Peer Revenue Publish or profit

Papers

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

Computer Science Computation and Language

cs.CL Watch Computation and Language

Tuesday 5 May

Computation and Language · Cross-listed from cs.AI

Agentic-imodels: Evolving agentic interpretability tools via autoresearch

Chandan Singh, Yan Shuo Tan, Weijia Xu et al. (+4 more)

Agentic data science (ADS) systems are rapidly improving their capability to autonomously analyze, fit, and interpret data, potentially moving towards a future where agents conduct the vast majority of data-science work. However, current ADS systems use statistical tools designed to be interpretable by humans, rather than interpretable by agents. To address this, we introduce Agentic-imodels, an agentic autoresearch loop that evolves data-science tools designed to be interpretable by agents. Specifically, it develops a library of scikit-learn-compatible regressors for tabular data that are optimized for both predictive performance and a novel LLM-based interpretability metric. The metric measures a suite of LLM-graded tests that probe whether a fitted model's string representation is "simulatable" by an LLM, i.e. whether the LLM can answer questions about the model's behavior by reading its string output alone. We find that the evolved models jointly improve predictive performance and agent-facing interpretability, generalizing to new datasets and new interpretability tests. Furthermore, these evolved models improve downstream end-to-end ADS, increasing performance for Copilot CLI, Claude Code, and Codex on the BLADE benchmark by up to 73%
Read the full abstract

All authors Chandan Singh, Yan Shuo Tan, Weijia Xu, Zelalem Gero, Weiwei Yang, Michel Galley, Jianfeng Gao

Computation and Language

Natural Language Processing: A Comprehensive Practical Guide from Tokenisation to RLHF

Mullosharaf K. Arabov

This preprint presents a systematic, research-oriented practicum that guides the reader through the entire modern NLP pipeline — from tokenisation and vectorisation to fine tuning of large language models, retrieval augmented generation, reinforcement learning from human feedback, prompt engineering, model compression, and multimodal systems. Seventeen hands-on sessions combine concise theory with detailed implementation plans, formalised evaluation metrics, and transparent assessment criteria. The work is not a conventional textbook: it is designed as a reproducible research artefact where every session requires publishing code, models, and reports in public repositories. All experiments are conducted on a single evolving corpus, and the work advocates open weight models over commercial APIs, with special attention to the Hugging Face ecosystem. The material is enriched by original research on low resource languages, incorporating linguistic resources for Tajik and Tatar — subword tokenisers, embeddings, lexical databases, and transliteration benchmarks — demonstrating how modern NLP can be adapted to data scarce environments. The practicum also covers advanced topics including AI agents, multi-agent systems, LLMOps, and efficient inference, preparing students for both research and industrial deployment. Designed for senior undergraduates, graduate students, and practising developers seeking to implement, compare, and deploy methods from classical ML to state of the art multimodal and agent-based systems.
Read the full abstract

Computation and Language

TriBench-Ko: Evaluating LLM Risks in Judicial Workflows

Haesung Lee, Gyubin Choi, Eun-Ju Lee et al. (+5 more)

Large language models (LLMs) are increasingly integrated into legal workflows. However, existing benchmarks primarily address proxy tasks, such as bar examination performance or classification, which fail to capture the performance and risks inherent in day-to-day judicial processes. To address this, we publicly release TriBench-Ko, a Korean benchmark designed to evaluate potential deployment risks of LLMs within the context of verified judicial task requirements. It covers four core tasks: jurisprudence summarization, precedent retrieval, legal issue extraction, and evidence analysis. It jointly assesses model behavior across multiple deployment risk categories, including inaccuracy (hallucination, omission, statutory misapplication), biases (demographic, overcompliance), inconsistencies (prompt sensitivity, non-determinism), and adjudicative overreach. Each item is structured to systematically assess both task performance and a specific risk type based on real judicial decisions. Our evaluation of a range of contemporary LLMs reveals that many models frequently manifest significant risks, most notably struggling with precedent retrieval and failing to capture critical legal information. We provide a comprehensive diagnosis of these LLMs and pinpoint critical areas where LLM-generated outputs in judicial contexts necessitate rigorous inspection and caution. Our dataset and code are available at https://github.com/holi-lab/TriBench-Ko
Read the full abstract

