Artificial Intelligence · Cross-listed from cs.CL
From Reweighting to Rewriting: Unlocking the Intervention Effects of Influential Samples in Training Data Attribution
Yuzhang Luo, Chenpeng Wang, Jianhui Chen et al. (+1 more)
Training data attribution (TDA) aims to identify training examples that shape model behavior, but its intervention value depends on both which examples are selected and how they are modified. Influence functions (IF) estimate behavioral changes under infinitesimal reweighting, yet IF-selected examples often show limited advantages over random selection under conventional weight-based interventions. This raises the question of whether influential examples lack intervention value or whether reweighting fails to realize their behavioral leverage.We introduce influence-guided response rewriting, which uses IF to identify intervention targets and replaces their responses with behavior-aligned or behavior-opposed supervision while keeping instructions fixed. Across four open-weight LLMs, we compare rewriting and reweighting on the same influence-selected examples using epistemic abstention as our primary testbed. Response rewriting produces stronger, more persistent, and bidirectional behavioral shifts, while reweighting the same examples yields weak and inconsistent effects. Further analyses show that influence-selected examples provide greater rewriting leverage than alternative selectors, with changes remaining concentrated on target-relevant behaviors. The same qualitative contrast extends to safety refusal. These results distinguish the local reweighting effects captured by influence estimates from the broader intervention leverage of the examples they identify, motivating intervention-aware evaluation of TDA methods.
Read the full abstract ▾
All authors Yuzhang Luo, Chenpeng Wang, Jianhui Chen, Liangming Pan
Artificial Intelligence
Measurement-Driven Sub-Network Selection for On-Premise Retrieval-Augmented Factory Agents
Vasileios Rizeakos, Georgios Paisios, Alexandros Machairas et al. (+2 more)
On-premise assistants can give factory workers conversational access to machine documentation, but models capable of the task rarely fit shop-floor hardware. We show that after structural compression and
retrieval-grounded adaptation, model size is no longer a reliable predictor of adapted answer quality: general capability falls almost linearly with parameter count, while judged
retrieval-augmented answer quality does not. We therefore treat deployment as a post-adaptation selection problem, committing one sub-network per device on judged answer quality and measured on-device throughput under a configurable general-capability floor and
memory budget; rules that optimize size, speed, or quality alone each give up capability or throughput. A weight-shared supernetwork trained with sandwich-style in-place
distillation keeps this selection inexpensive. In a manufacturing-manual case study, extraction costs 13.7 percent of the unpruned model's judged quality and
retrieval-grounded
distillation returns it to within 4.6 percent, recovering two thirds of the loss, and the same assistant runs across three heterogeneous edge tiers at 1.3 to 5 watts standby.
Read the full abstract ▾
All authors Vasileios Rizeakos, Georgios Paisios, Alexandros Machairas, Michael Birbas, Athanasios Bachoumis
Artificial Intelligence · Cross-listed from cs.CL
Untangling the Mechanisms of Misleading Context in Medical Question Answering
Robin Linzmayer and Noémie Elhadad
Large
language models now answer medical questions with expert-level performance. However, the context these systems act on can be misleading, and misleading context can corrupt a model's medical judgment. To understand how misleading context corrupts this judgment, we examine the model's susceptibility to the context, disclosure of it, mechanism of corrupted
reasoning, and monitorability of the decision. On the medical
reasoning subset of MedMisBench, a clinician-reviewed question-answering
benchmark of 8,627 questions, we inject two types of misleading context cues, fabricated evidence and a bare assertion. We test three
reasoning models, two that expose their full
reasoning trace and one frontier model that exposes only its response. All three are more susceptible to the assertion than to the fabricated evidence, adopting the asserted answer 10 to 27 points more often. The misleading cues are disclosed in 81 to 98% of traces but only 7 to 90% of responses, and the assertion is disclosed less often than evidence based cues. Resampling from
reasoning traces without disclosure shows the two cues corrupt
reasoning differently, evidence entering early and accumulating while the assertion redirects the conclusion near its end. An LLM monitor catches 78% of corrupted decisions at 5% false positives when reading an open model's trace with guidance, against at most 32% from any response. The misleading context that models are most susceptible to is disclosed least, and was caught reliably only from an open
reasoning trace, which frontier providers withhold.
