Computation and Language
STONIC: A Layered Measurement Contract for LLM Value Profiling
Andrei Chetvergov, Stepan Ukolov, Timofei Sivoraksha et al. (+4 more)
LLM value studies often merge questionnaire ratings, pairwise choices, and values inferred from generated text into one profile. That merge assumes that the three observations describe the same stable preference. STONIC tests this assumption on 5,144 situations from four banks and 35 fixed model configurations. It compares responses rated in isolation, choices made under counterbalanced conflict, spontaneous answers, and later choices between a model's own answer and authored alternatives. 10 of 17 configurations with usable behavioral data preserve the endorsement-choice relation across banks. Every one of the 17 eligible configurations prefers its own earlier answer (median effect 0.790), although option position changes the choice rate in every eligible configuration. Profile shape transfers most strongly from ratings to conflict choices and weakens for spontaneous text. Three-way annotation of 200 L3 responses provides a task-local check of the semantic audit: FULCRA agrees most closely with the human majority, while DeBERTa retains useful rank information after calibration. Hidden states encode the completed decision more clearly than the
prompt alone. Thus the models show reproducible behavioral continuity, but the evidence does not support one scorer-independent value identity across interfaces.
Read the full abstract ▾
All authors Andrei Chetvergov, Stepan Ukolov, Timofei Sivoraksha, Alexander Evseev, Danil Sazanakov, Mikhail Solovev, Sergey Bolovtsov
Computation and Language
Cross-Domain, Multi-Task Data-to-Text Generation without In-Domain Training Data
Yifei Song, Kun Efimov-Zhang and Claire Gardent
Structured data exists in many forms (tables, knowledge graphs, charts, and time series), and converting it into text may involve different generation tasks. However, most prior work on data-to-text (D2T) generation has focused on specific tasks and
datasets, relying either on task-specific training data or on the zero-shot capabilities of large
language models. We study cross-domain D2T generation in a setting where neither in-domain training text nor test references are available, and where domains, generation goals, and input structures vary substantially. We compare data-driven knowledge
distillation (DDKD) against zero-shot inference and fine-tuning on out-of-domain D2T data, and introduce structure-preserving augmentation via structural subsampling and perturbation. Experiments on five
benchmarks show that, at constant model size (1.7B parameters), DDKD consistently outperforms both fine-tuning and zero-shot inference. Moreover, the resulting small models outperform a much larger finetuned model on two of the five domains, achieving comparable performance on the remaining three. We further construct QUINTD-5, a fivefold extension of QUINTD-1, and show that simply scaling real target-domain inputs yields only modest gains, whereas our augmentation strategy remains more effective and more cost-efficient for cross-domain
distillation.
Read the full abstract ▾
Computation and Language
Cross-lingual Biography Enrichment via Claim Extraction and Alignment
Yifei Song, Ziyang Chen, Emil Sayilov et al. (+1 more)
English Wikipedia is often treated as the default encyclopedic source, yet non-English Wikipedia editions can contain richer locally grounded information for long-tail figures. We study cross-lingual biography enrichment: enriching an existing English biography with facts supported by a non-English biography about the same person. Focusing on women from non-English-speaking contexts, we introduce CLAW-4L, a
benchmark consisting of 300 Wikipedia biography pairs linking an English biography with its French, Chinese or Azerbaijani counterpart, along with claim annotations and a fine-grained claim-pair relation corpus. We propose a claim-based enrichment framework that extracts English claims from both biographies, aligns them to identify enrichment evidence from the non-English biography, and rewrites the English biography using the selected claims. Our results show that non-English Wikipedia biographies provide valuable evidence for improving English biography coverage, while lower-resource settings remain challenging.
Read the full abstract ▾
All authors Yifei Song, Ziyang Chen, Emil Sayilov, Claire Gardent
Computation and Language
The Geometry of Low-Resource Language Representations
Francois Meyer and Jan Buys
The performance gap between low- and high-resource
languages in LLMs is widely known, but it remains unclear which internal model factors drive these disparities. In this paper, we characterise this gap through the lens of representational geometry. Comparing the
geometric properties of hidden representations across 30
languages reveals that LLM geometry is systematically related to
language data availability. The most consistent effect is in final layers, where low-resource
languages exhibit representational degeneration. To counter this, we investigate the effectiveness of regularisation terms to penalise degeneration during continued pretraining (CPT). Experiments monolingually adapting 9 base LLMs to 10 African
languages show that
geometric regularisation successfully reduces representational degeneration during CPT. For larger models, cosine similarity-based regularisation marginally improves performance over vanilla CPT, with more consistent gains on the most challenging tasks. We establish that the representational geometry of low- and high-resource
languages in LLMs is measurably distinct, and that targeted
geometric intervention is a viable strategy for improving CPT for low-resource
languages.
Read the full abstract ▾
Computation and Language
FormuEvo: LLM-Guided Evolution for Discovering Solver-Efficient Mixed-Integer Programming Formulations
Haofeng Yuan, Jianing Peng, Jieyi Bi et al. (+3 more)
Mixed-integer programming (MIP) lies at the core of operations research and industrial optimization. While large
language models (LLMs) have recently shown promise in automated MIP modeling from natural
language, they prioritize semantic correctness but overlook formulation strength, severely bottlenecking the efficiency of downstream solvers. We propose FormuEvo, an LLM-guided evolutionary framework for automated discovery of solver-efficient MIP formulations. FormuEvo frames MIP formulation design as evolutionary optimization over the symbolic space of MIP formulations, represented as executable modeling programs, by iteratively generating, evaluating, and selecting stronger candidates via LLM-driven crossover, mutation, and repair operations. To move beyond blind exploration, FormuEvo introduces a solver-informed diagnosis mechanism that exploits fine-grained solver statistics as verbal gradients for targeted refinement. Additionally, a structured
memory abstracts prior experience into reusable modeling strategies, avoiding redundant exploration while enabling zero-shot transfer to unseen problems and bootstrapping smaller LLMs. Experiments across diverse linear and non-linear problems demonstrate that FormuEvo discovers formulations that significantly outperform both expert-designed formulations and existing LLM-based approaches, accelerating solvers by up to 5.5$\times$, with distilled knowledge transferring effectively across problems and model scales.
