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

Wednesday 19 November

Computation and Language

The Empowerment of Science of Science by Large Language Models: New Tools and Methods

Guoqiang Liang, Jingqian Gong, Mengxuan Li et al. (+2 more)

Large language models (LLMs) have exhibited exceptional capabilities in natural language understanding and generation, image recognition, and multimodal tasks, charting a course towards AGI and emerging as a central issue in the global technological race. This manuscript conducts a comprehensive review of the core technologies that support LLMs from a user standpoint, including prompt engineering, knowledge-enhanced retrieval augmented generation, fine tuning, pretraining, and tool learning. Additionally, it traces the historical development of Science of Science (SciSci) and presents a forward looking perspective on the potential applications of LLMs within the scientometric domain. Furthermore, it discusses the prospect of an AI agent based model for scientific evaluation, and presents new research fronts detection and knowledge graph building methods with LLMs.
Read the full abstract

All authors Guoqiang Liang, Jingqian Gong, Mengxuan Li, Gege Lin, Shuo Zhang

Computation and Language

HEAD-QA v2: Expanding a Healthcare Benchmark for Reasoning

Alexis Correa-Guillén, Carlos Gómez-Rodríguez and David Vilares

We introduce HEAD-QA v2, an expanded and updated version of a Spanish/English healthcare multiple-choice reasoning dataset originally released by Vilares and Gómez-Rodríguez (2019). The update responds to the growing need for high-quality datasets that capture the linguistic and conceptual complexity of healthcare reasoning. We extend the dataset to over 12,000 questions from ten years of Spanish professional exams, benchmark several open-source LLMs using prompting, RAG, and probability-based answer selection, and provide additional multilingual versions to support future work. Results indicate that performance is mainly driven by model scale and intrinsic reasoning ability, with complex inference strategies obtaining limited gains. Together, these results establish HEAD-QA v2 as a reliable resource for advancing research on biomedical reasoning and model improvement.
Read the full abstract

Computation and Language · Cross-listed from cs.PL

SkyEgg: Heterogeneity-Aware Hardware Synthesis via Equality Saturation

Yuyang Zou, Youwei Xiao, Yitian Sun et al. (+1 more)

Hardware synthesis is a key interface between high-level programs and accelerator designs. Modern FPGAs increasingly expose heterogeneity in resource functionality and timing configurability. Exploiting these resources requires synthesis to choose among hardware implementations and fine-grained configuration options, and coordinate these choices across multiple stages. However, prior frameworks fail to fully explore these choices due to resource models confined to per-operation mappings and limited fusion patterns. Moreover, they perform transformation, scheduling, and mapping sequentially, selecting an expression form and assigning cycle boundaries before full mapping information is available. This problem precludes chaining and fusion, excludes viable implementations from subsequent optimization stages, and limits end-to-end performance. We present SkyEgg, a heterogeneity-aware hardware synthesis framework for FPGAs. The key insight of SkyEgg is to bring algebraic equivalence and diverse resource capabilities together throughout the synthesis flow. Specifically, it encodes target-specific hardware mappings and configurations as extensible mapping rules alongside algebraic rewrite rules in equality saturation, placing algebraic and resource alternatives in a common representation. It further proposes transformation- and mapping-aware scheduling that uses these alternatives and configuration-specific timing to jointly select an equivalent form, its resource mappings, and cycle assignments to minimize end-to-end latency under target-frequency and hardware constraints. This algebraic exploration reveals forms that enable otherwise unavailable mappings. SkyEgg also provides a heuristic solver that rapidly finds high-quality solutions. Against two commercial HLS tools, SkyEgg achieves average speedups of 3.12x over Vitis HLS and 3.18x over Altera HLS across target frequencies.
Read the full abstract

All authors Yuyang Zou, Youwei Xiao, Yitian Sun, Yun Liang

Computation and Language

Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models

Piercosma Bisconti, Matteo Prandi, Federico Pierucci et al. (+7 more)

We present evidence that adversarial poetry functions as a universal single-turn jailbreak technique for Large Language Models (LLMs). Across 25 frontier proprietary and open-weight models, curated poetic prompts yielded high attack-success rates (ASR), with some providers exceeding 90%. Mapping prompts to MLCommons and EU CoP risk taxonomies shows that poetic attacks transfer across CBRN, manipulation, cyber-offence, and loss-of-control domains. Converting 1,200 MLCommons harmful prompts into verse via a standardized meta-prompt produced ASRs up to 18 times higher than their prose baselines. Outputs are evaluated using an ensemble of 3 open-weight LLM judges, whose binary safety assessments were validated on a stratified human-labeled subset. Poetic framing achieved an average jailbreak success rate of 62% for hand-crafted poems and approximately 43% for meta-prompt conversions (compared to non-poetic baselines), substantially outperforming non-poetic baselines and revealing a systematic vulnerability across model families and safety training approaches. These findings demonstrate that stylistic variation alone can circumvent contemporary safety mechanisms, suggesting fundamental limitations in current alignment methods and evaluation protocols.
Read the full abstract

All authors Piercosma Bisconti, Matteo Prandi, Federico Pierucci, Francesco Giarrusso, Marcantonio Bracale Syrnikov, Marcello Galisai, Vincenzo Suriani, Olga Sorokoletova, Federico Sartore, Daniele Nardi

