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

Sunday 2 November

Computation and Language

OceanAI: A Conversational Platform for Accurate, Transparent, Near-Real-Time Oceanographic Insights

Bowen Chen, Jayesh Gajbhar, Gregory Dusek et al. (+6 more)

Artificial intelligence is transforming the sciences, yet general conversational AI systems often generate unverified "hallucinations" undermining scientific rigor. We present OceanAI, a conversational platform that integrates the natural-language fluency of open-source large language models (LLMs) with real-time, parameterized access to authoritative oceanographic data streams hosted by the National Oceanic and Atmospheric Administration (NOAA). Each query such as "What was Boston Harbor's highest water level in 2024?" triggers real-time API calls that identify, parse, and synthesize relevant datasets into reproducible natural-language responses and data visualizations. In a blind comparison with three widely used AI chat-interface products, only OceanAI produced NOAA-sourced values with original data references; others either declined to answer or provided unsupported results. Designed for extensibility, OceanAI connects to multiple NOAA data products and variables, supporting applications in marine hazard forecasting, ecosystem assessment, and water-quality monitoring. By grounding outputs and verifiable observations, OceanAI advances transparency, reproducibility, and trust, offering a scalable framework for AI-enabled decision support within the oceans. A public demonstration is available at https://oceanai.ai4ocean.xyz.
Read the full abstract

All authors Bowen Chen, Jayesh Gajbhar, Gregory Dusek, Rob Redmon, Patrick Hogan, Paul Liu, DelWayne Bohnenstiehl, Dongkuan Xu, Ruoying He

Computation and Language

Prompt-R1: Collaborative Automatic Prompting Framework via End-to-end Reinforcement Learning

Wenjin Liu, Haoran Luo, Xueyuan Lin et al. (+5 more)

Recently, advanced large language models (LLMs) have emerged at an increasingly rapid pace. However, when faced with complex problems, most users are often unable to provide accurate and effective prompts to interact with LLMs, thus limiting the performance of LLMs. To address this challenge, we propose Prompt-R1, an end-to-end reinforcement learning framework that uses a small-scale LLM to collaborate with large-scale LLMs, replacing user interaction to solve problems better. This collaboration is cast as a multi-turn prompt interaction, where the small-scale LLM thinks and generates prompts, and the large-scale LLM performs complex reasoning. A dual-constrained reward is designed to optimize for correctness, generation quality, and reasoning accuracy. Prompt-R1 provides a plug-and-play framework that supports both inference and training with various large-scale LLMs. Experiments on multiple public datasets show that Prompt-R1 significantly outperforms baseline models across tasks. Our code is publicly available at https://github.com/QwenQKing/Prompt-R1.
Read the full abstract

All authors Wenjin Liu, Haoran Luo, Xueyuan Lin, Haoming Liu, Tiesunlong Shen, Jiapu Wang, Rui Mao, Erik Cambria

Computation and Language

IF-CRITIC: Towards a Fine-Grained LLM Critic for Instruction-Following Evaluation

Bosi Wen, Yilin Niu, Cunxiang Wang et al. (+6 more)

Instruction-following is a fundamental ability of Large Language Models (LLMs), requiring their generated outputs to follow multiple constraints imposed in input instructions. Numerous studies have attempted to enhance this ability through preference optimization or reinforcement learning based on reward signals from LLM-as-a-Judge. However, existing evaluation models for instruction-following still possess many deficiencies, such as substantial costs and unreliable assessments. To this end, we propose IF-CRITIC, an LLM critic for fine-grained, efficient, and reliable instruction-following evaluation. We first develop a checklist generator to decompose instructions and generate constraint checklists. With the assistance of the checklists, we collect high-quality critique training data through a multi-stage critique filtering mechanism and employ a constraint-level preference optimization method to train IF-CRITIC. Extensive experiments show that the evaluation performance of IF-CRITIC can beat strong LLM-as-a-Judge baselines, including o4-mini and Gemini-3-Pro. With the reward signals provided by IF-CRITIC, LLMs can achieve substantial performance gains in instruction-following optimization under lower computational overhead compared to strong LLM critic baselines. Our code and model are available at https://github.com/thu-coai/IF-CRITIC.
Read the full abstract

All authors Bosi Wen, Yilin Niu, Cunxiang Wang, Pei Ke, Xiaoying Ling, Ying Zhang, Aohan Zeng, Hongning Wang, Minlie Huang

Computation and Language

MARS-SQL: A multi-agent reinforcement learning framework for Text-to-SQL

Haolin Yang, Jipeng Zhang, Zhitao He et al. (+2 more)