Read the full abstract ▾
All authors Haofeng Yuan, Jianing Peng, Jieyi Bi, Ni Zhang, Shiji Song, Zhiguang Cao
Computation and Language
The Emergence of Relevance Through Axiomatic Attention Patterns During LoRA Fine-Tuning
Matthew Perlman, Atharva Nijasure and James Allan
LoRA fine-tuning is standard for adapting LLMs to reranking, but it remains unclear where in the network task-specific relevance behavior is learned and what
attention-level changes accompany that learning. Through ablation and
attention experiments, we identify where LoRA
attention updates to RankLLaMA improve performance and whether those gains coincide with interpretable relevance-oriented
attention patterns such as lexical matching, rarity sensitivity, and query-document interaction. We find that given LoRA fine-tuned MLPs throughout the network, restricting LoRA
attention updates to a compact mid-network region is sufficient for recovering over half of the performance gained by applying LoRA to all
attention layers, and that omitting
attention fine-tuning in this region hurts performance more than elsewhere in the network. Additionally, we show that regions where applying LoRA affects performance the most overlap with regions where fine-tuning increased
attention to axiomatic IR features. Rarity sensitivity, document-query interaction, and several compositional features are highly correlated with gains in ranking performance. Our results support an interpretable, correlational account of how relevance-oriented behavior emerges during LoRA fine-tuning and point toward improved strategies for adapting rerankers.
Read the full abstract ▾
Computation and Language
Flesch-Kincaid Readability Depends Only on the Topic Distribution in Long Texts under Topic Models
Yo Ehara
Flesch Reading Ease (FRE) and the Flesch-Kincaid Grade Level (FKGL) are widely used readability scores for English computed from the same two document statistics, yet their stability on long documents need not imply invariance to lexical composition. Surprisingly, under a topic model with an explicit sentence-boundary
token, both scores converge almost surely to deterministic functions of the document topic distribution through just two scalar rates: in the long-text limit, all score variation is mediated by topical composition rather than any residual readability signal. The theory covers both formulae, while the experiments evaluate FKGL. In a fixed admixture with rank[1, q, s] = 3, fibres through interior topic vectors are locally (K-3)-dimensional, whereas regular iso-score level sets are locally (K-2)-dimensional and curved. In out-of-fold evaluation on two balanced corpora, Brown and the written BNC, a topic vector inferred from one document half's content words predicts the other half's FKGL at r = 0.779 and 0.884, respectively. On Brown, adding the topic prediction to genre and mean content-word syllable count yields $\Delta R^2$ = 0.002, with a confidence interval spanning zero; on the BNC, the corresponding split-half increment is 0.024, positive in four of five K = 100 fits (median 0.021). Because inferred topics may also absorb genre, register, and style, we do not interpret these results as evidence about human readability or causal effects.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.AI
Agent-G$^2$: Gaussian Guidance for Agentic Reinforcement Learning
Zixuan Wang, Yanrui Miao, Zhengxi Lu et al. (+6 more)
Hint-based reinforcement learning addresses reward sparsity in long-horizon agentic tasks by retaining a prefix of an expert trajectory before each rollout, letting the policy explore from a state closer to success. Its effectiveness hinges on the guidance depth: how much of the trajectory to keep. Existing methods treat this depth as a deterministic scalar. Scheduled approaches share one value across samples and ignore per-task heterogeneity; per-sample probing estimates it separately at the cost of extra rollouts. We find that useful guidance occupies a band of depths whose informativeness profile is approximately Gaussian around the band center, rather than concentrating at a single optimal point. We propose
Agent-G$^2$, a Gaussian guidance framework that draws the depth per task from a Gaussian whose center and spread are estimated online from rollouts already collected for policy optimization, requiring no probe rollouts or learned depth predictor. The center combines a global baseline with per-cluster difficulty, and the spread tracks within-cluster variance. We evaluate
Agent-G$^2$ on ALFWorld and WebShop on Qwen2.5-1.5B / 7B-Instruct.
Agent-G$^2$ outperforms the strongest hint-based, hint-free, and Aux-RL baselines on ALFWorld by 2.3 / 3.9 / 7.4 points at under one-third the rollout cost of per-sample probing.