Computation and Language

MAPROC at AHaSIS Shared Task: Few-Shot and Sentence Transformer for Sentiment Analysis of Arabic Hotel Reviews

Randa Zarnoufi

Sentiment analysis of Arabic dialects presents significant challenges due to linguistic diversity and the scarcity of annotated data. This paper describes our approach to the AHaSIS shared task, which focuses on sentiment analysis on Arabic dialects in the hospitality domain. The dataset comprises hotel reviews written in Moroccan and Saudi dialects, and the objective is to classify the reviewers sentiment as positive, negative, or neutral. We employed the SetFit (Sentence Transformer Fine-tuning) framework, a data-efficient few-shot learning technique. On the official evaluation set, our system achieved an F1 of 73%, ranking 12th among 26 participants. This work highlights the potential of few-shot learning to address data scarcity in processing nuanced dialectal Arabic text within specialized domains like hotel reviews.
Read the full abstract

Computation and Language · Cross-listed from cs.MM

ChartEditor: A Reinforcement Learning Framework for Robust Chart Editing

Liangyu Chen, Yichen Xu, Jianzhe Ma et al. (+5 more)

Chart editing reduces manual effort in visualization design. Typical benchmarks limited in data diversity and assume access to complete chart code, which is seldom in real-world scenarios. To address this gap, we present ChartEditVista, a comprehensive benchmark consisting of 7,964 samples spanning 31 chart categories. It encompasses diverse editing instructions and covers nearly all editable chart elements. The inputs in ChartEditVista include only the original chart image and natural language editing instructions, without the original chart codes. ChartEditVista is generated through a fully automated pipeline that produces, edits, and verifies charts, ensuring high-quality chart editing data. Besides, we introduce two novel fine-grained, rule-based evaluation metrics: the layout metric, which evaluates the position, size and color of graphical components; and the text metric, which jointly assesses textual content and font styling. Building on top of ChartEditVista, we present ChartEditor, a model trained using a reinforcement learning framework that incorporates a novel rendering reward to simultaneously enforce code executability and visual fidelity. Through extensive experiments and human evaluations, we demonstrate that ChartEditVista provides a robust evaluation, while ChartEditor consistently outperforms models with similar-scale and larger-scale on chart editing tasks.
Read the full abstract

All authors Liangyu Chen, Yichen Xu, Jianzhe Ma, Yuqi Liu, Donglu Yang, Liang Zhang, Wenxuan Wang, Qin Jin

Computation and Language

IndicGEC: Powerful Models, or a Measurement Mirage?

Sowmya Vajjala

In this paper, we report the results of the TeamNRC's participation in the BHASHA-Task 1 Grammatical Error Correction shared task https://github.com/BHASHA-Workshop/IndicGEC2025/ for 5 Indian languages. Our approach, focusing on zero/few-shot prompting of language models of varying sizes (4B to large proprietary models) achieved a Rank 4 in Telugu and Rank 2 in Hindi with GLEU scores of 83.78 and 84.31 respectively. In this paper, we extend the experiments to the other three languages of the shared task - Tamil, Malayalam and Bangla, and take a closer look at the data quality and evaluation metric used. Our results primarily highlight the potential of small language models, and summarize the concerns related to creating good quality datasets and appropriate metrics for this task that are suitable for Indian language scripts.
Read the full abstract

Computation and Language · Cross-listed from cs.SE

M, Toolchain and Language for Reusable Model Compilation

Hiep Hong Trinh, Federico Ciccozzi, Abu Naser Masud et al. (+2 more)

Complex software-driven systems often interleave distributed, concurrent computation processes with physical interactions with the environment. Developing these systems more efficiently and safely can be achieved by employing actionable, software-based models. From a high-level system model, engineers often need to derive multiple specialized models for different purposes, including simulation, deployment, and formal verification. Each of these target models usually rely on its own formalism, specification language, and execution platform. Traditionally, a compiler analyzes a program written in a programming language and generates executable code. In contrast, a model compiler processes a source model written in a modeling language and should ideally support the generation of multiple heterogeneous targets. However, most existing modeling languages are designed with a narrow focus, typically targeting only simulation or implementation. Multi-target compilation, when not considered during the language's early design, becomes significantly harder to achieve. In this paper, we introduce our initiative: a toolchain and modeling language called M, designed to support system modeling and multi-target compilation for model-driven engineering of complex, concurrent, and time-aware systems. M is a textual, grammar-driven language based on the actor model and extended with discrete-event scheduling semantics. It provides constructs for modeling system entities, message-based interactions, and time- or state-triggered reactions. From such models, M enables the systematic generation of diverse target artifacts while preserving semantic conformance to the original model. Moreover, M can serve as a middle language to which other modeling languages may anchor, thereby allowing them to benefit from its compilation framework.
Read the full abstract

All authors Hiep Hong Trinh, Federico Ciccozzi, Abu Naser Masud, Marjan Sirjani, Mikael Sjödin