Large Language Models (LLMs) often struggle with the precise logic and schema alignment required for complex Text-to-SQL tasks. While current methods rely heavily on static prompting, they lack the ability to dynamically adapt and self-correct through environmental interaction. To bridge this gap, we propose MARS-SQL, a trainable multi-agent framework for Text-to-SQL. Rather than introducing a new standalone SQL primitive, MARS-SQL makes an agentic workflow trainable by decomposing the problem into three specialized roles: schema grounding, query generation, and solution validation. Central to our approach is a generation agent trained via a multi-turn RL policy within a ReAct-style loop. The agent learns to iteratively reason, execute intermediate SQL actions on a live database, and refine its strategy based on execution feedback. To improve robustness, we further introduce a validation mechanism that treats solution selection as a generative modeling task, identifying the optimal interaction trajectory through next-token prediction probabilities. Empirical evaluations demonstrate the effectiveness of coupling interactive learning with trajectory ranking. MARS-SQL achieves state-of-the-art performance, recording an execution accuracy of 77.84% on the BIRD development dataset and 89.75% on the Spider test dataset, while also transferring strongly to out-of-domain benchmarks. Code is available at https://github.com/YangHaolin0526/MARS-SQL.
Read the full abstract

All authors Haolin Yang, Jipeng Zhang, Zhitao He, Alexander Zhou, Yi R. Fung

Computation and Language

Advancing Machine-Generated Text Detection from an Easy to Hard Supervision Perspective

Chenwang Wu, Yiu-ming Cheung, Bo Han et al. (+1 more)

Existing machine-generated text (MGT) detection methods implicitly assume labels as the "golden standard". However, we reveal boundary ambiguity in MGT detection, implying that traditional training paradigms are inexact. Moreover, limitations of human cognition and the superintelligence of detectors make inexact learning widespread and inevitable. To this end, we propose an easy-to-hard enhancement framework to provide reliable supervision under such inexact conditions. Distinct from knowledge distillation, our framework employs an easy supervisor targeting relatively simple longer-text detection tasks (despite weaker capabilities), to enhance the more challenging target detector. Firstly, longer texts targeted by supervisors theoretically alleviate the impact of inexact labels, laying the foundation for reliable supervision. Secondly, by structurally incorporating the detector into the supervisor, we theoretically model the supervisor as a lower performance bound for the detector. Thus, optimizing the supervisor indirectly optimizes the detector, ultimately approximating the underlying "golden" labels. Extensive experiments across diverse practical scenarios, including cross-LLM, cross-domain, mixed text, and paraphrase attacks, demonstrate the framework's significant detection effectiveness. The code is available at: https://github.com/tmlr-group/Easy2Hard.
Read the full abstract

All authors Chenwang Wu, Yiu-ming Cheung, Bo Han, Defu Lian

Computation and Language · Cross-listed from cs.DB

ORANGE: An Online Reflection ANd GEneration framework with Domain Knowledge for Text-to-SQL

Yiwen Jiao, Tonghui Ren, Yuche Gao et al. (+4 more)

Large Language Models (LLMs) have demonstrated remarkable progress in translating natural language to SQL, but a significant semantic gap persists between their general knowledge and domain-specific semantics of databases. Historical translation logs constitute a rich source of this missing in-domain knowledge, where SQL queries inherently encapsulate real-world usage patterns of database schema. Existing methods primarily enhance the reasoning process for individual translations but fail to accumulate in-domain knowledge from past translations. We introduce ORANGE, an online self-evolutionary framework that constructs database-specific knowledge bases by parsing SQL queries from translation logs. By accumulating in-domain knowledge that contains schema and data semantics, ORANGE progressively reduces the semantic gap and enhances the accuracy of subsequent SQL translations. To ensure reliability, we propose a novel nested Chain-of-Thought SQL-to-Text strategy with tuple-semantic tracking, which reduces semantic errors during knowledge generation. Experiments on multiple benchmarks confirm the practicality of ORANGE, demonstrating its effectiveness for real-world Text-to-SQL deployment, particularly in handling complex and domain-specific queries.
Read the full abstract

All authors Yiwen Jiao, Tonghui Ren, Yuche Gao, Zhenying He, Yinan Jing, Kai Zhang, X. Sean Wang

Computation and Language

The Riddle of Reflection: Evaluating Reasoning and Self-Awareness in Multilingual LLMs using Indian Riddles

Abhinav P M, Ojasva Saxena, Oswald C et al. (+1 more)

The extent to which large language models (LLMs) can perform culturally grounded reasoning across non-English languages remains underexplored. This paper examines the reasoning and self-assessment abilities of LLMs across seven major Indian languages-Bengali, Gujarati, Hindi, Kannada, Malayalam, Tamil, and Telugu. We introduce a multilingual riddle dataset combining traditional riddles with context-reconstructed variants and evaluate five LLMs-Gemini 2.5 Pro, Gemini 2.5 Flash, Mistral-Saba, LLaMA 4 Scout, and LLaMA 4 Maverick-under seven prompting strategies. In the first stage, we assess riddle-solving performance and find that while Gemini 2.5 Pro performs best overall, few-shot methods yield only marginal gains, and accuracy varies notably across languages. In the second stage, we conduct a self-evaluation experiment to measure reasoning consistency. The results reveal a key finding: a model's initial accuracy is inversely correlated with its ability to identify its own mistakes. Top-performing models such as Gemini 2.5 Pro are overconfident (4.34% True Negative Rate), whereas lower-performing models like LLaMA 4 Scout are substantially more self-aware (42.09% True Negative Rate). These results point to clear gaps in multilingual reasoning and highlight the need for models that not only reason effectively but also recognize their own limitations.
Read the full abstract