All authors Haesung Lee, Gyubin Choi, Eun-Ju Lee, So-Min Lee, Youkang Ko, Dogyoon Lim, Sung-Kyoung Jang, Yohan Jo

Computation and Language · Cross-listed from cs.LG

Task Vector Geometry Underlies Dual Modes of Task Inference in Transformers

Hao Yan, Haolin Yang and Yiqiao Zhong

Transformers are effective at inferring the latent task from context via two inference modes: recognizing a task seen during training, and adapting to a novel one. Recent interpretability studies have identified from middle-layer representations task-specific directions, or task vectors, that steer model behavior. However, a lack of rigorous foundations hinders connecting internal representations to external model behavior: existing work fails to explain how task-vector geometry is shaped by the training distribution, and what geometry enables out-of-distribution (OOD) generalization. In this paper, we study these questions in a controlled synthetic setting by training small transformers from scratch on latent-task sequence distributions, which allows a principled mathematical characterization. We show that two inference modes can coexist within a single model. In-distribution behavior is governed by Bayesian task retrieval, implemented internally through convex combinations of learned task vectors. OOD behavior, by contrast, arises through extrapolative task learning, whose representations occupy a subspace nearly orthogonal to the task-vector subspace. Taken together, our results suggest that task-vector geometry, training distributions, and generalization behaviors are closely related.
Read the full abstract

Computation and Language

Benchmarking Parameter-Efficient Fine-Tuning of Large Language Models for Low-Resource Tajik Text Generation with the Tajik Web Corpus

Mullosharaf K. Arabov

We release the Tajik Web Corpus (319k docs, 1.11B chars) and benchmark generative LLMs on prompt continuation in Tajik, a low-resource Cyrillic-script language. Seventeen configurations across nine architectures are evaluated under three fine-tuning strategies: full fine-tuning, LoRA, and QLoRA (ranks 8 and 16). Because perplexity is not directly comparable across model families with different tokenizers, generation quality is assessed through perplexity interpreted within each family, complemented by qualitative analysis performed by a native Tajik speaker. Computational cost is measured via GPU memory and training time. The best quality-cost trade-off is achieved by Mistral 7B with QLoRA rank 8: perplexity 5.11 (within its tokenizer family), coherent Tajik output confirmed by the native speaker, 14.21 GB GPU memory, and approximately 33 minutes of training. Increasing the rank to 16 yields a negligible improvement for Mistral (perplexity 5.03, pairwise p > 0.05) while consuming about 1 GB more memory. Full fine-tuning of small GPT-2 models obtains lower numeric perplexity but leads to catastrophic forgetting (English or gibberish output); in contrast, QLoRA preserves multilingual pretrained knowledge and generates meaningful Tajik text. Encoder-only models perform worst (perplexity approximately 59), confirming their unsuitability for autoregressive generation. To our knowledge, this is the first systematic PEFT benchmark for Tajik text generation. Practical recommendations include using Mistral 7B with QLoRA r=8, avoiding full fine-tuning of small GPT-2 models, and adopting the released corpus and benchmark.
Read the full abstract

Computation and Language

Segmenting Human-LLM Co-authored Text via Change Point Detection

Mengchu Li, Jin Zhu, Jinglai Li et al. (+1 more)

