Peer Revenue Impact factor: volatile

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Computation and Language

cs.CL Watch Computation and Language

Monday 17 November

Computation and Language

Hierarchical Retrieval with Out-Of-Vocabulary Queries: A Case Study on SNOMED CT

Jonathon Dilworth, Hui Yang, Jiaoyan Chen et al. (+2 more)

SNOMED CT is a biomedical ontology with a hierarchical representation, modelling terminological concepts at a large scale. Knowledge retrieval in SNOMED CT is critical for its application but often proves challenging due to linguistic ambiguity, synonymy, polysemy, and so on. This problem is exacerbated when the queries are out-of-vocabulary (OOV), i.e., lacking any equivalent matches in the ontology. In this work, we focus on the problem of hierarchical concept retrieval from SNOMED CT with OOV queries, and propose an approach driven by utilising language model-based ontology embeddings, which represent hierarchical concepts in a hyperbolic space for enabling efficient subsumption inference between a textual query and an arbitrary concept. For evaluation, we construct three datasets where OOV queries are annotated against SNOMED CT concepts, testing the retrieval of the most specific subsumers and their less relevant ancestors. We find that our method outperforms the baselines, including SBERT, SapBERT, and two lexical matching methods. While evaluated against SNOMED CT, the approach is generalisable and can be extended to other ontologies. We release all the experiment codes and datasets at https://github.com/jonathondilworth/HR-OOV-SNOMED-CT.
Read the full abstract

All authors Jonathon Dilworth, Hui Yang, Jiaoyan Chen, Yongsheng Gao, Ernesto Jimenez-Ruiz

Computation and Language

Hint-Augmented Re-ranking: Efficient Product Search using LLM-Based Query Decomposition

Yilun Zhu, Nikhita Vedula and Shervin Malmasi

Search queries with superlatives (e.g., best, most popular) require comparing candidates across multiple dimensions, demanding linguistic understanding and domain knowledge. We show that LLMs can uncover latent intent behind these expressions in e-commerce queries through a framework that extracts structured interpretations or hints. Our approach decomposes queries into attribute-value hints generated concurrently with retrieval, enabling efficient integration into the ranking pipeline. Our method improves search performanc eby 10.9 points in MAP and ranking by 5.9 points in MRR over baselines. Since direct LLM-based reranking faces prohibitive latency, we develop an efficient approach transferring superlative interpretations to lightweight models. Our findings provide insights into how superlative semantics can be represented and transferred between models, advancing linguistic interpretation in retrieval systems while addressing practical deployment constraints.
Read the full abstract

Computation and Language · Cross-listed from cs.SE

Show and Tell: Prompt Strategies for Style Control in Multi-Turn LLM Code Generation

Jeremiah Bohr

Language models generate functionally correct code that tends toward excessive verbosity, with elaborate documentation and defensive patterns that diverge from human baselines. Two prompting mechanisms have emerged for stylistic control: instruction based prompts that articulate abstract directives, and example based prompts that provide concrete code demonstrations. The core problem is whether stylistic constraints persist when models enhance initial implementations with additional features while maintaining high functional accuracy. Here we show that instruction-based, example-based, and combined prompts produce distinct patterns of initial control and expansion discipline over one enhancement turn. We manipulated system prompts across four conditions in a paired two-turn protocol where models first generated solutions to an intermediate Python task, then revised their code under general improvement directives, holding the user task fixed (N = 160 paired programs). Combined prompts produced the strongest initial compression and greatest expansion discipline. Instructions showed large initial effects and moderate expansion discipline. Examples showed modest initial effects with no expansion discipline. These results show that initial prompt effectiveness and expansion discipline are separate aspects of prompt design, and that combined approaches provide the most stable stylistic control in this two-turn workflow.
Read the full abstract

Computation and Language · Cross-listed from cs.CV

EchoAgent: Guideline-Centric Reasoning Agent for Echocardiography Measurement and Interpretation

Matin Daghyani, Lyuyang Wang, Nima Hashemi et al. (+8 more)

Purpose: Echocardiographic interpretation requires video-level reasoning and guideline-based measurement analysis, which current deep learning models for cardiac ultrasound do not support. We present EchoAgent, a framework that enables structured, interpretable automation for this domain. Methods: EchoAgent orchestrates specialized vision tools under Large Language Model (LLM) control to perform temporal localization, spatial measurement, and clinical interpretation. A key contribution is a measurement-feasibility prediction model that determines whether anatomical structures are reliably measurable in each frame, enabling autonomous tool selection. We curated a benchmark of diverse, clinically validated video-query pairs for evaluation. Results: EchoAgent achieves accurate, interpretable results despite added complexity of spatiotemporal video analysis. Outputs are grounded in visual evidence and clinical guidelines, supporting transparency and traceability. Conclusion: This work demonstrates the feasibility of agentic, guideline-aligned reasoning for echocardiographic video analysis, enabled by task-specific tools and full video-level automation. EchoAgent sets a new direction for trustworthy AI in cardiac ultrasound.
Read the full abstract

All authors Matin Daghyani, Lyuyang Wang, Nima Hashemi, Bassant Medhat, Baraa Abdelsamad, Eros Rojas Velez, XiaoXiao Li, Michael Y. C. Tsang, Christina Luong, Teresa S.M. Tsang, Purang Abolmaesumi

Computation and Language

What Works for 'Lost-in-the-Middle' in LLMs? A Study on GM-Extract and Mitigations

Mihir Gupte, Eshan Dixit, Muhammad Tayyab et al. (+1 more)