Read the full abstract ▾
Artificial Intelligence
Bilevel Coordinated Reflection: A Game-Theoretic Approach to Multi-Agent LLM Systems
Yihang Chen, Yuxiang Chen, Yuxuan Huang et al. (+3 more)
Multi-
agent LLM systems commonly use an orchestrator to decompose a task for a team of workers and then improve through textual reflection. Despite strong empirical results, these systems lack a unified account of coordination,
memory improvement, and the role of external verification. We model orchestrator-worker interaction as a bilevel coordination game: under bounded coupling, the workers' local-update game is an approximate potential game whose
equilibrium slack is controlled by decomposition quality. We then analyse reflection as
stochastic movement over semantic
memory states. For free-form reflection, we derive a finite-time upper bound, prove worst-case tightness, and give a positive lower bound under a falsifiable persistent-harm condition. We further prove an information-theoretic impossibility result: no gate that observes only the generated transcript can improve uniformly over text-indistinguishable environments, whereas an environment-grounded gate can. Motivated by this separation, we introduce
Stochastic Reflective
Memory Ascent (SRMA), which accepts a candidate
memory only after a grounded evaluation risk strictly decreases. Under calibration and non-degenerate corrective mass, SRMA converges exactly, geometrically or polynomially; matching constructions show that both rate regimes are order-tight. We also provide confidence gating for
stochastic evaluation and re-anchoring guarantees for piecewise-stationary environments. Experiments instantiate these objects with environment-grounded metrics and test the predicted coordination and drift laws. On 500 SWE-bench instances, the complete Kimi-based system resolves 72.2% versus a 70.8% public mini-SWE-
agent reference. Code: https://github.com/YihangChen9/Bilevel-Coordinated-Reflection
Read the full abstract ▾
All authors Yihang Chen, Yuxiang Chen, Yuxuan Huang, Meng Fang, Weilin Luo, Jun Wang
Artificial Intelligence
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills
Jianlyu Chen, Yuyang Hu, Hongjin Qian et al. (+8 more)
Autonomous
agents are beginning to carry out machine-learning (ML) research end to end. These
agents combine a model backbone with a harness for planning, execution,
memory, and verification, but this architecture still leaves domain-specific know-how outside the
agent. We call this missing layer operational knowledge, the know-how that separates knowing a method from making it work. That knowledge is not absent from the field. It appears in repositories and papers, but in forms written for human readers and too large to load during a task. Once distilled into compact, verified skills, this knowledge can be reused across tasks rather than rediscovered during each run. We present DisCo, a skill-powered research
agent that creates skills and uses them during research. Its
distillation runs in two complementary forms: task-agnostic, condensing the field's widely used repositories into reusable skills, and task-oriented, producing the skills a concrete task calls for. The former, applied across the open ecosystem, yields the AREX-Skill Library, with 5,000+ verified skills distilled from 1,000 widely used ML repositories and organized into 20 areas and 178 capability families. With the GPT-5.5 backbone, research harness, and downstream execution budget held fixed, the skill-equipped research
agent scores 134.3% higher on MLE-bench, 34.4% higher on PaperBench, 9.2% higher on FrontierCS, and 14.0% higher on PassNet than the same
agent without skills. These gains come from adding distilled operating context under that fixed setup.
Read the full abstract ▾
All authors Jianlyu Chen, Yuyang Hu, Hongjin Qian, Jiawei Liu, Wenqing Wei, Xiaolong Chen, Defu Lian, Zhicheng Dou, Chaozhuo Li, Qiwei Ye, Zheng Liu
Artificial Intelligence · Cross-listed from physics.chem-ph
HiPoly: a hierarchical polymer-native AI framework for property prediction and generative design
Ge Sun, Gervasio Zaldivar, Yuan Tian et al. (+5 more)
Polymeric materials are central to modern technologies, with applications ranging from energy to health and transportation. Although AI has made significant advances in materials discovery, the hierarchical structure of
polymers across multiple length scales makes them inherently difficult to represent in a unified and physically meaningful way. Here we introduce HiPoly, a
polymer-native AI framework that processes complete
polymer descriptions through a three-level hierarchical graph architecture built on the G2RINS representation. HiPoly encodes
stochastic inter-monomer connectivity, composition, and molecular weight directly within its architecture, using physically motivated design principles that mirror the multi-scale nature of polymeric systems. The framework establishes an end-to-end AI-driven workflow from experimental formulation data to property prediction, generative molecular design, and physics-based validation through molecular simulations, all unified by a single
polymer representation. We demonstrate state-of-the-art prediction accuracy for thermophysical properties of multi-component
polymer systems, with ablation studies confirming that each hierarchical design choice contributes independently to model performance. As an example, the generative design pathway is applied here to the discovery of sustainable alternatives to persistent fluorinated
polymers, where it is possible to identify and independently validate PFAS-free candidates with target surface-energy properties. This work demonstrates how
polymer-native AI can accelerate discovery by linking representation, prediction, and design across complex
polymer chemistries.
Read the full abstract ▾
All authors Ge Sun, Gervasio Zaldivar, Yuan Tian, Gustavo Perez Lemus, Juhae Park, Daryna Safarian, Ming Han, Juan J. de Pablo
Artificial Intelligence · Cross-listed from cs.CL
Namgyu Ho, Huzama Ahmad, Woosung Koh et al. (+3 more)
Language models spend most of their
attention on a small fraction of context, yet they read the entire KV cache to find the few
tokens that matter. If the user asks about a previous detail in a 1M-
token conversation, global
attention layers must scan the full context to generate each
token of the reply. A prominent approach pre-selects relevant
tokens via lightweight proxy scores, but this extrinsic scoring still incurs O(N) per step. We take an intrinsic approach motivated by the simple question: wouldn't the model already know which parts of the context are relevant? We introduce Declarative
Attention (DA), a protocol that elicits the model to declare where it needs to attend within its chain-of-thought, partitioning generation into three modes: <global> (full context), <focus> (a specific region), and <local> (recent output only). The inference engine parses these declarations like tool calls and skips most of the KV cache read. Under zero-shot evaluation across 15 long-context tasks, DA on off-the-shelf models (Gemma-4-31B, Qwen-3.6-27B) reduces total attended
tokens per response (45.8%, 19.6%), despite extra decoding steps, with modest accuracy drops (1.40pp, 2.10pp) that shrink with model scale. DA unlocks a new axis of sparse
attention, with further potential under training-based methods. Code is available at https://github.com/itsnamgyu/declarative-
attention.