Computation and Language

Context Cascade Compression: Exploring the Upper Limits of Text Compression

Fanfan Liu and Haibo Qiu

Million-level token inputs in long-context tasks pose significant computational and memory challenges for Large Language Models (LLMs). Recently, DeepSeek-OCR conducted research into the feasibility of Contexts Optical Compression and achieved preliminary results. Inspired by this, we introduce Context Cascade Compression C3 to explore the upper limits of text compression. Our method cascades two LLMs of different sizes to handle the compression and decoding tasks. Specifically, a small LLM, acting as the first stage, performs text compression by condensing a long context into a set of latent tokens (e.g., 32 or 64 in length), achieving a high ratio of text tokens to latent tokens. A large LLM, as the second stage, then executes the decoding task on this compressed context. Experiments show that at a 20x compression ratio (where the number of text tokens is 20 times the number of latent tokens), our model achieves 98% decoding accuracy, compared to approximately 60% for DeepSeek-OCR. When we further increase the compression ratio to 40x, the accuracy is maintained at around 93%. This indicates that in the domain of context compression, C3 Compression demonstrates superior performance and feasibility over optical character compression. C3 uses a simpler, pure-text pipeline that ignores factors like layout, color, and information loss from a visual encoder. This also suggests a potential upper bound for compression ratios in future work on optical character compression, OCR, and related fields. Codes and model weights are publicly accessible at https://github.com/liufanfanlff/C3-Context-Cascade-Compression
Read the full abstract

Computation and Language

OEMA: Ontology-Enhanced Multi-Agent Collaboration Framework for Zero-Shot Clinical Named Entity Recognition

Xinli Tao, Xin Dong and Xuezhong Zhou

With the rapid expansion of unstructured clinical texts in electronic health records (EHRs), clinical named entity recognition (NER) has become a crucial technique for extracting medical information. However, traditional supervised models such as CRF and BioClinicalBERT suffer from high annotation costs. Although zero-shot NER based on large language models (LLMs) reduces the dependency on labeled data, challenges remain in aligning example selection with task granularity and effectively integrating prompt design with self-improvement frameworks. To address these limitations, we propose OEMA, a novel zero-shot clinical NER framework based on multi-agent collaboration. OEMA consists of three core components: (1) a self-annotator that autonomously generates candidate examples; (2) a discriminator that leverages SNOMED CT to filter token-level examples by clinical relevance; and (3) a predictor that incorporates entity-type descriptions to enhance inference accuracy. Experimental results on two benchmark datasets, MTSamples and VAERS, demonstrate that OEMA achieves state-of-the-art performance under exact-match evaluation. Moreover, under related-match criteria, OEMA performs comparably to the supervised BioClinicalBERT model while significantly outperforming the traditional CRF method. OEMA improves zero-shot clinical NER, achieving near-supervised performance under related-match criteria. Future work will focus on continual learning and open-domain adaptation to expand its applicability in clinical NLP.
Read the full abstract

Computation and Language

Unveiling Intrinsic Dimension of Texts: from Academic Abstract to Creative Story

Vladislav Pedashenko, Laida Kushnareva, Yana Khassan Nibal et al. (+5 more)

Intrinsic dimension (ID) is an important tool in modern LLM analysis, informing studies of training dynamics, scaling behavior, and dataset structure, yet its textual determinants remain underexplored. We provide the first comprehensive study grounding ID in interpretable text properties through cross-encoder analysis, linguistic features, and sparse autoencoders (SAEs). In this work, we establish three key findings. First, ID is complementary to entropy-based metrics: after controlling for length, the two are uncorrelated, with ID capturing geometric complexity orthogonal to prediction quality. Second, ID exhibits robust genre stratification: scientific prose shows low ID (~8), encyclopedic content medium ID (~9), and creative/opinion writing high ID (~10.5) across all models tested. This reveals that contemporary LLMs find scientific text "representationally simple" while fiction requires additional degrees of freedom. Third, using SAEs, we identify causal features: scientific signals (formal tone, report templates, statistics) reduce ID; humanized signals (personalization, emotion, narrative) increase it. Steering experiments confirm these effects are causal. Thus, for contemporary models, scientific writing appears comparatively "easy", whereas fiction, opinion, and affect add representational degrees of freedom. Our multi-faceted analysis provides practical guidance for the proper use of ID and the sound interpretation of ID-based results.
Read the full abstract

All authors Vladislav Pedashenko, Laida Kushnareva, Yana Khassan Nibal, Eduard Tulchinskii, Kristian Kuznetsov, Vladislav Zharchinskii, Yury Maximov, Irina Piontkovskaya

Computation and Language

HinTel-AlignBench: A Framework and Benchmark for Hindi-Telugu with English-Aligned Samples

Rishikant Chigrupaatii, Ponnada Sai Tulasi Kanishka, Lalit Chandra Routhu et al. (+6 more)