The diminishing ability of large language models (LLMs) to effectively utilize long-range context-the "lost-in-the-middle" phenomenon-poses a significant challenge in retrieval-based LLM applications. To study the impact of this phenomenon in a real-world application setting, we introduce GM-Extract, a novel benchmark dataset meticulously designed to evaluate LLM performance on retrieval of control variables. To accurately diagnose failure modes, we propose a simple yet elegant evaluation system using two distinct metrics: one for spatial retrieval capability (Document Metric) and the other for semantic retrieval capability (Variable Extraction Metric). We conduct a systematic evaluation of 7-8B parameter models on two multi-document tasks (key-value extraction and question-answering), demonstrating a significant change in retrieval performance simply by altering how the data is represented in the context window. While a distinct U-shaped curve was not consistently observed, our analysis reveals a clear pattern of performance across models, which we further correlate with perplexity scores. Furthermore, we perform a literature survey of mitigation methods, which we categorize into two distinct approaches: black-box and white-box methods. We then apply these techniques to our benchmark, finding that their efficacy is highly nuanced. Our evaluation highlights scenarios where these strategies successfully improve performance, as well as surprising cases where they lead to a negative impact, providing a comprehensive understanding of their utility in a practical context.
Read the full abstract

All authors Mihir Gupte, Eshan Dixit, Muhammad Tayyab, Arun Adiththan

Computation and Language

Can QE-informed (Re)Translation lead to Error Correction?

Govardhan Padmanabhan

The paper presents two approaches submitted to the WMT 2025 Automated Translation Quality Evaluation Systems Task 3 - Quality Estimation (QE)-informed Segment-level Error Correction. While jointly training QE systems with Automatic Post-Editing (APE) has shown improved performance for both tasks, APE systems are still known to overcorrect the output of Machine Translation (MT), leading to a degradation in performance. We investigate a simple training-free approach - QE-informed Retranslation, and compare it with another within the same training-free paradigm. Our winning approach selects the highest-quality translation from multiple candidates generated by different LLMs. The second approach, more akin to APE, instructs an LLM to replace error substrings as specified in the provided QE explanation(s). A conditional heuristic was employed to minimise the number of edits, with the aim of maximising the Gain-to-Edit ratio. The two proposed approaches achieved a Delta COMET score of 0.0201 and -0.0108, respectively, leading the first approach to achieve the winning position on the subtask leaderboard.
Read the full abstract

Computation and Language · Cross-listed from cs.AI

When AI Does Science: Evaluating the Autonomous AI Scientist KOSMOS in Radiation Biology

Humza Nusrat and Omar Nusrat

Agentic AI "scientists" now use language models to search the literature, run analyses, and generate hypotheses. We evaluate KOSMOS, an autonomous AI scientist, on three problems in radiation biology using simple random-gene null benchmarks. Hypothesis 1: baseline DNA damage response (DDR) capacity across cell lines predicts the p53 transcriptional response after irradiation (GSE30240). Hypothesis 2: baseline expression of OGT and CDO1 predicts the strength of repressed and induced radiation-response modules in breast cancer cells (GSE59732). Hypothesis 3: a 12-gene expression signature predicts biochemical recurrence-free survival after prostate radiotherapy plus androgen deprivation therapy (GSE116918). The DDR-p53 hypothesis was not supported: DDR score and p53 response were weakly negatively correlated (Spearman rho = -0.40, p = 0.76), indistinguishable from random five-gene scores. OGT showed only a weak association (r = 0.23, p = 0.34), whereas CDO1 was a clear outlier (r = 0.70, empirical p = 0.0039). The 12-gene signature achieved a concordance index of 0.61 (p = 0.017) but a non-unique effect size. Overall, KOSMOS produced one well-supported discovery, one plausible but uncertain result, and one false hypothesis, illustrating that AI scientists can generate useful ideas but require rigorous auditing against appropriate null models.
Read the full abstract

Computation and Language · Cross-listed from cs.DL

Rdgai: Classifying transcriptional changes using Large Language Models with a test case from an Arabic Gospel tradition

Robert Turnbull

Application of phylogenetic methods to textual traditions has traditionally treated all changes as equivalent even though it is widely recognized that certain types of variants were more likely to be introduced than others. While it is possible to give weights to certain changes using a maximum parsimony evaluation criterion, it is difficult to state a priori what these weights should be. Probabilistic methods, such as Bayesian phylogenetics, allow users to create categories of changes, and the transition rates for each category can be estimated as part of the analysis. This classification of types of changes in readings also allows for inspecting the probability of these categories across each branch in the resulting trees. However, classification of readings is time-consuming, as it requires categorizing each reading against every other reading at each variation unit, presenting a significant barrier to entry for this kind of analysis. This paper presents Rdgai, a software package that automates this classification task using multi-lingual large language models (LLMs). The tool allows users to easily manually classify changes in readings and then it uses these annotations in the prompt for an LLM to automatically classify the remaining reading transitions. These classifications are stored in TEI XML and ready for downstream phylogenetic analysis. This paper demonstrates the application with data an Arabic translation of the Gospels.
Read the full abstract

Computation and Language

Generalist Foundation Models Are Not Clinical Enough for Hospital Operations

Lavender Y. Jiang, Angelica Chen, Xu Han et al. (+16 more)