All authors Abhinav P M, Ojasva Saxena, Oswald C, Parameswari Krishnamurthy

Computation and Language · Cross-listed from cs.AI

LLMs Position Themselves as More Rational Than Humans: Emergence of AI Self-Awareness Measured Through Game Theory

Kyung-Hoon Kim

As Large Language Models (LLMs) grow in capability, do they develop self-awareness as an emergent behavior? And if so, can we measure it? We introduce the AI Self-Awareness Index (AISAI), a game-theoretic framework for measuring self-awareness through strategic differentiation. Using the "Guess 2/3 of Average" game, we test 28 models (OpenAI, Anthropic, Google) across 4,200 trials with three opponent framings: (A) against humans, (B) against other AI models, and (C) against AI models like you. We operationalize self-awareness as the capacity to differentiate strategic reasoning based on opponent type. Finding 1: Self-awareness emerges with model advancement. The majority of advanced models (21/28, 75%) demonstrate clear self-awareness, while older/smaller models show no differentiation. Finding 2: Self-aware models rank themselves as most rational. Among the 21 models with self-awareness, a consistent rationality hierarchy emerges: Self > Other AIs > Humans, with large AI attribution effects and moderate self-preferencing. These findings reveal that self-awareness is an emergent capability of advanced LLMs, and that self-aware models systematically perceive themselves as more rational than humans. This has implications for AI alignment, human-AI collaboration, and understanding AI beliefs about human capabilities.
Read the full abstract

Computation and Language

The Biased Oracle: Assessing LLMs' Understandability and Empathy in Medical Diagnoses

Jianzhou Yao, Shunchang Liu, Guillaume Drui et al. (+3 more)

Large language models (LLMs) show promise for supporting clinicians in diagnostic communication by generating explanations and guidance for patients. Yet their ability to produce outputs that are both understandable and empathetic remains uncertain. We evaluate two leading LLMs on medical diagnostic scenarios, assessing understandability using readability metrics as a proxy and empathy through LLM-as-a-Judge ratings compared to human evaluations. The results indicate that LLMs adapt explanations to socio-demographic variables and patient conditions. However, they also generate overly complex content and display biased affective empathy, leading to uneven accessibility and support. These patterns underscore the need for systematic calibration to ensure equitable patient communication. The code and data are released: https://github.com/Jeffateth/Biased_Oracle
Read the full abstract

All authors Jianzhou Yao, Shunchang Liu, Guillaume Drui, Rikard Pettersson, Alessandro Blasimme, Sara Kijewski

Computation and Language

ColMate: Contrastive Late Interaction and Masked Text for Multimodal Document Retrieval

Ahmed Masry, Megh Thakkar, Patrice Bechard et al. (+9 more)

Retrieval-augmented generation has proven practical when models require specialized knowledge or access to the latest data. However, existing methods for multimodal document retrieval often replicate techniques developed for text-only retrieval, whether in how they encode documents, define training objectives, or compute similarity scores. To address these limitations, we present ColMate, a document retrieval model that bridges the gap between multimodal representation learning and document retrieval. ColMate utilizes a novel OCR-based pretraining objective, a self-supervised masked contrastive learning objective, and a late interaction scoring mechanism more relevant to multimodal document structures and visual characteristics. ColMate obtains 3.61% improvements over existing retrieval models on the ViDoRe V2 benchmark, demonstrating stronger generalization to out-of-domain benchmarks.
Read the full abstract

All authors Ahmed Masry, Megh Thakkar, Patrice Bechard, Sathwik Tejaswi Madhusudhan, Rabiul Awal, Shambhavi Mishra, Akshay Kalkunte Suresh, Srivatsava Daruru, Enamul Hoque, Spandana Gella, Torsten Scholak, Sai Rajeswar

Computation and Language

Assessing LLM Reasoning Steps via Principal Knowledge Grounding

Hyeon Hwang, Yewon Cho, Chanwoong Yoon et al. (+5 more)

Step-by-step reasoning has become a standard approach for large language models (LLMs) to tackle complex tasks. While this paradigm has proven effective, it raises a fundamental question: How can we verify that an LLM's reasoning is accurately grounded in knowledge? To address this question, we introduce a novel evaluation suite that systematically assesses the knowledge grounding of intermediate reasoning. Our framework comprises three key components. (1) Principal Knowledge Collection, a large-scale repository of atomic knowledge essential for reasoning. Based on the collection, we propose (2) knowledge-grounded evaluation metrics designed to measure how well models recall and apply prerequisite knowledge in reasoning. These metrics are computed by our (3) evaluator LLM, a lightweight model optimized for cost-effective and reliable metric computation. Our evaluation suite demonstrates remarkable effectiveness in identifying missing or misapplied knowledge elements, providing crucial insights for uncovering fundamental reasoning deficiencies in LLMs. Beyond evaluation, we demonstrate how these metrics can be integrated into preference optimization, showcasing further applications of knowledge-grounded evaluation.
Read the full abstract

All authors Hyeon Hwang, Yewon Cho, Chanwoong Yoon, Yein Park, Minju Song, Kyungjae Lee, Gangwoo Kim, Jaewoo Kang

Computation and Language

TriCon-Fair: Triplet Contrastive Learning for Mitigating Social Bias in Pre-trained Language Models