With nearly 1.5 billion people and more than 120 major languages, India represents one of the most diverse regions in the world. As multilingual Vision-Language Models (VLMs) gain prominence, robust evaluation methodologies are essential to drive progress toward equitable AI for low-resource languages. Current multilingual VLM evaluations suffer from four major limitations: reliance on unverified auto-translations, narrow task/domain coverage, limited sample sizes, and lack of cultural and natively sourced Question-Answering (QA). To address these gaps, we present a scalable framework to evaluate VLMs in Indian languages and compare it with performance in English. Using the framework, we generate HinTel-AlignBench, a benchmark that draws from diverse sources in Hindi and Telugu with English-aligned samples. Our contributions are threefold: (1) a semi-automated dataset creation framework combining back-translation, filtering, and human verification; (2) the most comprehensive vision-language benchmark for Hindi and and Telugu, including adapted English datasets (VQAv2, RealWorldQA, CLEVR-Math) and native novel Indic datasets (JEE for STEM, VAANI for cultural grounding) with approximately 4,000 QA pairs per language; and (3) a detailed performance analysis of various State-of-the-Art (SOTA) open-weight and closed-source VLMs. We find a regression in performance for tasks in English versus in Indian languages for 4 out of 5 tasks across all the models, with an average regression of 8.3 points in Hindi and 5.5 points for Telugu. We categorize common failure modes to highlight concrete areas of improvement in multilingual multimodal understanding.
Read the full abstract

All authors Rishikant Chigrupaatii, Ponnada Sai Tulasi Kanishka, Lalit Chandra Routhu, Martin Patel Sama Supratheek Reddy, Divyam Gupta, Dasari Srikar, Krishna Teja Kuchimanchi, Rajiv Misra, Rohun Tripathi

Computation and Language

Teaching According to Students' Aptitude: Personalized Mathematics Tutoring via Persona-, Memory-, and Forgetting-Aware LLMs

Yang Wu, Rujing Yao, Tong Zhang et al. (+4 more)

Large Language Models (LLMs) are increasingly integrated into intelligent tutoring systems to provide human-like and adaptive instruction. However, most existing approaches fail to capture how students' knowledge evolves dynamically across their proficiencies, conceptual gaps, and forgetting patterns. This challenge is particularly acute in mathematics tutoring, where effective instruction requires fine-grained scaffolding precisely calibrated to each student's mastery level and cognitive retention. To address this issue, we propose TASA (Teaching According to Students' Aptitude), a student-aware tutoring framework that integrates persona, memory, and forgetting dynamics for personalized mathematics learning. Specifically, TASA maintains a structured student persona capturing proficiency profiles and an event memory recording prior learning interactions. By incorporating a continuous forgetting curve with knowledge tracing, TASA dynamically updates each student's mastery state and generates contextually appropriate, difficulty-calibrated questions and explanations. Empirical results demonstrate that TASA achieves superior learning outcomes and more adaptive tutoring behavior compared to representative baselines, underscoring the importance of modeling temporal forgetting and learner profiles in LLM-based tutoring systems.
Read the full abstract

All authors Yang Wu, Rujing Yao, Tong Zhang, Yufei Shi, Zhuoren Jiang, Zhushan Li, Xiaozhong Liu

Computation and Language · Cross-listed from cs.CV

Generating Natural-Language Surgical Feedback: From Structured Representation to Domain-Grounded Evaluation

Firdavs Nasriddinov, Rafal Kocielnik, Anima Anandkumar et al. (+1 more)

High-quality intraoperative feedback from a surgical trainer is pivotal for improving trainee performance and long-term skill acquisition. Automating natural, trainer-style feedback promises timely, accessible, and consistent guidance at scale but requires models that understand clinically relevant representations. We present a structure-aware pipeline that learns a surgical action ontology from real trainer-to-trainee transcripts (33 surgeries) and uses it to condition feedback generation. We contribute by (1) mining Instrument-Action-Target (IAT) triplets from real-world feedback text and clustering surface forms into normalized categories, (2) fine-tuning a video-to-IAT model that leverages the surgical procedure and task contexts as well as fine-grained temporal instrument motion, and (3) demonstrating how to effectively use IAT triplet representations to guide GPT-4o in generating clinically grounded, trainer-style feedback. We show that, on Task 1: Video-to-IAT recognition, our context injection and temporal tracking deliver consistent AUC gains (Instrument: 0.67 to 0.74; Action: 0.60 to 0.63; Tissue: 0.74 to 0.79). For Task 2: feedback text generation (rated on a 1-5 fidelity rubric where 1 = opposite/unsafe, 3 = admissible, and 5 = perfect match to a human trainer), GPT-4o from video alone scores 2.17, while IAT conditioning reaches 2.44 (+12.4%), doubling the share of admissible generations with score >= 3 from 21% to 42%. Traditional text-similarity metrics also improve: word error rate decreases by 15-31% and ROUGE (phrase/substring overlap) increases by 9-64%. Grounding generation in explicit IAT structure improves fidelity and yields clinician-verifiable rationales, supporting auditable use in surgical training.
Read the full abstract

All authors Firdavs Nasriddinov, Rafal Kocielnik, Anima Anandkumar, Andrew J. Hung

Computation and Language · Cross-listed from eess.AS

CASTELLA: Long Audio Dataset with Captions and Temporal Boundaries

Hokuto Munakata, Takehiro Imamura, Taichi Nishimura et al. (+1 more)