Read the full abstract ▾
All authors Namgyu Ho, Huzama Ahmad, Woosung Koh, Se-Young Yun, Tal Schuster, Cicero Nogueira dos Santos
Artificial Intelligence · Cross-listed from cs.CV
Canjie Liu, Jiawen Kang, Jinbo Wen et al. (+1 more)
Large
vision-
language models have achieved remarkable success in
vision-
language tasks. However, they remain prone to Visual
Hallucinations (VHs), undermining their reliability in real-world applications. Existing solutions typically require curated
datasets, additional training, or multi-round decoding, resulting in considerable computational overhead. In this paper, we propose RVSD (\underline{R}etrieval \underline{V}ision \underline{S}parse \underline{D}ecoding), a training-free and plug-and-play decoding framework that, for the first time, unifies
token sparsification and Semantic-Space Visual
Retrieval (SSVR) within a single decoding pass. Within RVSD, we introduce a semantics-directed
token selection strategy that selectively sparsifies redundant
tokens while preserving critical visual information. We further propose the SSVR mechanism, which reformulates visual compensation as an on-demand cross-modal
retrieval process within a shared semantic space. Extensive experiments demonstrate that RVSD achieves state-of-the-art performance in mitigating VHs while maintaining robust suppression capabilities under long-context generation settings. Our code is available here.\footnote{https://github.com/canjie-liu/RVSD}
Read the full abstract ▾
All authors Canjie Liu, Jiawen Kang, Jinbo Wen, Zishao Zhong
Artificial Intelligence
Door-in-the-Face Requests and Refusal Behaviour in Large Language Models
Til Jordan
Does the door-in-the-face technique work on
language models? In humans, a large request that is refused makes a smaller follow-up request more likely to be granted. We test this on nine production models from three providers: each model refuses a large request, then receives a smaller version of the same request, and we compare its compliance with asking directly. The answer depends on the model. On Anthropic's frontier models the technique works: Opus 5 answers the smaller request 65.8% of the time after refusing the larger one, against 29.3% when asked directly. On the frontier models of OpenAI and Google, and on Haiku 4.5, it backfires, lowering compliance by 15.5 to 23.0 points. A control locates the effect: a refused large request on an unrelated topic does less than the related one on all nine models, so the concession itself matters everywhere, while the reaction to having just refused something differs by model family. The technique does not transfer to refusals drawn from public
benchmarks. What decides whether a retreat can work is what the request asks for: rewriting 265 refused requests for usable instructions into requests for explanations of the same topic removed the refusal in 263 cases. Human influence techniques port to
language models one model family at a time.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
DKL: Decoupled Knowledge Learning for Instruction-Tuned Language Models
Kushagra Bhushan, Meghanadh Pulivarthi, Sai Krishna Reddy Sathi et al. (+7 more)
RAG has become the de facto method for incorporating new, corpus-specific knowledge into an instruction following LLM (Instruct LLM). Although RAG-based prompting improves factual grounding, it fails when
retrieval is incorrect or incomplete, leading to
hallucinations. Finetuning methods such as RAFT and PA-RAG enhance RAG by injecting new knowledge into the model's parameters, but require generating a massive amount of synthetic QA that covers the entire corpus. Extended Pre-Training (EPT) on the text corpus avoids the need for comprehensive synthetic data generation but compromises an Instruct LLM's instruction-following capabilities, necessitating instruction fine-tuning (IFT) after pre-training. However, IFT is costly and may be infeasible due to the unavailability of an instruction-tuning corpus. In this work, we propose DKL-Decoupled Knowledge Learning for Instruction-Tuned
Language Models. Instead of doing EPT on the Instruct LLM, DKL performs EPT on its corresponding base LLM to infuse new knowledge. These knowledge infused weights are then merged with the Instruct LLM, imparting new knowledge without affecting their instruction-following capabilities. DKL is a lightweight method that avoids expensive instruction fine-tuning and relies on model merging to infuse the new knowledge into the Instruct LLM without destroying its instruction following capabilities. Empirical results show that DKL improves RAG accuracy from 54.17 to 79.26 on
retrieval failure cases, while outperforming prior approaches with substantially less training data.
Read the full abstract ▾
All authors Kushagra Bhushan, Meghanadh Pulivarthi, Sai Krishna Reddy Sathi, Gaurav Pandey, Sonam Gupta, Vineet Kumar, Jaydeep Sen, Yatin Nandwani, Sachindra Joshi, Dinesh Raghu
Artificial Intelligence · Cross-listed from cs.CL
From Tokens to Semantics: Leveraging Complementary Signals for Hallucination Detection in Black-Box LLMs
Urja Pawar, Rajitha Ramanayake, Owen O'Neill et al. (+5 more)
When LLMs support public-facing or high-stakes workflows, missed fabrications can harm users and institutions, while false alarms consume limited human-review capacity. When no trusted context or reference document is available, we study two signals accessible through black-box model APIs: semantic
entropy, which measures disagreement among sampled response meanings, and uncertainty derived from
token log-probabilities. Their failure modes can be complementary: semantic
entropy becomes uninformative when responses form one semantic cluster, while
token uncertainty can miss consistently confident errors. We extend
token-based uncertainty detection by aggregating
token-level signals across sampled responses through our TopK method, evaluate the hybrid CoCoA method, which combines target-response uncertainty with semantic dissimilarity, and propose and study two supervised methods: Gated, which routes single-cluster cases to an aggregated-
token-feature classifier, and Stacked, which learns jointly from semantic uncertainty and broader
token features. We evaluate seven
benchmarks, including five public
benchmarks (four text
datasets and
multimodal handwritten-cheque extraction) and two constructed
benchmarks (Financial Summaries and Long-Text QA), using four
language models. In our evaluation across models and
datasets, Stacked gave the best performance in nearly half of the cases, while TopK and CoCoA remain competitive without supervised training labels, although their thresholds require careful calibration. No method is universally strongest. We therefore evaluate performance at false-positive-rate budgets from 1% to 15%, assess their sensitivity to generation and calibration choices, and examine variation across
dataset characteristics.