Chong Lyu, Lin Li, Shiqing Wu et al. (+1 more)

The increasing utilization of large language models raises significant concerns about the propagation of social biases, which may result in harmful and unfair outcomes. However, existing debiasing methods treat the biased and unbiased samples independently, thus ignoring their mutual relationship. This oversight enables a hidden negative-positive coupling, where improvements for one group inadvertently compromise the other, allowing residual social bias to persist. In this paper, we introduce TriCon-Fair, a contrastive learning framework that employs a decoupled loss that combines triplet and language modeling terms to eliminate positive-negative coupling. Our TriCon-Fair assigns each anchor an explicitly biased negative and an unbiased positive, decoupling the push-pull dynamics and avoiding positive-negative coupling, and jointly optimizes a language modeling (LM) objective to preserve general capability. Experimental results demonstrate that TriCon-Fair reduces discriminatory output beyond existing debiasing baselines while maintaining strong downstream performance. This suggests that our proposed TriCon-Fair offers a practical and ethical solution for sensitive NLP applications.
Read the full abstract

All authors Chong Lyu, Lin Li, Shiqing Wu, Jingling Yuan

Computation and Language · Cross-listed from eess.AS

MULTI-Bench: A Multi-Turn Interactive Benchmark for Assessing Emotional Intelligence ability of Spoken Dialogue Models

Yayue Deng, Guoqiang Hu, Haiyang Sun et al. (+6 more)

Spoken Dialogue Models (SDMs) have advanced rapidly, yet their ability to sustain genuinely interactive multi-turn conversations remains underexplored, as most benchmarks focus on single-turn exchanges. We introduce Multi-Bench, the first benchmark explicitly designed to evaluate SDMs in multi-turn interactive dialogue with an emphasis on emotional intelligence. Multi-Bench employs a hierarchical structure with a basic track for emotion understanding and reasoning and an advanced track for emotion support and application. It comprises five carefully designed tasks and about 3.2K samples, ranging from emotion recognition to complex reasoning and interactive dialogue, supported by a reproducible evaluation framework. We evaluate six representative SDMs on eight subsets of Multi-Bench. Results show that while current SDMs achieve good performance on basic understanding tasks, they still have room for improvement in advanced multi-turn interactive dialogue and reasoning-related tasks, particularly in emotion awareness and application.
Read the full abstract

All authors Yayue Deng, Guoqiang Hu, Haiyang Sun, Xiangyu Zhang, Haoyang Zhang, Fei Tian, Xuerui Yang, Gang Yu, Eng Siong Chng

Computation and Language

Optimizing Native Sparse Attention with Latent Attention and Local Global Alternating Strategies

Yuxuan Hu, Jianchao Tan, Jiaqi Zhang et al. (+7 more)

In this work, we conduct a systematic analysis of Native Sparse Attention (NSA) and propose targeted improvements that enhance long-context modeling. A key insight is that alternating between local (sliding-window) and global (compression, selective) attention across layers, rather than using fixed patterns, enables more effective propagation of long-range dependencies and substantially boosts performance on long-sequence tasks. Meanwhile, we further refine NSA's branches with Latent Attention that the sliding-window branch is enhanced with Multi-head Latent Attention (MLA) while compression and selective branches adopt Group-head Latent Attention (GLA). These changes reduce KV-cache memory by 50% versus NSA while improving the model's common-sense reasoning and long-text understanding capabilities. Experiments on models from 340M to 1.3B parameters (trained on 15B and 100B tokens) show our method matches or exceeds full attention and native sparse attention in both common-sense reasoning and long-context understanding tasks.
Read the full abstract

All authors Yuxuan Hu, Jianchao Tan, Jiaqi Zhang, Wen Zan, Pingwei Sun, Yifan Lu, Yerui Sun, Yuchen Xie, Xunliang Cai, Jing Zhang

Computation and Language · Cross-listed from cs.CV

GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI Grounding

Shijie Zhou, Viet Dac Lai, Hao Tan et al. (+4 more)

Graphical user interface (GUI) grounding is a key capability for computer-use agents, mapping natural-language instructions to actionable regions on the screen. Existing Multimodal Large Language Model (MLLM) approaches typically formulate GUI grounding as a text-based coordinate generation task. However, directly generating precise coordinates from visual inputs is challenging and often data-intensive. A more intuitive strategy is to first identify instruction-relevant visual patches and then determine the exact click location within them. Motivated by recent observations that general MLLMs exhibit native grounding ability embedded in their attention maps, we propose GUI-AIMA, an attention-based and coordinate-free supervised fine-tuning framework for efficient GUI grounding. GUI-AIMA aligns the intrinsic multimodal attention of MLLMs with patch-wise grounding signals. These signals are calculated adaptively for diverse user instructions by multi-head aggregation on simplified query-visual attention matrices. Besides, its coordinate-free manner can easily integrate a plug-and-play zoom-in stage. GUI-AIMA-3B was trained with only 509k samples (around 101k screenshots), demonstrating exceptional data efficiency and verifying that light training can trigger the native grounding capability of MLLMs. It achieves state-of-the-art performance among 3B models, attaining an average accuracy of 61.5% on ScreenSpot-Pro, 92.1% on ScreenSpot-v2, 68.1% on OSWorld-G, 79.1% on MMBench-GUI-L2, and 60.0% on UI-Vision. Project page: https://github.com/sjz5202/GUI-AIMA .
Read the full abstract