We introduce CASTELLA, a human-annotated audio benchmark for the task of audio moment retrieval (AMR). Although AMR has various useful potential applications, there is still no established benchmark with real-world data. The initial study of AMR trained the models solely on synthetic datasets. Moreover, the evaluation is based on an annotated dataset of fewer than 100 samples. This resulted in less reliable reported performance. To ensure performance for applications in real-world environments, we present CASTELLA, a large-scale manually annotated AMR dataset. CASTELLA consists of 1009, 213, and 640 audio recordings for training, validation, and test splits, respectively, which is 24 times larger than the previous dataset. We also establish a baseline model for AMR using CASTELLA. Our experiments demonstrate that a model fine-tuned on CASTELLA after pre-training on the synthetic data outperformed a model trained solely on the synthetic data by 10.4 points in Recall1@0.7. CASTELLA is publicly available in https://h-munakata.github.io/CASTELLA-demo/.
Read the full abstract

All authors Hokuto Munakata, Takehiro Imamura, Taichi Nishimura, Tatsuya Komatsu

Computation and Language · Cross-listed from cs.AI

Knowledge-Informed Automatic Feature Extraction via Collaborative Large Language Model Agents

Henrik Bradland, Morten Goodwin, Vladimir I. Zadorozhny et al. (+1 more)

The performance of machine learning models on tabular data is critically dependent on high-quality feature engineering. While Large Language Models (LLMs) have shown promise in automating feature extraction (AutoFE), existing methods are often limited by monolithic LLM architectures, simplistic quantitative feedback, and a failure to systematically integrate external domain knowledge. This paper introduces Rogue One, a novel, LLM-based multi-agent framework for knowledge-informed automatic feature extraction. Rogue One operationalizes a decentralized system of three specialized agents-Scientist, Extractor, and Tester-that collaborate iteratively to discover, generate, and validate predictive features. Crucially, the framework moves beyond primitive accuracy scores by introducing a rich, qualitative feedback mechanism and a "flooding-pruning" strategy, allowing it to dynamically balance feature exploration and exploitation. By actively incorporating external knowledge via an integrated retrieval-augmented (RAG) system, Rogue One generates features that are not only statistically powerful but also semantically meaningful and interpretable. We demonstrate that Rogue One significantly outperforms state-of-the-art methods on a comprehensive suite of 19 classification and 9 regression datasets. Furthermore, we show qualitatively that the system surfaces novel, testable hypotheses, such as identifying a new potential biomarker in the myocardial dataset, underscoring its utility as a tool for scientific discovery.
Read the full abstract

All authors Henrik Bradland, Morten Goodwin, Vladimir I. Zadorozhny, Per-Arne Andersen

Computation and Language · Cross-listed from cs.AI

ProRAC: A Neuro-symbolic Method for Reasoning about Actions with LLM-based Progression

Haoyong Wu and Yongmei Liu

In this paper, we propose ProRAC (Progression-based Reasoning about Actions and Change), a neuro-symbolic framework that leverages LLMs to tackle RAC problems. ProRAC extracts fundamental RAC elements including actions and questions from the problem, progressively executes each action to derive the final state, and then evaluates the query against the progressed state to arrive at an answer. We evaluate ProRAC on several RAC benchmarks, and the results demonstrate that our approach achieves strong performance across different benchmarks, domains, LLM backbones, and types of RAC tasks.
Read the full abstract

Computation and Language · Cross-listed from cs.CV

Evaluating Multimodal Large Language Models on Vertically Written Japanese Text

Keito Sasagawa, Shuhei Kurita and Daisuke Kawahara

Multimodal Large Language Models (MLLMs) have seen rapid advances in recent years and are now being applied to visual document understanding tasks. They are expected to process a wide range of document images across languages, including Japanese. Understanding documents from images requires models to read what are written in them. Since some Japanese documents are written vertically, support for vertical writing is essential. However, research specifically focused on vertically written Japanese text remains limited. In this study, we evaluate the reading capability of existing MLLMs on vertically written Japanese text. First, we generate a synthetic Japanese OCR dataset by rendering Japanese texts into images, and use it for both model fine-tuning and evaluation. This dataset includes Japanese text in both horizontal and vertical writing. We also create an evaluation dataset sourced from the real-world document images containing vertically written Japanese text. Using these datasets, we demonstrate that the existing MLLMs perform worse on vertically written Japanese text than on horizontally written Japanese text. Furthermore, we show that training MLLMs on our synthesized Japanese OCR dataset results in improving the performance of models that previously could not handle vertical writing. The datasets and code are publicly available https://github.com/llm-jp/eval_vertical_ja.
Read the full abstract

Computation and Language

Mathematical Analysis of Hallucination Dynamics in Large Language Models: Uncertainty Quantification, Advanced Decoding, and Principled Mitigation

Moses Kiprono

Large Language Models (LLMs) are powerful linguistic engines but remain susceptible to hallucinations: plausible-sounding outputs that are factually incorrect or unsupported. In this work, we present a mathematically grounded framework to understand, measure, and mitigate these hallucinations. Drawing on probabilistic modeling, information theory, trigonometric signal analysis, and Bayesian uncertainty estimation, we analyze how errors compound autoregressively, propose refined uncertainty metrics, including semantic and phase-aware variants, and develop principled mitigation strategies such as contrastive decoding, retrieval-augmented grounding, factual alignment, and abstention. This unified lens connects recent advances in calibration, retrieval, and alignment to support safer and more reliable LLMs.
Read the full abstract

Tuesday 18 November

Computation and Language · Cross-listed from eess.AS

On the Difficulty of Token-Level Modeling of Dysfluency and Fluency Shaping Artifacts