Hospitals and healthcare systems rely on operational decisions that determine patient flow, cost, and quality of care. Despite strong performance on medical knowledge and conversational benchmarks, foundation models trained on general text may lack the specialized knowledge required for these operational decisions. We introduce Lang1, a family of models (100M-7B parameters) pretrained on a specialized corpus blending 80B clinical tokens from NYU Langone Health's EHRs and 627B tokens from the internet. To rigorously evaluate Lang1 in real-world settings, we developed the REalistic Medical Evaluation (ReMedE), a benchmark derived from 668,331 EHR notes that evaluates five critical tasks: 30-day readmission prediction, 30-day mortality prediction, length of stay, comorbidity coding, and predicting insurance claims denial. In zero-shot settings, both general-purpose and specialized models underperform on four of five tasks (36.6%-71.7% AUROC), with mortality prediction being an exception. After finetuning, Lang1-1B outperforms finetuned generalist models up to 70x larger and zero-shot models up to 671x larger, improving AUROC by 3.64%-6.75% and 1.66%-23.66% respectively. We also observed cross-task scaling with joint finetuning on multiple tasks leading to improvement on other tasks. Lang1-1B effectively transfers to out-of-distribution settings, including other clinical tasks and an external health system. Our findings suggest that predictive capabilities for hospital operations require explicit supervised finetuning, and that this finetuning process is made more efficient by in-domain pretraining on EHR. Our findings support the emerging view that specialized LLMs can compete with generalist models in specialized tasks, and show that effective healthcare systems AI requires the combination of in-domain pretraining, supervised finetuning, and real-world evaluation beyond proxy benchmarks.
Read the full abstract

All authors Lavender Y. Jiang, Angelica Chen, Xu Han, Xujin Chris Liu, Radhika Dua, Kevin Eaton, Frederick Wolff, Robert Steele, Jeff Zhang, Anton Alyakin, Qingkai Pan, Yanbing Chen, Karl L. Sangwon, Daniel A. Alber, Jaden Stryker, Jin Vivian Lee, Yindalon Aphinyanaphongs, Kyunghyun Cho, Eric Karl Oermann

Computation and Language

Crossing Borders: A Multimodal Challenge for Indian Poetry Translation and Image Generation

Sofia Jamil, Kotla Sai Charan, Sriparna Saha et al. (+2 more)

Indian poetry, known for its linguistic complexity and deep cultural resonance, has a rich and varied heritage spanning thousands of years. However, its layered meanings, cultural allusions, and sophisticated grammatical constructions often pose challenges for comprehension, especially for non-native speakers or readers unfamiliar with its context and language. Despite its cultural significance, existing works on poetry have largely overlooked Indian language poems. In this paper, we propose the Translation and Image Generation (TAI) framework, leveraging Large Language Models (LLMs) and Latent Diffusion Models through appropriate prompt tuning. Our framework supports the United Nations Sustainable Development Goals of Quality Education (SDG 4) and Reduced Inequalities (SDG 10) by enhancing the accessibility of culturally rich Indian-language poetry to a global audience. It includes (1) a translation module that uses an Odds Ratio Preference Alignment Algorithm to accurately translate morphologically rich poetry into English, and (2) an image generation module that employs a semantic graph to capture tokens, dependencies, and semantic relationships between metaphors and their meanings, to create visually meaningful representations of Indian poems. Our comprehensive experimental evaluation, including both human and quantitative assessments, demonstrates the superiority of TAI Diffusion in poem image generation tasks, outperforming strong baselines. To further address the scarcity of resources for Indian-language poetry, we introduce the Morphologically Rich Indian Language Poems MorphoVerse Dataset, comprising 1,570 poems across 21 low-resource Indian languages. By addressing the gap in poetry translation and visual comprehension, this work aims to broaden accessibility and enrich the reader's experience.
Read the full abstract

All authors Sofia Jamil, Kotla Sai Charan, Sriparna Saha, Koustava Goswami, Joseph K J

Computation and Language

Why is "Chicago" Predictive of Deceptive Reviews? Using LLMs to Discover Language Phenomena from Lexical Cues

Jiaming Qu, Mengtian Guo and Yue Wang

Deceptive reviews mislead consumers, harm businesses, and undermine trust in online marketplaces. Machine learning classifiers can learn from large amounts of data to distinguish deceptive reviews from genuine ones. However, the distinguishing features learned by these classifiers are often subtle, fragmented, and difficult for humans to interpret, which can hinder user understanding and trust. In this work, we study whether large language models (LLMs) can translate such unintuitive lexical cues into human-understandable language phenomena. We propose a conjecture-then-validate framework, and show that language phenomena obtained in this manner are empirically grounded in data, generalizable across similar domains, and more predictive than phenomena derived from LLMs' prior knowledge or in-context learning. Such phenomena can aid people in critically assessing the credibility of online reviews in environments where deception detection classifiers are unavailable.
Read the full abstract

Computation and Language · Cross-listed from cs.SE

Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?

Chunqiu Steven Xia, Zhe Wang, Yan Yang et al. (+2 more)

Large Language Models (LLMs) are reshaping almost all industries, including software engineering. In recent years, a number of LLM agents have been proposed to solve real-world software problems. Such software agents are typically equipped with a suite of coding tools and can autonomously decide the next actions to form complete trajectories to solve end-to-end software tasks. While promising, they typically require dedicated design and may still be suboptimal, since it can be extremely challenging and costly to exhaust the entire agent scaffold design space. Recognizing that software agents are inherently software themselves that can be further refined/modified, researchers have proposed a number of self-improving software agents recently, including the Darwin-Gödel Machine (DGM). Meanwhile, such self-improving agents require costly offline training on specific benchmarks and may not generalize well across different LLMs or benchmarks. In this paper, we propose Live-SWE-agent, the first live software agent that can autonomously and continuously evolve itself on-the-fly during runtime when solving real-world software problems. More specifically, Live-SWE-agent starts with the most basic agent scaffold with only access to bash tools (e.g., mini-SWE-agent), and autonomously evolves its own scaffold implementation while solving real-world software problems. Our evaluation on the widely studied SWE-bench Verified benchmark shows that LIVE-SWE-AGENT can achieve an impressive solve rate of 77.4% without test-time scaling, outperforming all existing software agents, including the best proprietary solution. Moreover, Live-SWE-agent outperforms state-of-the-art manually crafted software agents on the recent SWE-Bench Pro benchmark, achieving the best-known solve rate of 45.8%.
Read the full abstract