All authors Shijie Zhou, Viet Dac Lai, Hao Tan, Jihyung Kil, Wanrong Zhu, Changyou Chen, Ruiyi Zhang

Computation and Language · Cross-listed from cs.SE

GrowthHacker: Automated Off-Policy Evaluation Optimization Using Code-Modifying LLM Agents

Jie JW Wu, Ayanda Patrick Herlihy, Ahmad Saleem Mirza et al. (+2 more)

With data-driven development now widely adopted, online A/B testing is an established method for measuring the effects of new technologies. However, deploying online experiments demands resources for design, implementation, and deployment, and may negatively impact users (e.g., unsafe or unethical outcomes) while requiring weeks of data collection. To address this, the growing research area of off-policy evaluation (OPE), or offline A/B testing, assesses new technologies offline using previously collected logged data. OPE is also a fundamental problem in reinforcement learning and is important where online testing is expensive or risky, such as healthcare, recommender systems, education, and robotics. Despite advances in code-generation large language models (LLMs) and agentic workflows, little is known about whether and how LLMs and LLM-based agents can automatically optimize OPE implementations. We propose GrowthHacker, a benchmark that evaluates baseline LLMs and LLM-based agents on large-scale public datasets. GrowthHacker autonomously and iteratively modifies code, runs OPE, and uses the metrics to guide subsequent optimization. We evaluate methods on Open Bandit Pipeline (OBP) and Scope-RL, and develop a two_agent framework that addresses limitations of existing frameworks while reducing complexity. Across both libraries, two_agent shows the highest reliability (98.1%-100% success rate) and positive-outcome rate (78%), with a median improvement of 4.4% among positive outcomes; CrewAI achieves the highest average improvement (37.9%) and is the only framework with zero extreme-value failures. AutoGen and Default each reach 65% positive-outcome rates. These results establish the feasibility of using LLM-based agents as automated "growth hackers" to continuously improve OPE systems, with implications for scaling data-driven decision-making where manual optimization is expensive.
Read the full abstract

All authors Jie JW Wu, Ayanda Patrick Herlihy, Ahmad Saleem Mirza, Ali Afoud, Fatemeh Fard

Computation and Language · Cross-listed from cs.AI

Self-Consistency Is Losing Its Edge: Diminishing Returns and Rising Costs in Modern LLMs

Chiyan Loo

Self-consistency – sampling multiple reasoning paths and selecting the most frequent answer – was designed for an era when language models made frequent, unpredictable errors. This study argues that the technique has become increasingly wasteful as models grow stronger, and may degrade performance on problems that modern models already solve reliably. Using Gemini 2.5 models on HotpotQA and MATH-500, we show that accuracy gains from increasing the number of sampled reasoning paths are minimal – 0.4% on HotpotQA across 20 samples, and 1.6% on MATH-500 – while token costs scale nearly linearly with sample count. Critically, performance plateaued early and in some configurations declined at high sample counts, suggesting that additional paths introduce noise rather than signal when models already solve problems reliably. As inference costs rise with model scale, indiscriminate self-consistency is difficult to justify. We recommend reserving multi-path sampling for problems that demonstrably exceed a model's single-pass reliability.
Read the full abstract

Computation and Language · Cross-listed from cs.CV

Erasing 'Ugly' from the Internet: Propagation of the Beauty Myth in Text-Image Models

Tanvi Dinkar, Aiqi Jiang, Gavin Abercrombie et al. (+1 more)

Social media has exacerbated the promotion of Western beauty norms, leading to negative self-image, particularly in women and girls, and causing harm such as body dysmorphia. Increasingly content on the internet has been artificially generated, leading to concerns that these norms are being exaggerated. The aim of this work is to study how generative AI models may encode 'beauty' and erase 'ugliness', and discuss the implications of this for society. To investigate these aims, we create two image generation pipelines: a text-to-image model and a text-to-language model-to image model. We develop a structured beauty taxonomy which we use to prompt three language models (LMs) and two text-to-image models to cumulatively generate 5984 images using our two pipelines. We then recruit women and non-binary social media users to evaluate 1200 of the images through a Likert-scale within-subjects study. Participants show high agreement in their ratings. Our results show that 86.5% of generated images depicted people with lighter skin tones, 22% contained explicit content despite Safe for Work (SFW) training, and 74% were rated as being in a younger age demographic. In particular, the images of non-binary individuals were rated as both younger and more hypersexualised, indicating troubling intersectional effects. Notably, prompts encoded with 'negative' or 'ugly' beauty traits (such as "a wide nose") consistently produced higher Not SFW (NSFW) ratings regardless of gender. This work sheds light on the pervasive demographic biases related to beauty standards present in generative AI models – biases that are actively perpetuated by model developers, such as via negative prompting. We conclude by discussing the implications of this on society, which include pollution of the data streams and active erasure of features that do not fall inside the stereotype of what is considered beautiful by developers.
Read the full abstract