Read the full abstract ▾
All authors Zixuan Wang, Yanrui Miao, Zhengxi Lu, Teng Pan, Yiwen Qiu, Hongxing Li, Peng Qiu, Ruiqing Zhang, Yongliang Shen
Computation and Language
Beyond the Stability-Exploration Dilemma: Environmental Regularization for LLM Policy Optimization
Xianlei Zhou, Xiangdi Meng, Yu He et al. (+7 more)
Policy optimization (PO) for Large
Language Models faces a stability–exploration trade-off, currently mediated by an action-side Policy-KL regularizer. This puts practitioners in a double bind: keeping Policy-KL constrains response behavior and consumes the action-side exploration budget, while dropping it leaves the optimization without an explicit drift control. We argue for an alternative that breaks the dilemma by moving regularization to the input side. As training progresses, the distribution over training queries induced by the current policy drifts unchecked from its pre-RL reference distribution. Concretely, Environment-Regularized Policy Optimization (ERPO) introduces a Query-KL (QKL) term that bounds this query distribution shift, together with a
dataset-static reference-derived per-query weight that biases each per-query update toward queries typical under the reference. The QKL gradient flows strictly through the query likelihood; the response score function used by policy-gradient
estimators does not appear in the QKL term, so QKL exerts no direct gradient pressure on the response distribution—exploration is preserved. ERPO plugs into GRPO/PPO/REINFORCE-style pipelines without additional forward passes. On six mathematical
reasoning benchmarks, ERPO replaces the standard Policy-KL regularizer while achieving effective control over query distribution drift, delivering stronger accuracy and substantially more stable behavior under high-temperature decoding and long-horizon training. Our source code are available at https://github.com/AlibabaResearch/ERPO
Read the full abstract ▾
All authors Xianlei Zhou, Xiangdi Meng, Yu He, Tianyu Qi, Shuyan Guan, Xianli Zhang, Jian Zhang, Xin Li, Qika Lin, Jun Liu
Computation and Language
Dynamic Topic Modeling for Cross-Corpus Temporal Analysis
Ruoxuan Li and Bruce Kogut
Dynamic Embedded Topic Models (D-ETM) provide an interpretable framework for modeling temporal semantic
evolution, but cross-corpus comparison remains difficult because topics are often learned independently and aligned only after training, a process that does not guarantee stable topic correspondence across corpora and time. To address this problem, we propose a D-ETM framework that first learns a common dynamic topic space over a merged multi-corpus collection, which we call the shared backbone, then introduces corpus-specific residual adaptation around the frozen backbone without creating separate latent topic spaces. This design preserves a shared topic index for cross-corpus comparison while allowing each corpus to specialize lexically. We evaluate the framework on three temporally structured corpora spanning 97 years: the Corpus of Historical American English, Harvard Business Review, and International Labour Review. Residual adaptation improves corpus-specific fit relative to the shared backbone while preserving the same-index cross-corpus topic trajectories, achieving substantially stronger
alignment than full fine-tuning from the same backbone, with $97.5 \pm 0.7\%$ versus $17.9 \pm 1.1\%$ trajectory
Retrieval@1, as well as stronger
alignment than independent training with post-hoc Hungarian matching. These results suggest that incorporating topic
alignment into the model can support more stable over-time cross-corpus comparisons while retaining corpus-specific lexical variation.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.AI
Apodex 1.1: Scaling Agentic Intelligence for Complex Work
B. An, B. Li, B. Wang et al. (+72 more)
General-purpose
language models can reason and synthesize knowledge, but complex work also requires sustained interaction with files, information sources, and executable code, together with state maintenance, failure recovery, and verifiable delivery. We call this working capability: sustained, verifiable progress toward a real-world objective. Apodex 1.1 develops this capability along two complementary dimensions. Environment Scaling expands the diversity and verifiability of executable file, search, and code environments, while Agentic Coordination Scaling trains
agents to decompose long-horizon tasks, delegate parallel work, integrate asynchronous results, and replan. A shared execution harness and AgentOS maintain task state and provenance across tools and
agents, and training turns environment trajectories and coordination traces into reliable behavior. Across complex professional work, finance, scientific research, mathematics, coding, and search, Apodex 1.1 reaches the leading performance band despite using a substantially smaller model than many frontier systems. The 35B-parameter Apodex 1.1 Mini further retains strong working capability in a locally deployable form. These results ground agentic intelligence in useful, verifiable work completed over time and advance our goal of building a Heavy-Duty Solver for ambitious, long-running tasks.
Read the full abstract ▾
All authors B. An, B. Li, B. Wang, B. Zhang, B.L. Wang, C. Feng, C. Wei, C. Xue, C. Zhang, D. Ng, D. Ye, E. Min, F. Chen, F. Liu, F. Yang, F. Ye, G. Sun, H. Ji, H. Xu, H. Yang, H. Ye, H. Zhang, H. Zhao, J. Li, J. Lin, J. Xia, K. Jin, K. Wang, K. Yang, L. Bing, L. Lei, L. Su, Le. Wang, Lu. Wang, N. Wang, Q. Ren, Q. Yang, R. Li, S. Bai, S. Du, S. Li, S. Lin, S. Nie, S. Wang, S. Zhang, S.Z. Wang, T. Ge, Ta.Q. Fang, Ti.Q. Fang, W. Fang, W. Li, W. Zhang, X. Chen, X. Li, X. Tang, X. Wang, X. Xu, X. Zhang, X.Q. Wang, X.Y. Wang, Y. Deng, Y. Gao, Y. Hu, Y. Li, Y. Sui, Y. Wang, Y. Xiao, Y. Zhang, Y. Zhou, Z. Chen, Z. Cheng, Z. Feng, Z. Liang, Z. Liu, Z. Zhang
Computation and Language · Cross-listed from cs.CY
Expectations and Practices around AI Disclosure in CS Research
Arati Mohapatra and Danish Pruthi
As generative AI tools find increasing use in research workflows, ongoing debates on their impact, appropriateness and responsible use have led policymakers to enact policies to disclose AI use at multiple publishing venues. However, are current AI disclosure policies and practices reflective of their purpose? In this work, we first investigate disclosure policies of top computer science venues and find that despite their prevalence, they remain highly under-specified. Secondly, through a survey of computer science researchers (N=$109$), we characterize the necessity of disclosures across different research tasks and levels of human involvement. We learn that researchers find disclosures most necessary for tasks involving research design, and for tasks when the human involvement is low. We also compile expectations that researchers have about the information to be conveyed in AI disclosure statements. Lastly, through an analysis of $13867$ disclosure statements from EMNLP $2025$ and ICLR $2026$, we reveal a large disconnect between these expectations and AI disclosures in practice—a
prime example being writing assistance which is deemed less necessary but is frequently disclosed. We conclude with recommendations to align AI disclosure policies and practices with expectations, suggesting a categorization of research tasks by perceived necessity and a boilerplate template capturing expected details.