The rise of large language models (LLMs) has created an urgent need to distinguish between human-written and LLM-generated text to ensure authenticity and societal trust. Existing detectors typically provide a binary classification for an entire passage; however, this is insufficient for human–LLM co-authored text, where the objective is to localize specific segments authored by humans or LLMs. To bridge this gap, we propose algorithms to segment text into human- and LLM-authored pieces. Our key observation is that such a segmentation task is conceptually similar to classical change point detection in time-series analysis. Leveraging this analogy, we adapt change point detection to LLM-generated text detection, develop a weighted algorithm and a generalized algorithm to accommodate heterogeneous detection score variability, and establish the minimax optimality of our procedure. Empirically, we demonstrate the strong performance of our approach against a wide range of existing baselines. The python implementation of our proposal is available at https://github.com/Mamba413/DetectLLMSegmentation.
Read the full abstract

All authors Mengchu Li, Jin Zhu, Jinglai Li, Chengchun Shi

Computation and Language

Rose-SQL: Role-State Evolution Guided Structured Reasoning for Multi-Turn Text-to-SQL

Le Zhou, Feng Yao, Fengcai Qiao et al. (+3 more)

Recent advances in Large Reasoning Models (LRMs) trained with Long Chain-of-Thought have demonstrated remarkable capabilities in code generation and mathematical reasoning. However, their potential in multi-turn Text-to-SQL tasks remains largely underexplored. Existing approaches typically rely on unstable API-based inference or require expensive fine-tuning on small-scale models. In this work, we present Rose-SQL, a training-free framework that leverages small-scale LRMs through in-context learning to enable accurate context-dependent parsing. We introduce the Role-State, a fine-grained representation that bridges the structural gap between schema linking and SQL generation by serving as a structural blueprint. To handle conversational dependencies, Rose-SQL traces the evolution of Role-State through historical context via structural isomorphism checks, guiding the model to infer the possible SQL composition for the current question through verified interaction trajectories. Experiments on the SParC and CoSQL benchmarks show that, within the Qwen3 series, Rose-SQL outperforms in-context learning baselines at the 4B scale and substantially surpasses state-of-the-art fine-tuned models at the 8B and 14B scales, while showing consistent gains on additional reasoning backbones.
Read the full abstract

All authors Le Zhou, Feng Yao, Fengcai Qiao, Bo Xu, Fangyuan Wang, Boyan Xu

Computation and Language

SAM-NER: Semantic Archetype Mediation for Zero-Shot Named Entity Recognition

Ruichu Cai, Juntao Gan, Miao Mai et al. (+2 more)

Zero-shot Named Entity Recognition (ZS-NER) remains brittle under domain and schema shifts, where unseen label definitions often misalign with a large language model's (LLM's) intrinsic semantic organization. As a result, directly mapping entity mentions to fine-grained target labels can induce systematic semantic drift, especially when target schemas are novel or semantically overlapping. We propose SAM-NER, a three-stage framework based on Semantic Archetype Mediation that stabilizes cross-domain transfer through an intermediate, domain-invariant archetype space. SAM-NER: (i) performs Entity Discovery via cooperative extraction and consensus-based denoising to obtain high-coverage, high-fidelity entity spans; (ii) conducts Abstract Mediation by projecting entities into a compact set of universal semantic archetypes distilled from high-level ontological abstractions; and (iii) applies Semantic Calibration to resolve archetype-level predictions into target-domain types through constrained, definition-aligned inference with a frozen LLM. Experiments on the CrossNER benchmark show that SAM-NER consistently outperforms strong prior ZS-NER baselines in cross-domain settings. Our implementation will be open-sourced at https://github.com/DMIRLAB-Group/SAM-NER.
Read the full abstract

All authors Ruichu Cai, Juntao Gan, Miao Mai, Zhifeng Hao, Boyan Xu

Computation and Language

SERE: Structural Example Retrieval for Enhancing LLMs in Event Causality Identification

Zhifeng Hao, Zhongjie Chen, Junhao Lu et al. (+5 more)