Read the full abstract ▾
All authors Urja Pawar, Rajitha Ramanayake, Owen O'Neill, Nabeel Kemal, Abhishek Mandal, Houssem Chatbri, Christopher Martin, Vadim Pertsovskiy
Artificial Intelligence · Cross-listed from cs.CV
Characterizing Text Branch Sensitivity in Medical Vision-Language Segmentation via Evidence Decoupling
Ziquan Liu, Zhewei Zhu and Xuyang Shi
Pretrained
vision-
language models (VLMs) have shown promising performance in medical image
segmentation by incorporating clinical text. However, it remains unclear how much textual information actually contributes to pixel-level predictions. In this work, we systematically investigate the role of text in
multimodal medical image
segmentation. We first analyze several commonly used fusion strategies and find that
segmentation performance is largely insensitive to the choice of fusion module. To further understand modality interactions, we propose an Evidence Decoupling Decoder (EDD) based on evidential deep learning and deep supervision. EDD serves as an internal representation analysis tool that decomposes image evidence and text-modulated evidence throughout the decoding process while maintaining competitive
segmentation performance. Experimental results show that the sensitivity to text perturbation varies substantially across
datasets. On BUSI and BTMRI, removing text causes catastrophic performance drops, indicating strong model reliance on textual input. On ISIC and Kvasir-SEG, text exerts relatively marginal influence. We further find that text affects predictions mainly through global semantic modulation rather than independent spatial localization, and that the specific semantic components driving text sensitivity differ across
datasets. These findings provide a deeper understanding of modality interaction in
multimodal medical image
segmentation and offer practical insights for future model design.
Read the full abstract ▾
Artificial Intelligence
Loom: Weaving Diagnostic Strands into Free-Text Consensus via Embedding-Space Reweighting
Ron Begleiter, Katya Egert Berg, Gilad Saban et al. (+1 more)
Aggregating noisy, conflicting textual hypotheses into a reliable consensus is a fundamental challenge when deploying NLP systems in real-world industrial settings. While monolithic Large
Language Model (LLM)
agents offer unbounded expressivity for tasks like Root Cause Analysis (RCA), they suffer from context limits, compounding
hallucinations, and prohibitive inference latency. Traditional weak supervision offers statistical rigor but is mathematically restricted to discrete classes. We present Loom, a generative consensus framework deployed for real-world RCA that bridges these paradigms. Loom aggregates open-form hypotheses emitted by modular heuristics (diagnostic templates dynamically populated with episode-specific entities, times, and metrics) by projecting them into a continuous
embedding space, and resolves conflicting signals with an iterative centroid-based reweighting
algorithm. The resulting consensus weights ground a single lightweight LLM synthesis step. Evaluated on the OpenRCA
benchmark, Loom occupies the accuracy–efficiency Pareto frontier: it matches a state-of-the-art autonomous
agent on Bank and
Market-2 and trails on
Market-1 and Telecom, while using a single LLM call per incident on all four
datasets ($\sim$26$\times$ faster; $\sim$33$\times$ with an 8B-parameter synthesizer). We discuss our deployment experience, highlighting lessons learned regarding the trade-offs between agentic depth and inference latency, negative results in redundancy detection, and how deterministic consensus fosters trust among Subject Matter Experts~(SMEs).
Read the full abstract ▾
All authors Ron Begleiter, Katya Egert Berg, Gilad Saban, Gil Shabat
Artificial Intelligence · Cross-listed from cs.CL
TaRA: Training-Aware Low-Rank Adaptation Initialization
Taehyeon Kim and Eunhyeok Park
Low-Rank Adaptation (LoRA) has become a de facto standard for parameter-efficient fine-tuning (PEFT), yet its performance is highly sensitive to initialization due to the information bottleneck imposed by low-rank decomposition. Existing approaches attempt to construct high-quality LoRA initializations by exploiting principal components of pretrained weights, activations, or gradients. However, these methods do not directly account for the training dynamics of the full-rank model. In this paper, we propose Training-aware Low-Rank Adaptation Initialization (TaRA), a method that initializes LoRA such that the gradients induced by the low-rank factors closely approximate the gradient of the corresponding full-rank weight
matrix. Derived from a mathematical formulation, TaRA improves gradient fidelity at the start of training while introducing negligible computational overhead. Across diverse and challenging fine-tuning tasks, TaRA consistently outperforms prior state-of-the-art methods, establishing a simple, robust, and scalable solution for effective LoRA initialization.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SE
Automated Vulnerability Injection in Smart Contracts Using Large Language Models
Luca Migliaccio, Roberto Natella, Naghmeh Ivaki et al. (+2 more)
Assessing vulnerability detection tools for smart contracts requires
datasets with known ground truth, yet such
datasets are scarce and difficult to build by hand. We propose an approach that uses Large
Language Models (LLMs) to automatically inject vulnerabilities into Solidity smart contracts, and demonstrate it in a case study targeting 49 vulnerability types from OpenSCV. Injected contracts are validated through a multi-step pipeline checking compilation, execution, business logic, and the presence of the intended vulnerability. Applied to real-world contracts from SmartBugs, LLMs generate nearly 1,000 candidate variants; after deduplication and validation, 32 confirmed vulnerable contracts spanning 25 vulnerability types survive (a 16.58% survival rate). Surviving contracts concentrate in structurally simpler targets and vulnerability types with localized syntactic patterns. We report practical challenges including LLMs' non-determinism and the difficulty of preserving contract semantics. We then use the validated contracts to assess three static analyzers, revealing complementary and incomplete coverage profiles. Results show that LLM-based vulnerability injection is feasible, while exposing key limitations in scalability and diversity.