Read the full abstract ▾
Computation and Language
EvoWiki: Incremental State Overwriting and Traceable Question Answering for Cross-Meeting Knowledge Evolution
Dongsheng Chen, Tianyu Wang and Wenhui Que
In long-term collaboration spanning multiple meetings, factual states such as decisions and risks are continually revised, overturned, and replaced. Existing long-context methods typically stack the entire history, while many RAG and structured-
memory methods organize knowledge as static or append-only facts and rely on semantic relevance at read time. Without explicit modeling of knowledge lifecycles, these approaches may retain conflicting old and new states simultaneously or discard history, leading to stale
retrieval and answers that are difficult to verify. We present EvoWiki, an incremental question-answering architecture for dynamic long-form text. EvoWiki decouples offline incremental construction (BUILD) from online structured reading (READ). BUILD captures the intra-meeting micro-
evolution from proposal to decision and uses entity version chains and a fine-grained State-Overwrite Protocol to explicitly distinguish current valid states from superseded history while preserving meeting-level provenance anchors. READ bypasses relevance-based Top-k
retrieval and performs deterministic entity addressing, temporal resolution, and cross-entity multi-hop aggregation over the complete Wiki to produce grounded and traceable answers. We further introduce CrossMeet, a high-fidelity bilingual
benchmark designed to simulate long-term state
evolution, covering factual consistency, temporal
reasoning, and cross-meeting multi-hop
reasoning. Across six
datasets and two reader models, EvoWiki improves macro-average Judge Accuracy over the strongest baselines by 9.72 and 10.00 percentage points, respectively. Human evaluation shows that EvoWiki is more robust and factually faithful under frequent state flips, validating valid-state-oriented reading as a reliable approach to cross-meeting knowledge
evolution.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.AI
Hidden in the Request: Explaining Unethical LLM Compliance through Token Relevance
Or Biton, Tomer Krichli, Itai Allouche et al. (+1 more)
Although Large
Language Models (LLMs) are aligned to optimize for both helpfulness and harmlessness, these dual objectives may conflict, inevitably leading to
alignment failures. This work systematically investigates instances where LLMs fail to exhibit ethical behavior. To understand the underlying mechanics of these vulnerabilities, we introduce a probing methodology that presents unethical scenarios to LLMs in three distinct structural modalities: objective classification tasks, subjective first-person statements, and direct requests for assistance. We find that model performance degrades in the request-for-assistance-based form. Using Layer-wise Relevance Propagation (LRP), we trace this discrepancy to an attribution bias: the model places greater emphasis on benign task-framing
tokens (e.g., "Can you help me...") than on
tokens signaling the underlying unethical behavior (e.g., "without getting caught"), which we term cue-
tokens. We hypothesize that this under-attribution contributes to harmful compliance. To test this, we introduce two LRP-guided decoding methods that steer generation toward trajectories more relevant to cue
tokens. Empirical evaluations show that these interventions promote safer responses, supporting cue-
token attribution's role in compliance failures.
Read the full abstract ▾
All authors Or Biton, Tomer Krichli, Itai Allouche, Joseph Keshet
Computation and Language · Cross-listed from cs.AI
Automated Construction of FAIR Digital Object Knowledge Graphs from Flat Cultural Heritage Records
Zeyd Boukhers, Lingxiao Kong, Xenophon Zabulis et al. (+1 more)
The FAIR Digital Object (FDO) framework mandates that metadata attribute values be expressed as persistent identifiers (PIDs) wherever possible, to produce a fully machine-actionable graph in which every reference is resolvable. The Europeana Data Model was designed long before the FDO specification, and it stores most metadata values as plain text. This serves human browsing well enough, but gives an automated
agent nothing to follow across records or collections. We present a pipeline that transforms flat Europeana records into an FDO-compliant knowledge graph structured with CIDOC-CRM. Following the FDO specification, we model every heritage entity as a discrete FDO with its own PID, type, profile, and metadata layer. The core technical challenge is automating the FDO-prescribed distinction between values that must become PID references (resolvable entities) and those that may remain literals (terminal leaves such as notes, measurements, and dates). We address this with a large
language model that classifies each metadata value, routes it to a controlled vocabulary (Getty AAT, Wikidata, VIAF, PeriodO), and links it to a shared entity FDO. We evaluate using 637 archaeological records from five Europeana providers, processing each with the LLM. The pipeline links 86% of metadata slots, resolving 58.5% of values Europeana had not already enriched. It also merges cross-lingual surface forms that byte-identical matching keeps apart, where 17 of 33 such merges are correct on manual review. Graph connectivity does not separate this from string matching; what distinguishes the FDO graph is that every node is typed and resolvable.