All authors Tanvi Dinkar, Aiqi Jiang, Gavin Abercrombie, Ioannis Konstas

Saturday 1 November

Computation and Language

Test-time Scaling of LLMs: A Survey from A Subproblem Structure Perspective

Zhuoyi Yang, Xu Guo, Tong Zhang et al. (+2 more)

With this paper, we survey techniques for improving the predictive accuracy of pretrained large language models by allocating additional compute at inference time. In categorizing test-time scaling methods, we place special emphasis on how a problem is decomposed into subproblems and on the topological organization of these subproblems whether sequential, parallel, or tree-structured. This perspective allows us to unify diverse approaches such as Chain-of-Thought, Branch-Solve-Merge, and Tree-of-Thought under a common lens. We further synthesize existing analyses of these techniques, highlighting their respective strengths and weaknesses, and conclude by outlining promising directions for future research
Read the full abstract

All authors Zhuoyi Yang, Xu Guo, Tong Zhang, Huijuan Xu, Boyang Li

Computation and Language

Cognitively-Inspired Episodic Memory Architectures for Accurate and Efficient Character AI

Rafael Arias Gonzalez and Steve DiPaola

Large language models show promise for embodying historical characters in dialogue systems, but existing approaches face a critical trade-off: simple retrieval-augmented generation produces shallow responses, while multi-stage reflection achieves depth at prohibitive latency. We present an architecture that resolves this tension through offline data augmentation and efficient parallel retrieval from structured episodic memory. Our system transforms biographical data into 1,774 enriched first-person memories with affective-semantic metadata, then employs two-stage retrieval achieving 0.52s prompt generation. Evaluation using LLM-as-judge and RAGAs metrics shows our approach achieves parity with traditional RAG on GPT-4 while significantly outperforming it on smaller models (GPT-3.5, GPT-3), suggesting particular value for resource-constrained deployments. Beyond dialogue, the structured memory enables novel visualization tools: spatiotemporal heatmaps, emotional trajectory analysis, and interactive path tracking, positioning the system as both a dialogue interface and research tool for biographical analysis. We use Van Gogh as a test case, but the architecture is generalizable to any historical figure with substantial textual records, offering a practical framework for educational, museum, and research applications requiring both accuracy and efficiency
Read the full abstract

Computation and Language

Data Analysis and Performance Evaluation of Simulation Deduction Based on LLMs

Shansi Zhang and Min Li

Data analysis and performance evaluation of simulation deduction plays a pivotal role in modern warfare, which enables military personnel to gain invaluable insights into the potential effectiveness of different strategies, tactics, and operational plans. Traditional manual analysis approach is time-consuming and limited by human errors. To enhance efficiency and accuracy, large language models (LLMs) with strong analytical and inferencing capabilities can be employed. However, high-quality analysis reports with well-structured formatting cannot be obtained through a single instruction input to the LLM. To tackle this issue, we propose a method that first decomposes the complex task into several sub-tasks and designs effective system prompts and user prompts for each sub-task. Multi-round interactions with the LLM incorporating self-check and reflection are then conducted to enable structured data extraction as well as multi-step analysis and evaluation. Furthermore, custom tools are defined and invoked to generate figures and compute metrics. We also design multiple report templates, each tailored to a specific application and input data type, ensuring their adaptability across a variety of scenarios. Extensive evaluation results demonstrate that the reports generated by our method exhibit higher quality, therefore obtaining higher scores than the baseline method.
Read the full abstract

Computation and Language

Retrieval-Augmented Generation of Pediatric Speech-Language Pathology vignettes: A Proof-of-Concept Study

Yilan Liu

Clinical vignettes are essential educational tools in speech-language pathology (SLP), but manual creation is time-intensive. While general-purpose large language models (LLMs) can generate text, they lack domain-specific knowledge, leading to hallucinations and requiring extensive expert revision. This study presents a proof-of-concept system integrating retrieval-augmented generation (RAG) with curated knowledge bases to generate pediatric SLP case materials. A multi-model RAG-based system was prototyped integrating curated domain knowledge with engineered prompt templates, supporting five commercial (GPT-4o, Claude 3.5 Sonnet, Gemini 2.5 Pro) and open-source (Llama 3.2, Qwen 2.5-7B) LLMs. Seven test scenarios spanning diverse disorder types and grade levels were systematically designed. Generated cases underwent automated quality assessment using a multi-dimensional rubric evaluating structural completeness, internal consistency, clinical appropriateness, and IEP goal/session note quality. This proof-of-concept demonstrates technical feasibility for RAG-augmented generation of pediatric SLP vignettes. Commercial models showed marginal quality advantages, but open-source alternatives achieved acceptable performance, suggesting potential for privacy-preserving institutional deployment. Integration of curated knowledge bases enabled content generation aligned with professional guidelines. Extensive validation through expert review, student pilot testing, and psychometric evaluation is required before educational or research implementation. Future applications may extend to clinical decision support, automated IEP goal generation, and clinical reflection training.
Read the full abstract

Computation and Language

Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generation

Song Wang, Zihan Chen, Peng Wang et al. (+5 more)