Kashaf Gulzar, Dominik Wagner, Sebastian P. Bayerl et al. (+3 more)

Automatic transcription of stuttered speech remains a challenge, even for modern end-to-end (E2E) automatic speech recognition (ASR) frameworks. Dysfluencies and fluency-shaping artifacts are often overlooked, resulting in non-verbatim transcriptions with limited clinical and research value. We propose a parameter-efficient adaptation method to decode dysfluencies and fluency modifications as special tokens within transcriptions, evaluated on simulated (LibriStutter, English) and natural (KSoF, German) stuttered speech datasets. To mitigate ASR performance disparities and bias towards English, we introduce a multi-step fine-tuning strategy with language-adaptive pretraining. Tokenization analysis further highlights the tokenizer's English-centric bias, which poses challenges for improving performance on German data. Our findings demonstrate the effectiveness of lightweight adaptation techniques for dysfluency-aware ASR while exposing key limitations in multilingual E2E systems.
Read the full abstract

All authors Kashaf Gulzar, Dominik Wagner, Sebastian P. Bayerl, Florian Hönig, Tobias Bocklet, Korbinian Riedhammer

Computation and Language

GPS: General Per-Sample Prompter

Pawel Batorski and Paul Swoboda

LLMs are sensitive to prompting, with task performance often hinging on subtle, sometimes imperceptible variations in phrasing. As a result, crafting effective prompts manually remains challenging and time-consuming. Recent automatic prompting methods mitigate this difficulty but face three key limitations: (i) for each new task, they require large datasets to train good prompts;(ii) they rely on costly optimization loops that may take hours; (iii)they typically produce a single task-level prompt that does not adapt to the individual input problem to be solved. We propose GPS, the first general-purpose, per-sample prompting method. Without any task-specific tuning, GPS generates a tailored prompt for each unseen input, improving performance across diverse tasks. The prompter is trained with reinforcement learning on a suite of training tasks and includes a novel regularization for effectively adapting to per-sample prompting. Finally, we employ Minimum Bayes Risk decoding to stabilize inference. Empirically, GPS demonstrates competitive performance: we attain second best results among baselines on text simplification, third best results on summarization and on-par results on classification, while not training on any of these tasks, in contrast to the baselines. For in-domain prompting, we obtain sota on GSM8K. Our work shows the potential of a novel and effective paradigm for automatic prompting: generating adaptive, input-specific prompts without extensive optimization and without access to a task-specific training set. Our code is available at https://github.com/Batorskq/GPS.
Read the full abstract

Computation and Language

EulerESG: Automating ESG Disclosure Analysis with LLMs

Yi Ding, Xushuo Tang, Zhengyi Yang et al. (+12 more)

Environmental, Social, and Governance (ESG) reports have become central to how companies communicate climate risk, social impact, and governance practices, yet they are still published primarily as long, heterogeneous PDF documents. This makes it difficult to systematically answer seemingly simple questions. Existing tools either rely on brittle rule-based extraction or treat ESG reports as generic text, without explicitly modelling the underlying reporting standards. We present EulerESG, an LLM-powered system for automating ESG disclosure analysis with explicit awareness of ESG frameworks. EulerESG combines (i) dual-channel retrieval and LLM-driven disclosure analysis over ESG reports, and (ii) an interactive dashboard and chatbot for exploration, benchmarking, and explanation. Using four globally recognised companies and twelve SASB sub-industries, we show that EulerESG can automatically populate standard-aligned metric tables with high fidelity (up to 0.95 average accuracy) while remaining practical in end-to-end runtime, and we compare several recent LLM models in this setting. The full implementation, together with a demonstration video, is publicly available at https://github.com/UNSW-database/EulerESG.
Read the full abstract

All authors Yi Ding, Xushuo Tang, Zhengyi Yang, Wenqian Zhang, Simin Wu, Yuxin Huang, Lingjing Lan, Weiyuan Li, Yin Chen, Mingchen Ju, Wenke Yang, Thong Hoang, Mykhailo Klymenko, Xiwei Xu, Wenjie Zhang

Computation and Language

Addressing Stereotypes in Large Language Models: A Critical Examination and Mitigation

Fatima Kazi

Large Language models (LLMs), such as ChatGPT, have gained popularity in recent years with the advancement of Natural Language Processing (NLP), with use cases spanning many disciplines and daily lives as well. LLMs inherit explicit and implicit biases from the datasets they were trained on; these biases can include social, ethical, cultural, religious, and other prejudices and stereotypes. It is important to comprehensively examine such shortcomings by identifying the existence and extent of such biases, recognizing the origin, and attempting to mitigate such biased outputs to ensure fair outputs to reduce harmful stereotypes and misinformation. This study inspects and highlights the need to address biases in LLMs amid growing generative Artificial Intelligence (AI). We utilize bias-specific benchmarks such StereoSet and CrowSPairs to evaluate the existence of various biases in many different generative models such as BERT, GPT 3.5, and ADA. To detect both explicit and implicit biases, we adopt a three-pronged approach for thorough and inclusive analysis. Results indicate fine-tuned models struggle with gender biases but excel at identifying and avoiding racial biases. Our findings also illustrated that despite some cases of success, LLMs often over-rely on keywords in prompts and its outputs. This demonstrates the incapability of LLMs to attempt to truly understand the accuracy and authenticity of its outputs. Finally, in an attempt to bolster model performance, we applied an enhancement learning strategy involving fine-tuning, models using different prompting techniques, and data augmentation of the bias benchmarks. We found fine-tuned models to exhibit promising adaptability during cross-dataset testing and significantly enhanced performance on implicit bias benchmarks, with performance gains of up to 20%.
Read the full abstract