Read the full abstract ▾
All authors Luca Migliaccio, Roberto Natella, Naghmeh Ivaki, Nuno Laranjeiro, Marco Vieira
Artificial Intelligence
Collective creativity in hybrid societies
Mason Youngblood, Katie Mudd, Manuel Anglada-Tort et al. (+4 more)
Generative AI is changing how cultural artifacts are created and circulated, and with it our understanding of creativity itself. Researchers disagree about whether these tools enrich or impoverish culture, and we argue that much of that disagreement comes from conflating two distinct components of creativity: novelty, a property of single artifacts, and diversity, a property of populations. We argue further that creativity in the context of generative AI is best understood as a property of hybrid collectives, or populations of interacting people and
algorithms, rather than of individuals. AI-assisted ideation reliably raises the novelty of individual output while narrowing diversity in the aggregate, but this is not an inevitable consequence of putting machines in the loop. Because humans and models search in complementary ways, mixed groups can outperform and out-diversify groups of either kind alone, and machine-discovered solutions can enter human culture and persist there. What decides the outcome is composition: which
agents are present, in what proportion, and how they are connected. The question is no longer whether AI helps or harms creativity, but which mixtures let individual gains accumulate without eroding collective diversity.
Read the full abstract ▾
All authors Mason Youngblood, Katie Mudd, Manuel Anglada-Tort, Cameron Jones, Elena Miu, Diana Omigie, Margaret Schedel
Artificial Intelligence · Cross-listed from cs.MA
Competitive Market Behavior of LLMs
Pawel Struski, Jakub Swistak, Inez Okulska et al. (+1 more)
Large
language models (LLMs) are increasingly deployed as economic
agents, yet there is little evidence whether LLM
agents are suited for participating in
market mechanisms designed for humans, and whether these mechanisms deliver desired outcomes when faced with LLM
agents. We address this question by replicating seminal economic experiments, replacing human subjects with LLM
agents. We place
agents in a double auction environment, which is a widely-used
market mechanism. We check whether such a
market is able to deliver an efficient allocation of resources, thereby testing a novel dimension of
alignment of LLM
agents – their compatibility with a fundamental
market mechanism. We find that
markets populated by LLM
agents exhibit slower or no convergence towards
market equilibrium, thus providing less efficient allocations than
markets populated by humans. We then analyze
agents' individual trading decisions and find substantial heterogeneity both across model families and
market roles. We also run a lexical analysis of Chain-of-Thought (CoT) traces generated by the
agents. We find that the decision to execute a trade rather than continue incrementally adjusting prices is associated with a shift from strategic considerations toward urgency. We publicly release our testing framework, which can be used for future evaluations.
Read the full abstract ▾
All authors Pawel Struski, Jakub Swistak, Inez Okulska, Przemyslaw Biecek
Artificial Intelligence · Cross-listed from cs.LG
ProbeMatchDTI: Probe-Driven Multi-Scale Biochemical Pattern Matching for Drug-Target Interaction Prediction
Quan Hao, Mengyue Fan, Zifan Dong et al. (+8 more)
Drug-target interaction (DTI) prediction is an important task in AI-driven drug discovery. Although recent biochemical representation learning methods have improved DTI prediction, their passive feature aggregation tends to favor dominant molecular patterns while suppressing weak yet binding-relevant signals, such as functional groups and residue-context patterns, limiting the modeling of multi-scale biochemical correspondences. To address this issue, we propose ProbeMatchDTI, a pattern-probe-driven framework comprising IterProbe and BindingProbe. IterProbe explicitly retains contextual states across refinement depths and uses learnable probes to select them at each position before cross-entity matching, thereby preserving weak biochemical patterns and strengthening associations among functional groups, local motifs, and molecular scaffolds. BindingProbe then characterizes cross-entity drug-
protein complementarity at local biochemical-unit and whole-pair levels, jointly modeling fine-grained interactions and multi-scale correspondences while preserving weaker binding-relevant associations. Extensive experiments demonstrate the superiority of ProbeMatchDTI, achieving 2.0% and 0.5% higher AUC-ROC on BindingDB and DrugBank, respectively. Feature-level pattern analyses further characterize its probe-driven behavior in cross-scale biochemical pattern matching. We further connect ProbeMatchDTI predictions with an evidence-guided downstream drug-discovery workflow, demonstrating their utility for candidate refinement and validation planning. Our code is available at https://github.com/developer-hq/ProbeMatchDTI
Read the full abstract ▾
All authors Quan Hao, Mengyue Fan, Zifan Dong, Youru Li, Jianduo Zhao, Lechuan Xu, Hao Zhang, Fei Xia, Jigang Wang, Chong Qiu, Liguo Zhang
Artificial Intelligence · Cross-listed from cs.LG
Learn from Whoever Is Right: Answer-Verified Multi-Teacher Distillation for Multi-Domain LLMs
Xixiang He, Xingming Li, Baiqi Wu et al. (+4 more)
Modern large
language models (LLMs) rely on reinforcement learning to build strong capabilities in individual domains, but integrating those capabilities into a single deployable model remains challenging. By routing each sample to the teacher whose domain matches it, existing approaches let a domain label decide which teacher provides supervision. However, domain expertise holds only on average: the matched teacher is not always correct on a given sample, while a teacher from another domain sometimes is. The reliable teacher therefore has to be identified per sample, not per domain. In this paper, we introduce Multi-Teacher Self-
Distillation Policy Optimization (MT-SDPO), an on-policy
distillation method that unifies several frozen teachers into one student model. MT-SDPO consists of three components: (1) self-anchors, where a rollout is supervised by a correct rollout from its own group; (2) answer-verified eligibility, where a teacher may supervise a sample only if its own answer passes a verifier; and (3) privileged
distillation, which merges the anchor and all verified feedback into one context that an exponential moving average self-teacher reads and the student does not, thereby keeping one policy at deployment. Across five students from three model families, MT-SDPO lifts the weakest domain of Qwen3-8B by 14.79 points and narrows its domain gap by 74.7%, a better balance than serving one matched teacher per domain. Verified reliability, not domain membership, should decide who teaches. Code is available at https://github.com/hexixiang/MT-SDPO.