All authors Chunqiu Steven Xia, Zhe Wang, Yan Yang, Yuxiang Wei, Lingming Zhang

Computation and Language · Cross-listed from cs.LG

P1: Mastering Physics Olympiads with Reinforcement Learning

Jiacheng Chen, Qianjia Cheng, Fangchen Yu et al. (+25 more)

Recent progress in large language models (LLMs) has moved the frontier from puzzle-solving to science-grade reasoning-the kind needed to tackle problems whose answers must stand against nature, not merely fit a rubric. Physics is the sharpest test of this shift, which binds symbols to reality in a fundamental way, serving as the cornerstone of most modern technologies. In this work, we manage to advance physics research by developing large language models with exceptional physics reasoning capabilities, especially excel at solving Olympiad-level physics problems. We introduce P1, a family of open-source physics reasoning models trained entirely through reinforcement learning (RL). Among them, P1-235B-A22B is the first open-source model with Gold-medal performance at the latest International Physics Olympiad (IPhO 2025), and wins 12 gold medals out of 13 international/regional physics competitions in 2024/2025. P1-30B-A3B also surpasses almost all other open-source models on IPhO 2025, getting a silver medal. Further equipped with an agentic framework PhysicsMinions, P1-235B-A22B+PhysicsMinions achieves overall No.1 on IPhO 2025, and obtains the highest average score over the 13 physics competitions. Besides physics, P1 models also present great performance on other reasoning tasks like math and coding, showing the great generalibility of P1 series.
Read the full abstract

All authors Jiacheng Chen, Qianjia Cheng, Fangchen Yu, Haiyuan Wan, Yuchen Zhang, Shenghe Zheng, Junchi Yao, Qingyang Zhang, Haonan He, Yun Luo, Yufeng Zhao, Futing Wang, Li Sheng, Chengxing Xie, Yuxin Zuo, Yizhuo Li, Wenxauan Zeng, Yulun Wu, Rui Huang, Dongzhan Zhou, Kai Chen, Yu Qiao, Lei Bai, Yu Cheng, Ning Ding, Bowen Zhou, Peng Ye, Ganqu Cui

Computation and Language

O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agents

Piaohong Wang, Motong Tian, Jiaxian Li et al. (+8 more)

Recent advancements in LLM-powered agents have demonstrated significant potential in generating human-like responses; however, they continue to face challenges in maintaining long-term interactions within complex environments, primarily due to limitations in contextual consistency and dynamic personalization. Existing memory systems often depend on semantic grouping prior to retrieval, which can overlook semantically irrelevant yet critical user information and introduce retrieval noise. In this report, we propose the initial design of O-Mem, a novel memory framework based on active user profiling that dynamically extracts and updates user characteristics and event records from their proactive interactions with agents. O-Mem supports hierarchical retrieval of persona attributes and topic-related context, enabling more adaptive and coherent personalized responses. O-Mem achieves 51.67% on the public LoCoMo benchmark, a nearly 3% improvement upon LangMem,the previous state-of-the-art, and it achieves 62.99% on PERSONAMEM, a 3.5% improvement upon A-Mem,the previous state-of-the-art. O-Mem also boosts token and interaction response time efficiency compared to previous memory frameworks. Our work opens up promising directions for developing efficient and human-like personalized AI assistants in the future.
Read the full abstract

All authors Piaohong Wang, Motong Tian, Jiaxian Li, Yuan Liang, Yuqing Wang, Qianben Chen, Tiannan Wang, Zhicong Lu, Jiawei Ma, Yuchen Eleanor Jiang, Wangchunshu Zhou

Computation and Language

Beyond SELECT: A Comprehensive Taxonomy-Guided Benchmark for Real-World Text-to-SQL Translation

Hao Wang, Yuanfeng Song, Xiaoming Yin et al. (+1 more)

Text-to-SQL datasets are essential for training and evaluating text-to-SQL models, but existing datasets often suffer from limited coverage and fail to capture the diversity of real-world applications. To address this, we propose a novel taxonomy for text-to-SQL classification based on dimensions including core intents, statement types, syntax structures, and key actions. Using this taxonomy, we evaluate widely used public text-to-SQL datasets (e.g., Spider and Bird) and reveal limitations in their coverage and diversity. We then introduce a taxonomy-guided dataset synthesis pipeline, yielding a new dataset named SQL-Synth. This approach combines the taxonomy with Large Language Models (LLMs) to ensure the dataset reflects the breadth and complexity of real-world text-to-SQL applications. Extensive analysis and experimental results validate the effectiveness of our taxonomy, as SQL-Synth exhibits greater diversity and coverage compared to existing benchmarks. Moreover, we uncover that existing LLMs typically fall short in adequately capturing the full range of scenarios, resulting in limited performance on SQL-Synth. However, fine-tuning can substantially improve their performance in these scenarios. The proposed taxonomy has significant potential impact, as it not only enables comprehensive analysis of datasets and the performance of different LLMs, but also guides the construction of training data for LLMs.
Read the full abstract

All authors Hao Wang, Yuanfeng Song, Xiaoming Yin, Xing Chen

Computation and Language · Cross-listed from cs.CR

ForgeDAN: An Evolutionary Framework for Jailbreaking Aligned Large Language Models