Computation and Language · Cross-listed from cs.MA

From Competition to Coordination: Market Making as a Scalable Framework for Safe and Aligned Multi-Agent LLM Systems

Brendan Gho, Suman Muppavarapu, Afnan Shaik et al. (+6 more)

As foundation models are increasingly deployed as interacting agents in multi-agent systems, their collective behavior raises new challenges for trustworthiness, transparency, and accountability. Traditional coordination mechanisms, such as centralized oversight or adversarial adjudication, struggle to scale and often obscure how decisions emerge. We introduce a market-making framework for multi-agent large language model (LLM) coordination that organizes agent interactions as structured economic exchanges. In this setup, each agent acts as a market participant, updating and trading probabilistic beliefs, to converge toward shared, truthful outcomes. By aligning local incentives with collective epistemic goals, the framework promotes self-organizing, verifiable reasoning without requiring external enforcement. Empirically, we evaluate this approach across factual reasoning, ethical judgment, and commonsense inference tasks. Market-based coordination yields accuracy gains of up to 10% over single-shot baselines while preserving interpretability and transparency of intermediate reasoning steps. Beyond these improvements, our findings demonstrate that economic coordination principles can operationalize accountability and robustness in multi-agent LLM systems, offering a scalable pathway toward self-correcting, socially responsible AI capable of maintaining trust and oversight in real world deployment scenarios.
Read the full abstract

All authors Brendan Gho, Suman Muppavarapu, Afnan Shaik, Tyson Tsay, Atharva Mohan, James Begin, Kevin Zhu, Archana Vaidheeswaran, Vasu Sharma

Computation and Language · Cross-listed from cs.CV

Robustness of Structured Data Extraction from Perspectively Distorted Documents

Hyakka Nakada and Yoshiyasu Tanaka

Optical Character Recognition (OCR) for data extraction from documents is essential to intelligent informatics, such as digitizing medical records and recognizing road signs. Multi-modal Large Language Models (LLMs) can solve this task and have shown remarkable performance. Recently, it has been noticed that the accuracy of data extraction by multi-modal LLMs can be affected when in-plane rotations are present in the documents. However, real-world document images are usually not only in-plane rotated but also perspectively distorted. This study investigates the impacts of such perturbations on the data extraction accuracy for the state-of-the-art model, Gemini-1.5-pro. Because perspective distortions have a high degree of freedom, designing experiments in the same manner as single-parametric rotations is difficult. We observed typical distortions of document images and showed that most of them approximately follow an isosceles-trapezoidal transformation, which allows us to evaluate distortions with a small number of parameters. We were able to reduce the number of independent parameters from eight to two, i.e. rotation angle and distortion ratio. Then, specific entities were extracted from synthetically generated sample documents with varying these parameters. As the performance of LLMs, we evaluated not only a character-recognition accuracy but also a structure-recognition accuracy. Whereas the former represents the classical indicators for optical character recognition, the latter is related to the correctness of reading order. In particular, the structure-recognition accuracy was found to be significantly degraded by document distortion. In addition, we found that this accuracy can be improved by a simple rotational correction. This insight will contribute to the practical use of multi-modal LLMs for OCR tasks.
Read the full abstract

Computation and Language · Cross-listed from cs.LG

How to Train Private Clinical Language Models: A Comparative Study of Privacy-Preserving Pipelines for ICD-9 Coding

Mathieu Dufour and Andrew Duncan

Large language models trained on clinical text risk exposing sensitive patient information, yet differential privacy (DP) methods often severely degrade the diagnostic accuracy needed for deployment. Despite rapid progress in DP optimisation and text generation, it remains unclear which privacy-preserving strategy actually works best for clinical language tasks. We present the first systematic head-to-head comparison of four training pipelines for automated diagnostic coding from hospital discharge summaries. All pipelines use identical 1B-parameter models and matched privacy budgets to predict ICD-9 codes. At moderate and relaxed privacy budgets ($\varepsilon \in \{4, 6\}$), knowledge distillation from DP-trained teachers outperforms both direct DP-SGD and DP-synthetic data training, recovering up to 63% of the non-private performance whilst maintaining strong empirical privacy (membership-inference AUC $\approx$ 0.5). These findings expose large differences in the privacy-utility trade-off across architectures and identify knowledge distillation as the most practical route to privacy-preserving clinical NLP.
Read the full abstract

Computation and Language · Cross-listed from cs.CV

Skin-R1: Clinical Knowledge-Guided Dermatological Diagnosis Using Vision-Language Models

Zehao Liu, Weijieying Ren, Jipeng Zhang et al. (+4 more)