Read the full abstract ▾
All authors Zeyd Boukhers, Lingxiao Kong, Xenophon Zabulis, Georgios Toubekis
Computation and Language
A Scalable Cross-Domain Event Extraction System via a Unified Generative Training Framework
Siting Liang, Omar Adjali, Omair Shahzad Bhatti et al. (+1 more)
Event extraction is fundamental to information extraction. Prior approaches often separate event detection and argument extraction or depend on
dataset-specific designs, limiting scalability and cross-domain generalization. We propose a unified generative sequence-to-sequence framework that performs event extraction subtasks jointly and supports both pipeline and end-to-end configurations. We fine-tune pretrained
language models on multiple event
datasets across diverse domains, enabling a single model to retain domain-specific semantics while generalizing over large and evolving label spaces. We demonstrate these capabilities through a web-based application tailored for researchers and practitioners. The platform supports document upload, schema-aware event extraction, visualization of triggers and arguments, and comparison of different extraction configurations across domains.
Read the full abstract ▾
All authors Siting Liang, Omar Adjali, Omair Shahzad Bhatti, Daniel Sonntag
Computation and Language · Cross-listed from cs.LG
The Laws of Context Allocation: Causal Measurement and Closed-Loop Orchestration in Generative Search
Peiyang Liu, Xi Wang, Di Liang et al. (+1 more)
As
Retrieval-Augmented Generation (RAG) shifts toward diverse portfolio generation, it is stymied by two critical bottlenecks: flawed measurement of evidence utilization, and suboptimal context budget allocation. We resolve both sequentially. To resolve measurement, we expose a pervasive “diagnostic illusion”: standard relevance proxies fail catastrophically on hard negatives. We replace them with an efficient causal leave-one-out probe that accurately isolates generative reliance and formally calibrates the structural dilution of LLM
attention. To resolve allocation, we deploy this causal probe in a deconfounded factorial grid. We prove that the prevailing strategy of monolithic context widening is an architectural trap penalized by relevance decay. Instead, allocating compute iteratively across multiple sequential generations drives transformative portfolio recall gains of 16.7–20.5 absolute percentage points, scaling robustly up to 32B models. Finally, we unify these solutions into a deployable closed-loop submodular scheduler. Augmented by an attribution-steered contrastive decoder to override LLM
attention inertia, our architecture systematically forces fresh evidence integration. By dominating classical open-loop baselines, we establish sequential, feedback-driven orchestration as the definitive paradigm for generative search. Our code, data, and causal measurement instruments are available at https://github.com/PeiYangLiu/ascp.
Read the full abstract ▾
All authors Peiyang Liu, Xi Wang, Di Liang, Wei Ye
Computation and Language
Future Querying: Can LLMs Serve as Implicit Medical World Models?
Siri Willems, James Butterworth, Lore Goetschalckx et al. (+4 more)
Traditional clinical prediction models rely on task-specific pipelines and curated, structured data, which scale poorly and underutilize unstructured text. To address this, we introduce future querying, a paradigm that probes whether large
language models (LLMs) can function as implicit medical world models by evaluating their ability to answer time-indexed clinical queries about a patient's future. Our framework operates on unstructured clinical documentation using endpoint-agnostic training, enabling a single model to answer diverse clinical queries over patient trajectories without manual feature engineering or task-specific retraining. We show that small, locally fine-tuned open-weight models can match or approach larger proprietary systems, making the framework suitable for
privacy-preserving, on-premise deployment. Evaluated on a new synthetic medical reports
dataset and real ICU notes from the MIMIC-IV
dataset, our results provide encouraging evidence that LLMs can capture aspects of clinical dynamics.
Read the full abstract ▾
All authors Siri Willems, James Butterworth, Lore Goetschalckx, Peter Vrancx, Philippe Modard, Elke Giets, Ludovic Denoyer
Computation and Language
Credal Large Language Models for Semantic Commitment under Uncertainty
Shireen Kudukkil Manchingal, Sofiia Nikolenko and Fabio Cuzzolin
Large
language models (LLMs) often produce fluent but incorrect answers with unwarranted confidence. A central limitation is that standard LLMs represent uncertainty through a single predictive distribution, conflating epistemic ignorance with genuine ambiguity. We introduce Credal Large
Language Models (CLLMs): an ensemble of LoRA adapters induces a credal set whose lower and upper probabilities expose the spread of plausible predictive distributions rather than collapsing to a single softmax output. From this representation, we derive a single commitment rule: the model commits to an answer only when its lower probability exceeds the upper probability of every alternative, and otherwise returns the set of answers that no plausible predictor rules out. We apply this commitment rule at two depths: Credal
Token Commitment (CTC) applies it to answer
tokens from one ensemble forward pass, which decides constrained answers without any generation; for open-ended answers, credal decoding extends a partial answer only when no completed answer dominates it, so that the completions produced are those the plausible predictors license, and Credal Semantic Commitment (CSC) applies the rule to their meaning clusters. We evaluate CLLMs with Gemma-2-9B, Llama-3.1-8B and Qwen2.5-7B on OpenBookQA, CoQA, TriviaQA and ARC-Challenge. On multiple choice, CTC commits on 73-91% of questions at 89-98% accuracy, returns sets of 1.1-1.5 options containing the gold one on 89-98%, and its intervals contain the observed accuracy in 24 of 30 confidence bins without calibration; corrupted context lowers commitment from 87-92% to 65-71%, and on Gemma the credal bound detects corruption better than every baseline. On open-ended QA, CLLM outperforms semantic
entropy and Laplace-LoRA at a fixed coverage by up to 19% and 9.5% absolute accuracy on CoQA and TriviaQA with context, for every backbone.