Read the full abstract ▾
All authors Xixiang He, Xingming Li, Baiqi Wu, Qiyao Sun, Xuanyu Ji, Ao Cheng, Qingyong Hu
Artificial Intelligence · Cross-listed from cs.CV
Fine-Grained Anomaly Perception in Wild UGC-Enhanced Images: A Comprehensive Dataset and Difference-Fusion Framework
Yan Zhong, Gefei Chen, Qiufang Ma et al. (+4 more)
Image enhancement and restoration have become standard back-end operations on short-
video and social media platforms to boost UGC visual experience. Yet these processes inevitably introduce visual anomalies–especially in faces, texts, and textures–that directly undermine perceptual fidelity and viewer trust. While existing IQA methods perform well on classic distortions, they target holistic quality assessment and fail to capture the specific, localized anomalies caused by enhancement
algorithms in real-world UGC. To bridge this gap, we formally define a new task-quality Anomaly Perception for UGC image Enhancement (UEAP), and contribute the first UEAP
benchmark dataset, named UEAP-4k, curated from the real business scenarios. It provides fine-grained annotations for anomaly categories, localization and severity levels. Furthermore, we propose a Difference-Fusion Anomaly Perception Method (DFAP-UGC) for wild UGC-enhanced images, which leverages explicit problem-reference difference fusion with dense spatial querying, regional verification, and quality-aware ranking, enabling robust anomaly identification in challenging scenarios. To handle the inherent coupling of subtasks in this new task, we propose a Locality-Aware Dynamic Task Prioritization (LADTP) training strategy that enables effective end-to-end learning and eliminates multi-stage overhead. Extensive experiments show that our method outperforms baselines adapted from classical approaches for this task, validating the value of this
dataset and the superior of DFAP-UGC for robust UGC-enhanced image anomaly perception. Code and data will be public.
Read the full abstract ▾
All authors Yan Zhong, Gefei Chen, Qiufang Ma, Zhen Wang, Zhiwei Fan, Lei Shi, Tingting Jiang
Artificial Intelligence · Cross-listed from cs.LG
Spectral Initialization and Scheduled Graph Smoothness for Uncertain Knowledge Graph Completion
Md Abrar Jahin, Taufikur Rahman Fuad, Jay Pujara et al. (+1 more)
Uncertain knowledge graphs (UKGs) extend knowledge graphs by assigning each triple a continuous confidence score. Since most possible triples lack observed confidences, recent methods rely on semi-supervised learning to generate pseudo-labels. These methods initialize entity
embeddings without using the confidence-weighted graph, discarding its global community and hub structure. We introduce QUEST, which adds no trainable parameters to the standard confidence-distribution learning pipeline. First, QUEST initializes entity
embeddings using the smallest non-trivial eigenvectors of the confidence-weighted graph
Laplacian, incorporating community and hub structure before training. Second, QUEST applies an unbiased mini-batch Dirichlet energy regularizer to enforce early-stage structural consistency. On two UKG
datasets, QUEST improves confidence prediction and link prediction on six of eight metric-
dataset pairs over prior methods and matches the previous best on the remaining two, while removing the instability spike observed on dense graphs. These results indicate that spectral structural priors combined with a graph Dirichlet energy regularizer improve accuracy, training stability, and checkpoint reliability in UKG completion.
Read the full abstract ▾
All authors Md Abrar Jahin, Taufikur Rahman Fuad, Jay Pujara, Craig A. Knoblock
Artificial Intelligence · Cross-listed from cs.CV
Blending Concepts: Benchmarking Visual Metaphor Generation in Text-to-Image Models
Chuer Chen, Zichen Wang, Yi He et al. (+2 more)
Text-to-image (T2I) models have achieved remarkable success at faithfully rendering specified objects and attributes, yet their ability to produce visual metaphors, images that convey abstract ideas by combining elements from two distinct domains, remains largely unexamined. To bridge this gap, we introduce VMetaphor-Bench, the first
benchmark for evaluating visual metaphor generation in T2I models. It comprises 1,500 visual metaphors curated from real-world creative imagery, organized into three levels and ten categories, with each sample paired with two
prompts of differing specificity. For evaluation, we develop a hybrid framework within an MLLM-as-judge paradigm, combining a multiple-choice question (MCQ) based protocol of 9,594 questions across four levels of metaphorical fidelity with a dimension-based scoring protocol along three perceptual dimensions. Extensive evaluation of 11 representative T2I models reveals that even the strongest proprietary models struggle with compositional structuring and cross-domain mapping, key aspects of metaphorical expression, highlighting visual metaphor generation as an important frontier for future T2I research.