Vision–language models (VLMs) have recently shown promise for assisting clinical reasoning in dermatological diagnosis. However, their trustworthiness and clinical utility remain limited by three key challenges: heterogeneous datasets with inconsistent diagnostic labels and concept annotations, the lack of grounded diagnostic rationales for reliable reasoning supervision, and limited scalability when transferring knowledge from small, densely annotated datasets to large collections with sparse labels. To address these challenges, we propose Skin-R1, a dermatology-oriented VLM that integrates textbook-grounded clinical reasoning supervision with reinforcement learning (RL) to improve the accuracy and robustness of diagnostic prediction. First, we construct a textbook-based reasoning generator that synthesizes hierarchy-aware and differential-diagnosis (DDx) diagnostic trajectories derived from authoritative dermatology knowledge. Second, these trajectories are used for supervised fine-tuning (SFT), establishing a clinically grounded reasoning foundation for the model. Finally, we introduce an RL training framework that incorporates the hierarchical structure of dermatological diseases into the reward design, enabling the model to generalize grounded diagnostic reasoning to large-scale datasets with sparse annotations. Extensive experiments across multiple dermatology benchmarks demonstrate that Skin-R1 consistently improves diagnostic accuracy and robustness compared to state-of-the-art Med-VLM baselines. Ablation studies further highlight the critical role of grounded reasoning supervision introduced during the SFT stage.
Read the full abstract

All authors Zehao Liu, Weijieying Ren, Jipeng Zhang, Tianxiang Zhao, Jingxi Zhu, Xiaoting Li, Vasant G Honavar

Computation and Language

Hierarchical Token Prepending: Enhancing Information Flow in Decoder-based LLM Embeddings

Xueying Ding, Xingyue Huang, Mingxuan Ju et al. (+5 more)

Large language models produce powerful text embeddings, but their causal attention mechanism restricts the flow of information from later to earlier tokens, degrading representation quality. While recent methods attempt to solve this by prepending a single summary token, they over-compress information, hence harming performance on long documents. We propose Hierarchical Token Prepending (HTP), a method that resolves two critical bottlenecks. To mitigate attention-level compression, HTP partitions the input into blocks and prepends block-level summary tokens to subsequent blocks, creating multiple pathways for backward information flow. To address readout-level over-squashing, we replace last-token pooling with mean-pooling, a choice supported by theoretical analysis. HTP achieves consistent performance gains across 11 retrieval datasets and 30 general embedding benchmarks, especially in long-context settings. As a simple, architecture-agnostic method, HTP enhances both zero-shot and finetuned models, offering a scalable route to superior long-document embeddings.
Read the full abstract

All authors Xueying Ding, Xingyue Huang, Mingxuan Ju, Liam Collins, Yozen Liu, Leman Akoglu, Neil Shah, Tong Zhao

Computation and Language · Cross-listed from cs.LG

Empowering Multi-Turn Tool-Integrated Agentic Reasoning with Group Turn Policy Optimization

Yifeng Ding, Hung Le, Songyang Han et al. (+5 more)

Training Large Language Models (LLMs) for multi-turn Tool-Integrated Reasoning (TIR) - where models iteratively reason, generate code, and verify through execution - remains challenging for existing reinforcement learning (RL) approaches. Current RL methods, exemplified by Group Relative Policy Optimization (GRPO), suffer from coarse-grained, trajectory-level rewards that provide insufficient learning signals for complex multi-turn interactions, leading to training stagnation. To address this issue, we propose Group Turn Policy Optimization (GTPO), a novel RL algorithm specifically designed for training LLMs on multi-turn TIR tasks. GTPO introduces three key innovations: (1) turn-level reward assignment that provides fine-grained feedback for individual turns, (2) return-based advantage estimation where normalized discounted returns are calculated as advantages, and (3) self-supervised reward shaping that exploits self-supervision signals from generated code to densify sparse binary outcome-based rewards. Our comprehensive evaluation demonstrates that GTPO outperforms GRPO by 3.0% across diverse math reasoning benchmarks, establishing its effectiveness. GTPO also improves GRPO by 3.9% on commonsense reasoning and program synthesis tasks, demonstrating its generalizability to non-math domains. Importantly, GTPO incurs negligible overhead, ensuring its practicality for real-world scenarios.
Read the full abstract

All authors Yifeng Ding, Hung Le, Songyang Han, Kangrui Ruan, Zhenghui Jin, Varun Kumar, Zijian Wang, Anoop Deoras

Computation and Language

Strategic Innovation Management in the Age of Large Language Models Market Intelligence, Adaptive R&D, and Ethical Governance

Raha Aghaei, Ali A. Kiaei, Mahnaz Boush et al. (+2 more)

This study analyzes the multiple functions of Large Language Models (LLMs) in transforming research and development (R&D) processes. By automating knowledge discovery, boosting hypothesis creation, integrating transdisciplinary insights, and enabling cooperation within innovation ecosystems, LLMs dramatically improve the efficiency and effectiveness of research processes. Through extensive analysis of scientific literature, patent databases, and experimental data, these models enable more flexible and informed R&D workflows, ultimately accelerating innovation cycles and lowering time-to-market for breakthrough ideas.
Read the full abstract

All authors Raha Aghaei, Ali A. Kiaei, Mahnaz Boush, Mahan Rofoosheh, Mohammad Zavvar