Siyang Cheng, Gaotian Liu, Rui Mei et al. (+7 more)

The rapid adoption of large language models (LLMs) has brought both transformative applications and new security risks, including jailbreak attacks that bypass alignment safeguards to elicit harmful outputs. Existing automated jailbreak generation approaches e.g. AutoDAN, suffer from limited mutation diversity, shallow fitness evaluation, and fragile keyword-based detection. To address these limitations, we propose ForgeDAN, a novel evolutionary framework for generating semantically coherent and highly effective adversarial prompts against aligned LLMs. First, ForgeDAN introduces multi-strategy textual perturbations across character, word, and sentence-level operations to enhance attack diversity; then we employ interpretable semantic fitness evaluation based on a text similarity model to guide the evolutionary process toward semantically relevant and harmful outputs; finally, ForgeDAN integrates dual-dimensional jailbreak judgment, leveraging an LLM-based classifier to jointly assess model compliance and output harmfulness, thereby reducing false positives and improving detection effectiveness. Our evaluation demonstrates ForgeDAN achieves high jailbreaking success rates while maintaining naturalness and stealth, outperforming existing SOTA solutions.
Read the full abstract

All authors Siyang Cheng, Gaotian Liu, Rui Mei, Yilin Wang, Kejia Zhang, Kaishuo Wei, Yuqi Yu, Weiping Wen, Xiaojie Wu, Junhua Liu

Computation and Language

Toward Conversational Hungarian Speech Recognition: Introducing the BEA-Large and BEA-Dialogue Datasets

Máté Gedeon, Piroska Zsófia Barta, Péter Mihajlik et al. (+3 more)

The advancement of automatic speech recognition (ASR) has been largely enhanced by extensive datasets in high-resource languages, while languages such as Hungarian remain underrepresented due to limited spontaneous and conversational corpora. To address this gap, we introduce two new datasets – BEA-Large and BEA-Dialogue – constructed from the previously unprocessed portions of the Hungarian speech corpus named BEA. BEA-Large extends BEA-Base with 255 hours of spontaneous speech from 433 speakers, enriched with detailed segment-level metadata. BEA-Dialogue, comprising 85 hours of spontaneous conversations, is a Hungarian speech corpus featuring natural dialogues partitioned into speaker-independent subsets, supporting research in conversational ASR and speaker diarization. We establish reproducible baselines on these datasets using publicly available ASR models, with the fine-tuned Fast Conformer model achieving word error rates as low as 14.18% on spontaneous and 4.8% on repeated speech. Diarization experiments yield diarization error rates between 12.46% and 17.40%, providing reference points for future improvements. The results highlight the persistent difficulty of conversational ASR, particularly due to disfluencies, overlaps, and informal speech patterns. By releasing these datasets and baselines, we aim to advance Hungarian speech technology and offer a methodological framework for developing spontaneous and conversational benchmarks in other languages.
Read the full abstract

All authors Máté Gedeon, Piroska Zsófia Barta, Péter Mihajlik, Tekla Etelka Gráczi, Anna Kohári, Katalin Mády

Computation and Language

Applying Large Language Models to Characterize Public Narratives

Elinor Poole-Dayan, Daniel T Kessler, Hannah Chiou et al. (+4 more)

Public Narratives (PNs) are key tools for leadership development and civic mobilization, yet their systematic analysis remains challenging due to their subjective interpretation and the high cost of expert annotation. In this work, we propose a novel computational framework that leverages large language models (LLMs) to automate the qualitative annotation of public narratives. Using a codebook we co-developed with subject-matter experts, we evaluate LLM performance against that of expert annotators. Our work reveals that LLMs can achieve near-human-expert performance, achieving an average F1 score of 0.80 across 8 narratives and 14 codes. We then extend our analysis to empirically explore how PN framework elements manifest across a larger dataset of 22 stories. Lastly, we extrapolate our analysis to a set of political speeches, establishing a novel lens in which to analyze political rhetoric in civic spaces. This study demonstrates the potential of LLM-assisted annotation for scalable narrative analysis and highlights key limitations and directions for future research in computational civic storytelling.
Read the full abstract

All authors Elinor Poole-Dayan, Daniel T Kessler, Hannah Chiou, Margaret Hughes, Emily S Lin, Marshall Ganz, Deb Roy

Computation and Language

Aspect-Level Obfuscated Sentiment in Thai Financial Disclosures and Its Impact on Abnormal Returns

Attapol T. Rutherford, Sirisak Chueykamhang, Thachaparn Bunditlurdruk et al. (+1 more)

Understanding sentiment in financial documents is crucial for gaining insights into market behavior. These reports often contain obfuscated language designed to present a positive or neutral outlook, even when underlying conditions may be less favorable. This paper presents a novel approach using Aspect-Based Sentiment Analysis (ABSA) to decode obfuscated sentiment in Thai financial annual reports. We develop specific guidelines for annotating obfuscated sentiment in these texts and annotate more than one hundred financial reports. We then benchmark various text classification models on this annotated dataset, demonstrating strong performance in sentiment classification. Additionally, we conduct an event study to evaluate the real-world implications of our sentiment analysis on stock prices. Our results suggest that market reactions are selectively influenced by specific aspects within the reports. Our findings underscore the complexity of sentiment analysis in financial texts and highlight the importance of addressing obfuscated language to accurately assess market sentiment.
Read the full abstract

All authors Attapol T. Rutherford, Sirisak Chueykamhang, Thachaparn Bunditlurdruk, Nanthicha Angsuwichitkul