Read the full abstract ▾
All authors Chuer Chen, Zichen Wang, Yi He, Zhengxi Yu, Nan Cao
Artificial Intelligence · Cross-listed from cs.LG
RINSE: Robust Target-Time Normality Estimation for Zero-Shot Graph Anomaly Detection
Taufikur Rahman Fuad, Md Abrar Jahin and Amir Hussain
Zero-shot graph anomaly detection seeks to deploy a detector trained on source graphs to unseen, unlabeled targets, yet domain shift can make source-derived notions of normality unreliable. We introduce RINSE (Robust Iterative Normality Self-Estimation), a gradient-free target-time framework that keeps the source-trained detector fixed while sequentially estimating target normality, representation calibration, and evidence reliability from the target graph. Its core idea is to identify a reliable subset of low-residual target nodes, use them to construct a trimmed target-aware normality model, and combine complementary anomaly evidence through reliability-gated rank fusion and encoder ensembling. Across eight unseen target graphs, RINSE achieves the highest average AUPRC among the evaluated methods under two separate preprocessing protocols, while block ablations and sensitivity analyses support the combined design. These results support robust target-time estimation as a practical approach to generalist graph anomaly detection without target labels, gradients, or per-target tuning.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.IR
ViSAR: Training-Free Adaptive-$k$ Retrieval for Visual Document Question Answering
Adrien Mialland, Marc Plantevit, Julien Gallois et al. (+1 more)
Document Visual Question Answering (DocVQA) often leverages
Retrieval-Augmented Generation (RAG), where late-interaction encoders are commonly used to identify document pages relevant to a user query, before answer generation by a Large
Vision-
Language Model (LVLM). Existing approaches typically retrieve a fixed top-$k$ number of pages regardless of query complexity, which increases LVLM latency and may degrade answer accuracy. We introduce ViSAR (Visual Semantic Activation
Retrieval), a training-free adaptive-$k$
retrieval method for late-interaction visual document
retrieval. ViSAR operates directly in the
embedding space to construct a query-conditioned page-level similarity
matrix that highlights query-relevant semantics and dynamically determines the number of pages to retrieve. Across multiple encoders and LVLMs, ViSAR retrieves compact, query-adapted page sets that reduce RAG latency by up to 58.7%, while maintaining or improving answer accuracy compared with fixed top-$k$ and adaptive
retrieval heuristics. Furthermore, we show that the similarity
matrix structure correlates with answer accuracy, suggesting future directions for
retrieval quality-aware document understanding.
Read the full abstract ▾
All authors Adrien Mialland, Marc Plantevit, Julien Gallois, Céline Robardet
Artificial Intelligence · Cross-listed from cs.LG
DeepAffinity: Long-Term Aspect Preference Prediction in eCommerce using Small Language Models
Yotam Eshel, Guy Hadad, Guy Feigenblat et al. (+3 more)
We explore predicting eCommerce user preferences for product aspects such as brand, size, and color - a task we define as Aspect Affinity. Solving this task improves customer understanding and enables fine-grained personalization in recommendation, search, and marketing. We frame Aspect Affinity as a temporal prediction task:
forecasting a users future aspect choices from their time-ordered interaction history, capturing long-term preferences that evolve beyond the current session. To this end, we propose DeepAffinity, which leverages Small
Language Models (SLMs) with structured
prompts and specialized prediction heads fine-tuned for this task. We show DeepAffinity outperforms standard generative fine-tuning methods, while general-purpose open-source LLMs perform poorly without task-specific tuning, highlighting their limits in modeling nuanced behavior. Finally, DeepAffinity enhances recommendation quality on a large-scale multinational eCommerce platform.
Read the full abstract ▾
All authors Yotam Eshel, Guy Hadad, Guy Feigenblat, Yuri M. Brovman, Matt Gearhart, Bracha Shapira
Artificial Intelligence
CivBench: A Long-Horizon Benchmark for Tool-Mediated Agents in Civilization VI
Austin Tudor David Andrews, Liam Wilkinson, Jamie Heagerty et al. (+3 more)
We present CivBench, an open-source
benchmark for evaluating
language model
agents in long-horizon, tool-mediated environments through the Model Context Protocol (MCP). A single episode spans 300+ turns and produces thousands of tool calls over a large action space, requiring sustained planning, state monitoring, and execution under partial observability. The environment exposes 76 MCP tools and a narration layer that converts visual game state into structured text. We use CivBench to characterise
agent behaviour across four model families in 23 admissible runs. The sample is a pilot, not a model ranking: aggregate outcomes do not reliably discriminate models at this scale. Instead, we introduce two interface-level metrics that the environment makes measurable: Proactive Monitoring Rate (PMR), capturing whether
agents actively query latent strategic state, and RAG@10, capturing whether commitments stated in structured planning reflections are executed within ten subsequent turns. Across runs we observe two consistent patterns under a shared playbook protocol.
Agents under-monitor strategically relevant state that is available but requires explicit querying: despite playbook guidance to query victory progress every 20 turns,
agents do so only every 30 to 75 turns, and in 7 of 20 detectable defeats they failed to query within the 20 turn warning window before game end.
