CBO) problem that can be mapped to a physical system (Ising glass), whose energies are a strong proxy for downstream model performance. This formulation enables an efficient ranking of a large number of candidate block-removal configurations yielding many high-quality, non-trivial solutions beyond those only removing consecutive regions. Our method performs strongly in the deep compression regime, such as for 50% compression of Llama-3.3-70B-Instruct, where we achieve an almost 23 percentage point increase on the MMLU benchmark compared to other state-of-the-art (SOTA) block-removal methods. For lighter compression, it performs on par with those methods across several benchmarks for Llama-3.1-8B-Instruct, Qwen3-14B (both before and after retraining), as well as Llama-3.3-70B-Instruct. The approach is computationally efficient and requires only forward and backward passes on a calibration dataset for a few active parameters. Additionally, we demonstrate that using good heuristic solvers for the CBO problem provides solutions that perform well on downstream tasks in negligible runtime when it is unfeasible to solve the problem exactly. The method can be readily applied to any architecture. We illustrate this generality on the recent NVIDIA-Nemotron-3-Nano-30B-A3B-FP8 model, which exhibits a highly inhomogeneous and challenging block structure, and where we outperform SOTA for AIME25 and GPQA when removing either 2 attention layers or 3 mixture-of-experts layers.

25.
arXiv (CS.CV) 2026-06-16

MatchLM2Lite: A Scalable MLLM-to-Lite Framework for Reproduced Content Identification

Content moderation is critical for online video platforms to ensure content safety, protect creators, and sustain positive user experiences. Beyond filtering harmful content, platforms must guarantee content authenticity at scale so that users are exposed to diverse, original videos rather than low-value reproductions. We present MatchLM2Lite, a real-time, production-grade reproduced content identification (RCI) system that leverages the powerful understanding of a multimodal large language model (MLLM) distilled into a small and fast-inference model. Our system jointly models video, audio, and text signals, operating on pairs of videos to produce fine-grained reproduction scores. The system comprises two modules, MatchLM and MatchLite, and a two-stage training recipe. First, our high-capacity MLLM, MatchLM, serves as a teacher model to define the upper bound of RCI performance. Its capabilities are then distilled into a compact student model, MatchLite. This design allows MatchLite to deliver low-latency, high-throughput inference on video pairs while preserving much of MatchLM's accuracy, making it suitable for integration into real-time recommendation systems. MatchLM achieves an F1-score improvement of +8.57 compared to our previous production model. After knowledge distillation, MatchLite retains a +6.55 gain in F1-score while reducing computational cost by 35x. Deployed at scale, MatchLM2Lite enables efficient, pairwise multimodal RCI, stably serving online traffic at high queries per second (QPS) with an end-to-end latency below 30 seconds. This system has reduced the reproduced video view rate on our platform by 2.5% without degrading user engagement, demonstrating its effectiveness in a large-scale production environment.