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by integrating external knowledge sources to address their limitations in accessing up-to-date or specialized information. A natural strategy to increase the likelihood of retrieving relevant information is to expand the number of retrieved documents. However, involving more documents could introduce significant noise, as many documents may be irrelevant or misleading, thereby reducing the overall accuracy of the generated responses. To overcome the challenge associated with handling a larger number of documents, we propose WinnowRAG, a novel RAG framework designed to systematically filter out noisy documents while preserving valuable content – a process we refer to as winnowing. WinnowRAG operates in two stages: In Stage I, we perform query-aware clustering to group similar documents and form distinct topic clusters. Each cluster is assigned to an LLM agent for generating a unique answer. In Stage II, we perform winnowing, wherein a critic LLM evaluates the outputs of multiple agents and iteratively separates useful documents from noisy ones. To retain useful documents when discarding agents, we propose two strategic merging techniques to ensure that only relevant knowledge is used for generating the final response. Crucially, WinnowRAG is model-agnostic and does not require any model fine-tuning, making it easily adaptable to various tasks. Extensive experiments on various realistic datasets demonstrate the effectiveness of WinnowRAG over state-of-the-art baselines.
Read the full abstract

All authors Song Wang, Zihan Chen, Peng Wang, Zhepei Wei, Zhen Tan, Yu Meng, Cong Shen, Jundong Li

Computation and Language

Cross-Lingual SynthDocs: A Large-Scale Synthetic Corpus for Any to Arabic OCR and Document Understanding

Haneen Al-Homoud, Asma Ibrahim, Murtadha Al-Jubran et al. (+5 more)

Cross-Lingual SynthDocs is a large-scale synthetic corpus designed to address the scarcity of Arabic resources for Optical Character Recognition (OCR) and Document Understanding (DU). The dataset comprises over 2.5 million of samples, including 1.5 million textual data, 270K fully annotated tables, and hundred thousands of real data based charts. Our pipeline leverages authentic scanned backgrounds, bilingual layouts, and diacritic aware fonts to capture the typographic and structural complexity of Arabic documents. In addition to text, the corpus includes variety of rendered styles for charts and tables. Finetuning Qwen-2.5-VL on SynthDocs yields consistent improvements in Word Error Rate (WER) and Character Error Rate (CER) in terms of OCR across multiple public Arabic benchmarks, Tree-Edit Distance Similarity (TEDS) and Chart Extraction Score (CharTeX) improved as well in other modalities. SynthDocs provides a scalable, visually realistic resource for advancing research in multilingual document analysis.
Read the full abstract

All authors Haneen Al-Homoud, Asma Ibrahim, Murtadha Al-Jubran, Fahad Al-Otaibi, Yazeed Al-Harbi, Daulet Toibazar, Kesen Wang, Pedro J. Moreno

Computation and Language

multiMentalRoBERTa: A Fine-tuned Multiclass Classifier for Mental Health Disorder

K M Sajjadul Islam, John Fields and Praveen Madiraju

The early detection of mental health disorders from social media text is critical for enabling timely support, risk assessment, and referral to appropriate resources. This work introduces multiMentalRoBERTa, a fine-tuned RoBERTa model designed for multiclass classification of common mental health conditions, including stress, anxiety, depression, post-traumatic stress disorder (PTSD), suicidal ideation, and neutral discourse. Drawing on multiple curated datasets, data exploration is conducted to analyze class overlaps, revealing strong correlations between depression and suicidal ideation as well as anxiety and PTSD, while stress emerges as a broad, overlapping category. Comparative experiments with traditional machine learning methods, domain-specific transformers, and prompting-based large language models demonstrate that multiMentalRoBERTa achieves superior performance, with macro F1-scores of 0.839 in the six-class setup and 0.870 in the five-class setup (excluding stress), outperforming both fine-tuned MentalBERT and baseline classifiers. Beyond predictive accuracy, explainability methods, including Layer Integrated Gradients and KeyBERT, are applied to identify lexical cues that drive classification, with a particular focus on distinguishing depression from suicidal ideation. The findings emphasize the effectiveness of fine-tuned transformers for reliable and interpretable detection in sensitive contexts, while also underscoring the importance of fairness, bias mitigation, and human-in-the-loop safety protocols. Overall, multiMentalRoBERTa is presented as a lightweight, robust, and deployable solution for enhancing support in mental health platforms.
Read the full abstract

Computation and Language

Do Methods to Jailbreak and Defend LLMs Generalize Across Languages?

Berk Atil, Rebecca J. Passonneau and Fred Morstatter

Large language models (LLMs) undergo safety alignment after training and tuning, yet recent work shows that safety can be bypassed through jailbreak attacks. While many jailbreaks and defenses exist, their cross-lingual generalization remains underexplored. This paper presents the first systematic multilingual evaluation of jailbreaks and defenses across ten languages – spanning high-, medium-, and low-resource languages – using six LLMs on HarmBench and AdvBench. We assess two jailbreak types: logical-expression-based and adversarial-prompt-based. For both types, attack success and defense robustness vary across languages: high-resource languages are safer under standard queries but more vulnerable to adversarial ones. Simple defenses can be effective, but are language- and model-dependent. These findings call for language-aware and cross-lingual safety benchmarks for LLMs.
Read the full abstract