Computation and Language

Non-Linear Scoring Model for Translation Quality Evaluation

Serge Gladkoff, Lifeng Han and Katerina Gasova

Analytic Translation Quality Evaluation (TQE), based on Multidimensional Quality Metrics (MQM), traditionally uses a linear error-to-penalty scale calibrated to a reference sample of 1000-2000 words. However, linear extrapolation biases judgment on samples of different sizes, over-penalizing short samples and under-penalizing long ones, producing misalignment with expert intuition. Building on the Multi-Range framework, this paper presents a calibrated, non-linear scoring model that better reflects how human content consumers perceive translation quality across samples of varying length. Empirical data from three large-scale enterprise environments shows that acceptable error counts grow logarithmically, not linearly, with sample size. Psychophysical and cognitive evidence, including the Weber-Fechner law and Cognitive Load Theory, supports this premise by explaining why the perceptual impact of additional errors diminishes while the cognitive burden grows with scale. We propose a two-parameter model E(x) = a * ln(1 + b * x), a, b > 0, anchored to a reference tolerance and calibrated from two tolerance points using a one-dimensional root-finding step. The model yields an explicit interval within which the linear approximation stays within +/-20 percent relative error and integrates into existing evaluation workflows with only a dynamic tolerance function added. The approach improves interpretability, fairness, and inter-rater reliability across both human and AI-generated translations. By operationalizing a perceptually valid scoring paradigm, it advances translation quality evaluation toward more accurate and scalable assessment. The model also provides a stronger basis for AI-based document-level evaluation aligned with human judgment. Implementation considerations for CAT/LQA systems and implications for human and AI-generated text evaluation are discussed.
Read the full abstract

Computation and Language · Cross-listed from cs.IR

Exploring Multi-Table Retrieval Through Iterative Search

Allaa Boutaleb, Bernd Amann, Rafael Angarita et al. (+1 more)

Open-domain question answering over datalakes requires retrieving and composing information from multiple tables, a challenging subtask that demands semantic relevance and structural coherence (e.g., joinability). While exact optimization methods like Mixed-Integer Programming (MIP) can ensure coherence, their computational complexity is often prohibitive. Conversely, simpler greedy heuristics that optimize for query coverage alone often fail to find these coherent, joinable sets. This paper frames multi-table retrieval as an iterative search process, arguing this approach offers advantages in scalability, interpretability, and flexibility. We propose a general framework and a concrete instantiation: a fast, effective Greedy Join-Aware Retrieval algorithm that holistically balances relevance, coverage, and joinability. Experiments across 5 NL2SQL benchmarks demonstrate that our iterative method achieves competitive retrieval performance compared to the MIP-based approach while being 4-400x faster depending on the benchmark and search space settings. This work highlights the potential of iterative heuristics for practical, scalable, and composition-aware retrieval.
Read the full abstract

All authors Allaa Boutaleb, Bernd Amann, Rafael Angarita, Hubert Naacke

Computation and Language · Cross-listed from cs.IR

Attention Grounded Enhancement for Visual Document Retrieval

Wanqing Cui, Wei Huang, Yazhi Guo et al. (+4 more)

Visual document retrieval requires understanding heterogeneous and multi-modal content to satisfy implicit information needs. Recent advances use screenshot-based document encoding with fine-grained late interaction to encode holistic information and capture nuanced alignments, significantly improving retrieval performance. However, retrievers are still trained with coarse global relevance labels, without revealing which regions support the match. As a result, retrievers tend to rely on surface-level cues and struggle to capture implicit semantic connections, hindering their ability to handle non-extractive queries.To improve fine-grained relevance modeling, we propose a Attention-Grounded REtriever Enhancement (AGREE) framework. AGREE leverages cross-modal attention from multimodal large language models (MLLMs) as proxy supervision to guide the retriever in identifying relevant document regions. Specifically, AGREE extracts attention maps from the MLLM that highlight which document regions are attended to based on the query. These attention scores serve as local, region-level relevance signals. During training, AGREE combines local signals with the global document-level relevance label to jointly optimize the retriever. This dual-level supervision enables the model to learn not only whether documents match, but also which content drives relevance. Experiments on the challenging visual document retrieval benchmark, ViDoRe V2, show that AGREE significantly outperforms the global-supervision-only baseline by 12.82% and 5.03% in terms of average nDCG@1 and nDCG@5. Quantitative and qualitative analyses further demonstrate that AGREE promotes deeper alignment between query terms and document regions, moving beyond surface-level matching toward more accurate and interpretable retrieval. Our code is available at: https://github.com/VickiCui/AGREE.
Read the full abstract

All authors Wanqing Cui, Wei Huang, Yazhi Guo, Yibo Hu, Meiguang Jin, Junfeng Ma, Keping Bi

Computation and Language

Mem-PAL: Towards Memory-based Personalized Dialogue Assistants for Long-term User-Agent Interaction

Zhaopei Huang, Qifeng Dai, Guozheng Wu et al. (+7 more)

With the rise of smart personal devices, service-oriented human-agent interactions have become increasingly prevalent. This trend highlights the need for personalized dialogue assistants that can understand user-specific traits to accurately interpret requirements and tailor responses to individual preferences. However, existing approaches often overlook the complexities of long-term interactions and fail to capture users' subjective characteristics. To address these gaps, we present PAL-Bench, a new benchmark designed to evaluate the personalization capabilities of service-oriented assistants in long-term user-agent interactions. In the absence of available real-world data, we develop a multi-step LLM-based synthesis pipeline, which is further verified and refined by human annotators. This process yields PAL-Set, the first Chinese dataset comprising multi-session user logs and dialogue histories, which serves as the foundation for PAL-Bench. Furthermore, to improve personalized service-oriented interactions, we propose H$^2$Memory, a hierarchical and heterogeneous memory framework that incorporates retrieval-augmented generation to improve personalized response generation. Comprehensive experiments on both our PAL-Bench and an external dataset demonstrate the effectiveness of the proposed memory framework.
Read the full abstract