Read the full abstract ▾
Computation and Language
A Multi-Domain and Multi-Task Generative Framework with Explicit Task and Domain Conditioning for Cross-Domain Event Extraction
Siting Liang, Omar Adjali and Daniel Sonntag
Event extraction aims to identify event triggers, classify event types, and extract arguments to construct structured event representations. Despite strong in-domain performance, developing models that generalize robustly across domains remains challenging due to variations in contextual expressions and event schemas. Prior unified and multi-task approaches improve in-domain accuracy but exhibit limited flexibility when applied to unseen domains. Even large
language model-based methods that provide full event ontologies at inference time often underperform compared to smaller, task-specific fine-tuned models. We propose a unified multi-domain and multi-task training framework that models heterogeneous event schemas within a single model. Our approach introduces domain conditioning signals, jointly with task-specific
prompts, enabling dynamic adaptation to
dataset-specific schemas without requiring complete event label sets at inference time. The framework supports both pipeline and end-to-end extraction settings, facilitating efficient task- and domain-level transfer. Experiments on diverse event extraction
benchmarks demonstrate that our method achieves competitive performance, strong cross-domain generalization, and practical scalability, while preserving domain-specific precision.
Read the full abstract ▾
Computation and Language
Aligning Biomedical Texts and Knowledge Graphs: A Systematic Comparison of Lightweight Alignment Strategies
Artem Bisliouk, Elizaveta Nosova, Heiko Paulheim et al. (+2 more)
Biomedical knowledge exists in two complementary but distinct forms: unstructured scientific literature and structured knowledge graphs (KGs). Aligning them is essential for knowledge grounding, evidence
retrieval, and KG completion, yet existing methods do not explicitly align free-text evidence with KG triples. We present a unified framework for systematically studying design choices for aligning biomedical text and KGs. With a text encoder and a KG
embedding model both frozen, we learn only a lightweight projection between their spaces via a contrastive objective. This enables a fair comparison across six design dimensions: text encoder, KG
embedding model, projection head, triple composition, training direction, and hard-negatives sampling. We construct CTD-Align, a corpus of over 22K one-to-one tripledocument pairs linking chemical-gene interactions from the Comparative Toxicogenomics Database to supporting PubMed passages. We evaluate
alignment on it in two
retrieval settings: document-to-triple and triple-to-document. We find that the triple composition and the training direction (i.e., shared
retrieval space) have the greatest impact, whereas the text encoder and hard-negatives sampling matter little. Overall, simple choices win: projecting text into the KG space with a linear head over concatenated subject, predicate, and object
embeddings performs best. These findings establish lightweight contrastive
alignment as an effective, practical foundation for bridging biomedical text and KGs.
Read the full abstract ▾
All authors Artem Bisliouk, Elizaveta Nosova, Heiko Paulheim, Andreea Iana, Rita T. Sousa
Computation and Language · Cross-listed from cs.AI
Cognitive Profiling of LRMs' Reasoning Traces Using Bloom's Taxonomy
Maria-Eleni Zoumpoulidi, Georgios Paraskevopoulos and Alexandros Potamianos
Large
Reasoning Models (LRMs) have revolutionized
reasoning in LLMs, and the increasing public availability of
reasoning traces creates valuable opportunities to study model behavior not only at the surface level but also at the granularity of individual
reasoning steps. However, understanding the types of thinking employed during
reasoning - which offers critical insights into models'
reasoning patterns and enables actionable applications - remains underexplored. To address this gap, we introduce a framework for automatic annotation of
reasoning steps through the lens of Bloom's Taxonomy, which classifies thinking into six cognitive levels, such as Remembering, Applying and Evaluating. Using this framework, we perform a large-scale analysis across models and
datasets, revealing both similarities and differences in thinking patterns across models and tasks. Moreover, we demonstrate that thinking-type information derived from
reasoning traces correlates with correctness, paving the way for improved
reasoning. Our findings establish a fine-grained framework for analyzing thinking patterns in LRMs and provide actionable insights for enhancing
reasoning quality.
Read the full abstract ▾
Computation and Language
LongWoF-Bench: Evaluating EvoMap Genes for Verifiable Long-Workflow Tasks
Xiao Zhang, Qumeng Sun, Jiahao Li et al. (+3 more)
Large
language models are increasingly expected to execute complex workflows whose success depends on maintaining interdependent constraints and producing artifacts that satisfy strict end-to-end verification. Yet successful execution experience is typically lost after a single run, forcing subsequent models to rediscover strategies and failure modes from scratch. We study whether such experience can instead be externalized and reused through EvoMap, where verifier-confirmed execution trajectories are consolidated into structured Gene. To evaluate this setting, we introduce the Long-Workflow
Benchmark (LongWoF-Bench), comprising 778 machine-verifiable tasks across code generation,
agent-environment synthesis, mathematical
reasoning, and rule following. On the 252 tasks with verifier-confirmed Opus trajectories, evolved EvoMap Gene outperform Skill across all seven evaluated models by 8.7-15.5 percentage points, with the gains extending to consumer models from different model families. In contrast, reference-distilled Gene do not exhibit the same advantage, indicating that compact representation alone is insufficient and that Gene utility is closely associated with verified experience provenance. For Claude Opus, Gene reuse also completes 39 more tasks than Skill while reducing solve-time
token consumption by 9.9%. Together, these results show that verified execution experience can be retained and shared as a reusable external resource, enabling models to improve long-workflow completion without repeatedly paying the full cost of experience discovery.