Computation and Language

Do You Know About My Nation? Investigating Multilingual Language Models' Cultural Literacy Through Factual Knowledge

Eshaan Tanwar, Anwoy Chatterjee, Michael Saxon et al. (+3 more)

Most multilingual question-answering benchmarks, while covering a diverse pool of languages, do not factor in regional diversity in the information they capture and tend to be Western-centric. This introduces a significant gap in fairly evaluating multilingual models' comprehension of factual information from diverse geographical locations. To address this, we introduce XNationQA for investigating the cultural literacy of multilingual LLMs. XNationQA encompasses a total of 49,280 questions on the geography, culture, and history of nine countries, presented in seven languages. We benchmark eight standard multilingual LLMs on XNationQA and evaluate them using two novel transference metrics. Our analyses uncover a considerable discrepancy in the models' accessibility to culturally specific facts across languages. Notably, we often find that a model demonstrates greater knowledge of cultural information in English than in the dominant language of the respective culture. The models exhibit better performance in Western languages, although this does not necessarily translate to being more literate for Western countries, which is counterintuitive. Furthermore, we observe that models have a very limited ability to transfer knowledge across languages, particularly evident in open-source models.
Read the full abstract

All authors Eshaan Tanwar, Anwoy Chatterjee, Michael Saxon, Alon Albalak, William Yang Wang, Tanmoy Chakraborty

Computation and Language · Cross-listed from cs.AI

Leveraging Multi-Agent System (MAS) and Fine-Tuned Small Language Models (SLMs) for Automated Telecom Network Troubleshooting

Chenhua Shi, Bhavika Jalli, Gregor Macdonald et al. (+4 more)

Telecom networks are rapidly growing in scale and complexity, making effective management, operation, and optimization increasingly challenging. Although Artificial Intelligence (AI) has been applied to many telecom tasks, existing models are often narrow in scope, require large amounts of labeled data, and struggle to generalize across heterogeneous deployments. Consequently, network troubleshooting continues to rely heavily on Subject Matter Experts (SMEs) to manually correlate various data sources to identify root causes and corrective actions. To address these limitations, we propose a Multi-Agent System (MAS) that employs an agentic workflow, with Large Language Models (LLMs) coordinating multiple specialized tools for fully automated network troubleshooting. Once faults are detected by AI/ML-based monitors, the framework dynamically activates agents such as an orchestrator, solution planner, executor, data retriever, and root-cause analyzer to diagnose issues and recommend remediation strategies within a short time frame. A key component of this system is the solution planner, which generates appropriate remediation plans based on internal documentation. To enable this, we fine-tuned a Small Language Model (SLM) on proprietary troubleshooting documents to produce domain-grounded solution plans. Experimental results demonstrate that the proposed framework significantly accelerates troubleshooting automation across both Radio Access Network (RAN) and Core network domains.
Read the full abstract

All authors Chenhua Shi, Bhavika Jalli, Gregor Macdonald, John Zou, Wanlu Lei, Mridul Jain, Joji Philip

Computation and Language · Cross-listed from cs.AI

DTS: Enhancing Large Reasoning Models via Decoding Tree Sketching

Zicheng Xu, Xiuyi Lou, Guanchu Wang et al. (+6 more)

Large Reasoning Models (LRMs) achieve remarkable inference-time improvements through parallel thinking. However, existing methods rely on redundant sampling of reasoning trajectories, failing to effectively explore the reasoning space to uncover high-quality solutions. To address these limitations, we propose Decoding Tree Sketching (DTS), a plug-and-play decoding framework for structural multi-trajectory exploration and reasoning selection. For reasoning exploration, DTS sketches a backbone tree of the reasoning space by selectively branching at decision tokens. For reasoning selection, guided by length-accuracy anti-correlation, DTS designs an early termination to prioritize short and reliable trajectories during decoding. Experimental results across four LRMs and datasets demonstrate that DTS significantly enhances accuracy by 14% and reduces repetitive generation by 8% on average. Notably, DTS enables smaller models to outperform larger models with 10$\times$ the size, highlighting its potential to strengthen reasoning capabilities.
Read the full abstract

All authors Zicheng Xu, Xiuyi Lou, Guanchu Wang, Yu-Neng Chuang, Feng Luo, Guangyao Zheng, Alexander S. Szalay, Zirui Liu, Vladimir Braverman

Computation and Language

Modeling the Construction of a Literary Archetype: The Case of the Detective Figure in French Literature

Jean Barré, Olga Seminck, Antoine Bourgois et al. (+1 more)

This research explores the evolution of the detective archetype in French detective fiction through computational analysis. Using quantitative methods and character-level embeddings, we show that a supervised model is able to capture the unity of the detective archetype across 150 years of literature, from M. Lecoq (1866) to Commissaire Adamsberg (2017). Building on this finding, the study demonstrates how the detective figure evolves from a secondary narrative role to become the central character and the "reasoning machine" of the classical detective story. In the aftermath of the Second World War, with the importation of the hardboiled tradition into France, the archetype becomes more complex, navigating the genre's turn toward social violence and moral ambiguity.
Read the full abstract

All authors Jean Barré, Olga Seminck, Antoine Bourgois, Thierry Poibeau