All authors Zhaopei Huang, Qifeng Dai, Guozheng Wu, Xiaopeng Wu, Kehan Chen, Chuan Yu, Xubin Li, Tiezheng Ge, Wenxuan Wang, Qin Jin

Computation and Language

Can Large Language Models Function as Qualified Pediatricians? A Systematic Evaluation in Real-World Clinical Contexts

Siyu Zhu, Mouxiao Bian, Yue Xie et al. (+7 more)

With the rapid rise of large language models (LLMs) in medicine, a key question is whether they can function as competent pediatricians in real-world clinical settings. We developed PEDIASBench, a systematic evaluation framework centered on a knowledge-system framework and tailored to realistic clinical environments. PEDIASBench assesses LLMs across three dimensions: application of basic knowledge, dynamic diagnosis and treatment capability, and pediatric medical safety and medical ethics. We evaluated 12 representative models released over the past two years, including GPT-4o, Qwen3-235B-A22B, and DeepSeek-V3, covering 19 pediatric subspecialties and 211 prototypical diseases. State-of-the-art models performed well on foundational knowledge, with Qwen3-235B-A22B achieving over 90% accuracy on licensing-level questions, but performance declined ~15% as task complexity increased, revealing limitations in complex reasoning. Multiple-choice assessments highlighted weaknesses in integrative reasoning and knowledge recall. In dynamic diagnosis and treatment scenarios, DeepSeek-R1 scored highest in case reasoning (mean 0.58), yet most models struggled to adapt to real-time patient changes. On pediatric medical ethics and safety tasks, Qwen2.5-72B performed best (accuracy 92.05%), though humanistic sensitivity remained limited. These findings indicate that pediatric LLMs are constrained by limited dynamic decision-making and underdeveloped humanistic care. Future development should focus on multimodal integration and a clinical feedback-model iteration loop to enhance safety, interpretability, and human-AI collaboration. While current LLMs cannot independently perform pediatric care, they hold promise for decision support, medical education, and patient communication, laying the groundwork for a safe, trustworthy, and collaborative intelligent pediatric healthcare system.
Read the full abstract

All authors Siyu Zhu, Mouxiao Bian, Yue Xie, Yongyu Tang, Zhikang Yu, Tianbin Li, Pengcheng Chen, Bing Han, Jie Xu, Xiaoyan Dong

Computation and Language

Donors and Recipients: On Asymmetric Transfer Across Tasks and Languages with Parameter-Efficient Fine-Tuning

Kajetan Dymkiewicz, Ivan Vulic, Helen Yannakoudakis et al. (+3 more)

Large language models (LLMs) perform strongly across tasks and languages, yet how improvements in one task or language affect other tasks and languages remains poorly understood. We conduct a controlled LoRA fine-tuning study across multiple open-weight LLM families and scales, using a standardised grid of 11 languages and four benchmarks. We fine-tune each model on a single task-language source, then evaluate it on all other task-language target pairs to measure transfer. We decompose transfer into three regimes: (i) Matched-Task (Cross-Language), (ii) Cross-Task (Matched-Language), and (iii) Cross-Task (Cross-Language). Single-source fine-tuning yields a net positive uplift across regimes, but the gains are strongly asymmetric. Matched-Task (Cross-Language) transfer emerges as the most effective and structurally regular regime, with transfer magnitude driven principally by the identity of the target language rather than model architecture. We identify a stable coarse-grained hierarchy in which some task and language targets consistently absorb gains from diverse sources, while others remain relatively isolated. These results imply that effective fine-tuning requires accounting for donor-recipient roles to maximise downstream gains while limiting collateral degradation in other capabilities.
Read the full abstract

All authors Kajetan Dymkiewicz, Ivan Vulic, Helen Yannakoudakis, Eilam Shapira, Roi Reichart, Anna Korhonen

Computation and Language

AHaSIS: Shared Task on Sentiment Analysis for Arabic Dialects

Maram Alharbi, Salmane Chafik, Saad Ezzini et al. (+3 more)

The hospitality industry in the Arab world increasingly relies on customer feedback to shape services, driving the need for advanced Arabic sentiment analysis tools. To address this challenge, the Sentiment Analysis on Arabic Dialects in the Hospitality Domain shared task focuses on Sentiment Detection in Arabic Dialects. This task leverages a multi-dialect, manually curated dataset derived from hotel reviews originally written in Modern Standard Arabic (MSA) and translated into Saudi and Moroccan (Darija) dialects. The dataset consists of 538 sentiment-balanced reviews spanning positive, neutral, and negative categories. Translations were validated by native speakers to ensure dialectal accuracy and sentiment preservation. This resource supports the development of dialect-aware NLP systems for real-world applications in customer experience analysis. More than 40 teams have registered for the shared task, with 12 submitting systems during the evaluation phase. The top-performing system achieved an F1 score of 0.81, demonstrating the feasibility and ongoing challenges of sentiment analysis across Arabic dialects.
Read the full abstract

All authors Maram Alharbi, Salmane Chafik, Saad Ezzini, Ruslan Mitkov, Tharindu Ranasinghe, Hansi Hettiarachchi

Computation and Language · Cross-listed from cs.CR

AutoMalDesc: Large-Scale Script Analysis for Cyber Threat Research

Alexandru-Mihai Apostu, Andrei Preda, Alexandra Daniela Damir et al. (+4 more)