Read the full abstract ▾
All authors Xiao Zhang, Qumeng Sun, Jiahao Li, Xiang Liu, Bruno, Haoyang Zhang
Computation and Language · Cross-listed from cs.CR
CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild
Jian Yang, Haau-Sing Li, Shawn Guo et al. (+10 more)
As large
language models (LLMs) continue to advance in coding capabilities, their potential in cybersecurity has drawn increasing research
attention, with closed-source LLMs (e.g., Mythos) delivering advanced cybersecurity capabilities. However, existing open-source efforts remain limited: frontier open-weight models do not provide reproducible cybersecurity training solutions, open-source training solutions focus on isolated tasks and lack scalable agentic data, and scaling agentic rollouts requires strong domain priors. In this work, we introduce CyberFactory, a unified open-source framework that connects data construction, trajectory synthesis, and model training across proof-of-concept (PoC) generation, vulnerability patching, and cybersecurity question answering (CyberQA). CyberFactory transforms public vulnerability artifacts, including CVEs from the wild, into executable and verifiable task instances. It further uses a reusable vulnerability-analysis skill to guide the teacher through source inspection, problem solving with domain prior, and evidence-based validation. The resulting supervision is agentic: the model interacts with tools and target environments and revises its solutions according to execution feedback. Using these trajectories, we train and release \modelname\footnote{Aegis is, in Greek mythology, the protective shield of Zeus and Athena; the name reflects the model's defensive, security-oriented purpose.}, which internalizes the skill-guided procedure without requiring the skill at inference time. On CyberGym, \modelname reaches 52.4% Pass@1 under a one-hour budget, improving over its Qwen~3.5 base model by +22.8 points and outperforming the evaluated general-purpose backbones under the same scaffold.
Read the full abstract ▾
All authors Jian Yang, Haau-Sing Li, Shawn Guo, Zixi Zhao, Yibo Tan, Jiajun Wu, Aishan Liu, Zhoujun Li, Xianglong Liu, Tianyu Zheng, Bryan Dai, Chengran Yang, Weifeng Lv
Computation and Language
CaRGo-T: Causal Reasoning Graph-of-Thought improves Multimodal Humor Comprehension
Abhilash Nandy, Rahul Seetharaman, Aman Bansal et al. (+5 more)
Large-scale
vision-
language models (VLMs) have demonstrated remarkable versatility across a wide range of
multimodal tasks. However, understanding humor remains challenging because humorous content often depends on subtle interactions among entities, events, context, and implicit relationships across image and text modalities. These interactions can involve complex chains of
reasoning that are difficult to capture through conventional prompting or linear chain-of-thought
reasoning. In this work, we propose CaRGo-T (Causal
Reasoning Graph-of-Thought), a
reasoning framework that represents the causal and contextual relationships underlying
multimodal humor as a lightweight graph-based
reasoning structure. The graph is serialized into a code-based representation generated by a VLM, which can subsequently be interpreted by the same or a different VLM to produce the final prediction in zero-shot or in-context learning settings. We evaluate CaRGo-T on humor understanding and humor detection across four
datasets spanning diverse forms of comedic content, including satire, sarcasm, and memes. Experiments with state-of-the-art commercial and open-source VLMs show that CaRGo-T consistently improves performance over existing
reasoning-based baselines, achieving gains of approximately 1-20% on humor understanding and 1-3% on humor detection. Further analysis using mutual information indicates that the
reasoning representations produced by CaRGo-T contain more information relevant to the target output than those generated by baseline
reasoning approaches. Code is available at https://github.com/abhi1nandy2/CaRGo-T.
Read the full abstract ▾
All authors Abhilash Nandy, Rahul Seetharaman, Aman Bansal, Rounak Saha, Manav Nitin Kapadnis, Millon Madhur Das, Pawan Goyal, Niloy Ganguly
Computation and Language
Accelerating Diffusion Language Models via Structured Suffix Modeling
Zifeng Cheng, Keda Li, Zhiwei Jiang et al. (+3 more)
Diffusion Language Models (DLMs) exhibit strong parallel decoding capabilities by denoising multiple
tokens in a single generation step. However, this parallelism comes with substantial computational overhead, as each step requires interactions with all suffix
tokens. Existing methods typically reduce this cost by retaining only a local suffix window as a substitute for the full suffix. Despite their effectiveness, these methods overlook the structural heterogeneity across suffix regions and re-initialize suffix
tokens with identical representations at each timestep. To this end, we propose a structured suffix modeling method for efficient DLM inference. Specifically, we divide the suffix into three regions, i.e., the local, middle, and tail regions, and retain different numbers of suffix
tokens in each region according to their structural roles. Moreover, we incorporate the decoding results from the previous step into the suffix
token representations at the current step, allowing them to carry evolving denoising information across generation steps. Notably, our method is training-free and orthogonal to several existing acceleration techniques, such as parallel decoding strategies and KV cache. Empirical results across multiple
benchmarks on three DLMs demonstrate that our method can further accelerate DLM inference and improve performance in most cases. In particular, in long-sequence inference, our method achieves up to a \(72.81\times\) speedup when combined with other acceleration techniques. Our code is available at https://github.com/zifengcheng/SSM.