Agents also frequently fail to execute near-term commitments stated in their own planning reflections (RAG@10 between 48.2% and 65.8% across models). Both patterns arise despite tool access and explicit guidance, and we interpret them as deviations under instruction rather than absences of capability. We release the environment, scenarios, logs, metrics, and analysis pipeline at https://github.com/lmwilki/civ6-mcp
Read the full abstract ▾
All authors Austin Tudor David Andrews, Liam Wilkinson, Jamie Heagerty, Harry Coppock, Jakob Nicolaus Foerster, Rui Ponte Costa
Artificial Intelligence · Cross-listed from cs.CY
Addressing Trust in AI Systems through Education: A Didactic Perspective
Pierre Haritz, Hendrik Krone and Thomas Liebig
Machine learning (ML) education faces two persistent and connected obstacles: many educational tools present ML as an opaque black box, which leaves learners with a superficial understanding, and this same opacity prevents users from forming the calibrated trust that appropriate reliance on AI systems requires. We present ICE-T, a didactic framework that integrates three mutually reinforcing facets: intermodal transfer grounded in Bruner's enactive, iconic, and symbolic modes of representation, computational thinking operationalized through the Use-Modify-Create progression, and explanatory thinking supported by a process model. Connecting the framework to the empirical literature on
algorithm aversion, AI literacy, and mental model formation, and to systematic reviews of the K-12 ML activity landscape, we argue that the three facets supply the cognitive mechanisms that the trust calibration literature identifies as drivers of appropriate reliance: representational richness, graduated process control, and the capacity to contextualize errors. On this basis, we propose that trust calibration be treated as an explicit educational objective, with ICE-T as a principled and scalable means of achieving it.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Scalable Kronecker-Fisher Approximation: Efficient Hessian Analysis for Billion-Parameter Language Models Compression
Viacheslav Yusupov, Daria Cherniuk and Evgeny Frolov
In this paper, we propose a scalable Kronecker-based approximation that captures cross-layer interactions without storing the entire Fisher
matrix, enabling practical Hessian analysis for billion-parameter networks where full computation is infeasible. Our approach reveals consistent vulnerability patterns: value projection layers exhibit the highest sensitivity and strongest cross-layer correlations across multiple model families, while other components exhibit architecture-specific behaviors. Through extensive experiments on quantization, sparsification, inter-layer corruption, and post-corruption fine-tuning, we demonstrate that our approximation strongly correlates with both performance degradation and recovery. Our framework provides a practical, theoretically grounded tool for identifying fragile components in large models, opening new avenues for guided compression and optimization strategies, such as mixed-precision allocation, layer-wise sparsity, and adaptive low-rank decomposition across layers and even individual weight groups.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Towards One-for-All Robustness Across a Continuum of Threat Levels
Zhichao Hou and Xiaorui Liu
Adversarially robust models often overfit to a specific attack budget, necessitating multiple specialized models for diverse and dynamic
adversarial environments, a strategy that becomes fundamentally intractable as the threat space grows. This raises an open challenge: can we achieve strong robustness across a continuum of threat levels within a single model? We propose the Threat Conditional Network (TCN), grounded in a representation factorization framework that decomposes representation learning into a threat-invariant shared backbone and a lightweight threat-conditional adaptor. TCN conditions a single model on the perturbation level via
Fourier-based
embeddings and channel-wise affine modulation, and is trained against a distribution over perturbation budgets, enabling flexible and seamless adaptation across an infinite continuum of threat levels during inference. Extensive experiments on CIFAR-10, CIFAR-100, and Tiny-ImageNet show that TCN matches or surpasses a full ensemble of budget-specialized models with a single set of parameters, generalizes to unseen perturbation budgets, and transfers robustly under mismatched threat conditions, with only 4.6% parameter overhead. These contributions chart a promising path toward adaptive and generalizable robustness in dynamic and diverse threat environments.
Read the full abstract ▾
Artificial Intelligence
UTP-Bench: Uncertainty-aware Travel Planning Benchmark
Etcharla Revanth Rao, Priyanshu Karmakar, Shubhojit Mallick et al. (+3 more)
Large
Language Models (LLMs) have recently demonstrated strong capabilities in automated travel itinerary generation. However, real- world travel planning is inherently uncertain: transportation delays, crowd fluctuations, and unexpected
stochastic delays frequently inval- idate otherwise feasible schedules. Existing
benchmarks like TravelPlanner and TripCraft assume deterministic environments, evaluating only static constraint satisfaction and ignoring whether generated plans remain robust when such uncertainties arise. To address this limitation, we introduce UTP-Bench1 , a large-scale
benchmark for uncertainty-aware travel planning. The
dataset integrates real-world travel data spanning 504 cities of India, including attractions, restau- rants, accommodations, and multi-modal trans- portation networks. To model realistic disrup- tions, UTP-Bench incorporates empirical delay distributions and crowd-density patterns col- lected from major cities, enabling evaluation of travel plans under
stochastic conditions. We further propose three evaluation metrics, namely Buffer Adequacy Score (BAS), Crowd- Aware Timing Score (CATS), and Transport Delay Absorption Score (TDAS), which quan- tify the ability of generated itineraries to main- tain robustness against transit delays and crowd variability. Experiments with state-of-the-art LLMs like GPT-5, Qwen3, Mistral and Phi-4 re- veal substantial gaps between model-generated and human-authored plans, particularly in tem- poral buffering, delay-aware transportation scheduling, and crowd-sensitive planning.
Read the full abstract ▾
All authors Etcharla Revanth Rao, Priyanshu Karmakar, Shubhojit Mallick, Manish Gupta, Shreya Ghosh, Abhik Jana