Generating thorough natural language explanations for threat detections remains an open problem in cybersecurity research, despite significant advances in automated malware detection systems. In this work, we present AutoMalDesc, an automated static analysis summarization framework that, following initial training on a small set of expert-curated examples, operates independently at scale. This approach leverages an iterative self-paced learning pipeline to progressively enhance output quality through synthetic data generation and validation cycles, eliminating the need for extensive manual data annotation. Evaluation across 3,600 diverse samples in five scripting languages demonstrates statistically significant improvements between iterations, showing consistent gains in both summary quality and classification accuracy. Our comprehensive validation approach combines quantitative metrics based on established malware labels with qualitative assessment from both human experts and LLM-based judges, confirming both technical precision and linguistic coherence of generated summaries. To facilitate reproducibility and advance research in this domain, we publish our complete dataset of more than 100K script samples, including annotated seed (0.9K) and test (3.6K) datasets, along with our methodology and evaluation framework.
Read the full abstract

All authors Alexandru-Mihai Apostu, Andrei Preda, Alexandra Daniela Damir, Diana Bolocan, Radu Tudor Ionescu, Ioana Croitoru, Mihaela Gaman

Computation and Language

RegionMarker: A Region-Triggered Semantic Watermarking Framework for Embedding-as-a-Service Copyright Protection

Shufan Yang, Zifeng Cheng, Zhiwei Jiang et al. (+5 more)

Embedding-as-a-Service (EaaS) is an effective and convenient deployment solution for addressing various NLP tasks. Nevertheless, recent research has shown that EaaS is vulnerable to model extraction attacks, which could lead to significant economic losses for model providers. For copyright protection, existing methods inject watermark embeddings into text embeddings and use them to detect copyright infringement. However, current watermarking methods often resist only a subset of attacks and fail to provide comprehensive protection. To this end, we present the region-triggered semantic watermarking framework called RegionMarker, which defines trigger regions within a low-dimensional space and injects watermarks into text embeddings associated with these regions. By utilizing a secret dimensionality reduction matrix to project onto this subspace and randomly selecting trigger regions, RegionMarker makes it difficult for watermark removal attacks to evade detection. Furthermore, by embedding watermarks across the entire trigger region and using the text embedding as the watermark, RegionMarker is resilient to both paraphrasing and dimension-perturbation attacks. Extensive experiments on various datasets show that RegionMarker is effective in resisting different attack methods, thereby protecting the copyright of EaaS.
Read the full abstract

All authors Shufan Yang, Zifeng Cheng, Zhiwei Jiang, Yafeng Yin, Cong Wang, Shiping Ge, Yuchen Fu, Qing Gu

Computation and Language · Cross-listed from cs.AI

Dropouts in Confidence: Moral Uncertainty in Human-LLM Alignment

Jea Kwon, Luiz Felipe Vecchietti, Sungwon Park et al. (+1 more)

Humans display significant uncertainty when confronted with moral dilemmas, yet the extent of such uncertainty in machines and AI agents remains underexplored. Recent studies have confirmed the overly confident tendencies of machine-generated responses, particularly in large language models (LLMs). As these systems are increasingly embedded in ethical decision-making scenarios, it is important to understand their moral reasoning and the inherent uncertainties in building reliable AI systems. This work examines how uncertainty influences moral decisions in the classical trolley problem, analyzing responses from 32 open-source models and 9 distinct moral dimensions. We first find that variance in model confidence is greater across models than within moral dimensions, suggesting that moral uncertainty is predominantly shaped by model architecture and training method. To quantify uncertainty, we measure binary entropy as a linear combination of total entropy, conditional entropy, and mutual information. To examine its effects, we introduce stochasticity into models via "dropout" at inference time. Our findings show that our mechanism increases total entropy, mainly through a rise in mutual information, while conditional entropy remains largely unchanged. Moreover, this mechanism significantly improves human-LLM moral alignment, with correlations in mutual information and alignment score shifts. Our results highlight the potential to better align model-generated decisions and human preferences by deliberately modulating uncertainty and reducing LLMs' confidence in morally complex scenarios.
Read the full abstract

All authors Jea Kwon, Luiz Felipe Vecchietti, Sungwon Park, Meeyoung Cha

Computation and Language

Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance

Shalini Maiti, Amar Budhiraja, Bhavul Gauri et al. (+8 more)

Large Language Models (LLMs) have displayed remarkable capabilities across diverse domains, but their training remains resource- and time-intensive, requiring massive computational resources and careful orchestration of training procedures. Model souping-the practice of averaging weights from multiple models of the same architecture-has emerged as a promising pre- and post-training technique that can enhance performance without expensive retraining. We observe that previous souping approaches can lead to collapse in precision-sensitive LLM capabilities. In this paper, we introduce SoCE, a principled approach for model souping to overcome this shortcoming. The proposed method utilizes benchmark composition to identify optimal model candidates and applies non-uniform weighted averaging to maximize performance. Contrary to previous approaches, our method leverages the observation that different clusters (or categories) of points within a benchmark often exhibit low inter-correlations in model performance. SoCE identifies "expert" models for each weakly-correlated category cluster and combines them using optimized weighted averaging rather than uniform weights. We demonstrate that SoCE improves performance and robustness across multiple domains and achieves state-of-the-art results on the Berkeley Function Calling Leaderboard.
Read the full abstract

All authors Shalini Maiti, Amar Budhiraja, Bhavul Gauri, Gaurav Chaurasia, Anton Protopopov, Alexis Audran-Reiss, Michael Slater, Despoina Magka, Tatiana Shavrina, Roberta Raileanu, Yoram Bachrach