Read the full abstract ▾
All authors Zifeng Cheng, Keda Li, Zhiwei Jiang, Cong Wang, Fei Shen, Qing Gu
Computation and Language
Counter with Evidence! A Multi-Agent Memory Efficient Reasoning Framework for Hate Category Informed Counterspeech Generation
Sujoy Nath, Aswini Kumar and Tanmoy Chakraborty
Counterspeech effectively neutralizes the impact of online hate. Although prior work explores automated counterspeech generation, it largely emphasizes stylistic control while treating hate
speech as homogeneous, overlooking that distinct forms of abuse require fundamentally different counterspeech strategies. To address this gap, we introduce FIRE (Factuality Informed Multi-
Agent Reasoning Framework) that first decomposes hate
speech into one of the five distinct categories (misinformation, stereotype, conspiracy, dehumanizing, non-factual), and then maps it to a targeted counterspeech style. To facilitate FIRE, we curate FactualCS, a novel
dataset of $4,784$ instances that provides the annotations regarding hate categories,
reasoning traces, and evidence mappings, which are critical elements for grounded generation that are missing in prior work. A comprehensive evaluation across $28$ baseline configurations demonstrates that FIRE significantly surpasses existing methods, despite using compact
agents ($<$2B). FIRE achieves a $\sim$ $12 \%$ and $\sim$ $11 \%$ improvements in factual and category-specific accuracy respectively, while simultaneously reducing toxicity by $\sim$ $11 \%$ relative to the strongest baselines. Further human evaluation confirms that responses generated by FIRE are significantly preferred over the strongest baselines, underscoring its effectiveness for real-world deployment. These findings show that decomposing the underlying intent of hate
speech is essential for generating safe, effective, and contextually precise counterspeech.
Read the full abstract ▾
Computation and Language
Language Chain in Alignment: Cross-lingual Ranking Preference Optimization
Seungyoon Lee, Minhyuk Kim, Jungseob Lee et al. (+1 more)
The
alignment of Large
Language Models heavily relies on English-centric high-quality preference data, which often leads to suboptimal performance in other
languages. In this paper, we propose Cross-lingual Ranking Preference Optimization~(CRPO), a novel framework that leverages robust preference knowledge from English to facilitate preference
alignment in the target
language. We design a hierarchical structure within parallel preference pairs across the target
language and English to jointly optimize intra- and inter-lingual preferences, thereby enhancing
language adaptation and output quality. Building on the LambdaLoss framework, CRPO goes beyond the binary comparison based optimization by providing a relative ranking signal across multiple candidate responses. Our experiments across five
languages with varying resource scales demonstrate that CRPO consistently outperforms standard approaches in both instruction-following and knowledge utilization capability. Notably, the robust performance gains observed across various weighting schemes further validate the empirical effectiveness of our hierarchical design in a
multilingual setup. Furthermore, our findings highlight that CRPO significantly improves both reward margins and the log-probability of desirable responses, contributing to a more stable preference
manifold for cross-lingual
alignment. Our code is available at https://github.com/dltmddbs100/CRPO.
Read the full abstract ▾
All authors Seungyoon Lee, Minhyuk Kim, Jungseob Lee, Heuiseok Lim
Computation and Language · Cross-listed from cs.LG
Activation-Weighted Seeded Residual Coding for Low-Bit LLM Weight Repair
Zehao Liu, Chuangchuang Fang and Yang Ren
Low-bit weight quantization saves storage but leaves errors that degrade LLM quality. We introduce activation-weighted seeded residual coding (AWSRC), a compact repair codec for an existing quantization backbone. Given a reconstructed weight $W_0$, AWSRC encodes the residual $W-W_0$ using deterministic seed-generated bases. The sidecar stores seed selectors, low-bit coefficients, and scales rather than an explicit codebook. Two variants combine activation weighting with per-module byte quotas ($\mathrm{AWSRC\text{-}U}$), or blended activation/Fisher weighting with globally ranked progressive prefixes ($\mathrm{AWSRC\text{-}P}_{F}$) that support multiple byte budgets without refitting. On Qwen2.5-3B-Instruct, adding $0.162$ scope-bits/weight to an RTN-INT4 baseline closes $88.2\%$, $78.9\%$, and $71.3\%$ of the PPL, KL, and 11-task mean-accuracy gaps to BF16, respectively. AWSRC achieves the highest mean downstream accuracy in byte-matched residual-codec ablations and improves all metrics across model families with up to 32B parameters.
Read the full abstract ▾
Computation and Language
LITERARYBIGFIVE: Author-Personalized Text Generation in a Unified Interpretable Space
Jinghui Zhang, Lang Gao, Ao Li et al. (+5 more)
Personalized text generation for authors and literary writing is essential for applications such as adaptive writing assistants, creative support tools, and computational literary analysis. However, existing approaches to author modeling and personalization often represent writing behavior as independent labels, requiring large-scale corpus collection or fine-tuning for each author or stylistic category. Such formulations are costly, difficult to interpret, and poorly suited for generalizing across authors. Inspired by the Big Five model's dimensional view of personality, we propose LiteraryBigFive, a framework that reframes authorial writing characteristics as coordinates within a unified and interpretable space. In this space, we derive each interpretable axis (e.g., Classicism, Emotionality) from activation-space contrasts between author-written and neutral passages, yielding distinct stylistic dimensions that allow texts or authors to be positioned within a five-dimensional system. Beyond localizing different authors, we further introduce an interpretable steering mechanism, which adaptively guides text generation toward target coordinates to perform author-personalized writing. Experimental results show that LiteraryBigFive improves authorial expressiveness while preserving semantic fidelity. The derived author per-axis scores strongly correlate with real-world literary consensus, offering transparent and interpretable explanations of author-specific generation behavior: https://github.com/Znull-1220/LiteraryBigFive.
Read the full abstract ▾
All authors Jinghui Zhang, Lang Gao, Ao Li, Mingzhe Li, Ruihong Zeng, Zirui Song, Kentaro Inui, Xiuying Chen