Event Causality Identification (ECI) requires models to determine whether a given pair of events in a context exhibits a causal relationship. While Large Language Models (LLMs) have demonstrated strong performance across various NLP tasks, their effectiveness in ECI remains limited due to biases in causal reasoning, often leading to overprediction of causal relationships (causal hallucination). To mitigate these issues and enhance LLM performance in ECI, we propose SERE, a structural example retrieval framework that leverages LLMs' few-shot learning capabilities. SERE introduces an innovative retrieval mechanism based on three structural concepts: (i) Conceptual Path Metric, which measures the conceptual relationship between events using edit distance in ConceptNet; (ii) Syntactic Metric, which quantifies structural similarity through tree edit distance on syntactic trees; and (iii) Causal Pattern Filtering, which filters examples based on predefined causal structures using LLMs. By integrating these structural retrieval strategies, SERE selects more relevant examples to guide LLMs in causal reasoning, mitigating bias and improving accuracy in ECI tasks. Extensive experiments on multiple ECI datasets validate the effectiveness of SERE. The source code is publicly available at https://github.com/DMIRLAB-Group/SERE.
Read the full abstract

All authors Zhifeng Hao, Zhongjie Chen, Junhao Lu, Shengyin Yu, Guimin Hu, Keli Zhang, Ruichu Cai, Boyan Xu

Computation and Language

A Comprehensive Analysis of Tokenization and Self-Supervised Learning in End-to-End Automatic Speech Recognition applied on French Language

Thibault Bañeras-Roux, Mickael Rouvier, Jane Wottawa et al. (+1 more)

The performance of end-to-end automatic speech recognition (ASR) systems enables their increasing integration into numerous applications. While there are various benefits to such speech-to-text systems, the choice of hyperparameters and models plays a crucial role in their performance. Typically, these choices are determined by considering only the character (CER) and/or word error rate (WER) metrics. However, it has been shown in several studies that these metrics are largely incomplete and fail to adequately describe the downstream application of automatic transcripts. In this paper, we conduct a qualitative study on the French language that investigates the impact of subword tokenization algorithms and self-supervised learning models from different linguistic and acoustic perspectives, using a comprehensive set of evaluation metrics.
Read the full abstract

All authors Thibault Bañeras-Roux, Mickael Rouvier, Jane Wottawa, Richard Dufour

Computation and Language

A Paradigm for Interpreting Metrics and Identifying Critical Errors in Automatic Speech Recognition

Thibault Bañeras-Roux, Mickael Rouvier, Jane Wottawa et al. (+1 more)

The most commonly used metrics for evaluating automatic speech transcriptions, namely Word Error Rate (WER) and Character Error Rate (CER), have been heavily criticized for their poor correlation to human perception and their inability to take into account linguistic and semantic information. While metric-based embeddings, seeking to approximate human perception, have been proposed, their scores remain difficult to interpret, unlike WER and CER. In this article, we overcome this problem by proposing a paradigm that consists in incorporating a chosen metric into it in order to obtain an equivalent of the error rate: a Minimum Edit Distance (minED). This approach parallels transcription errors with their human perception, also allowing an original study of the severity of these errors from a human perspective.
Read the full abstract

All authors Thibault Bañeras-Roux, Mickael Rouvier, Jane Wottawa, Richard Dufour

Computation and Language

Annotation Quality in Aspect-Based Sentiment Analysis: A Case Study Comparing Experts, Students, Crowdworkers, and Large Language Model

Niklas Donhauser, Jakob Fehle, Nils Constantin Hellwig et al. (+3 more)

Aspect-Based Sentiment Analysis (ABSA) enables fine-grained opinion analysis by identifying sentiments toward specific aspects or targets within a text. While ABSA has been widely studied for English, research on other languages such as German remains limited, largely due to the lack of high-quality annotated datasets. This paper examines how different annotation sources influence the development of German ABSA. To this end, an existing dataset is re-annotated by experts to establish a ground truth, which serves as a reference for evaluating annotations produced by students, crowdworkers, Large Language Models (LLMs), and experts. Annotation quality is compared using Inter-Annotator Agreement (IAA) and its impact on downstream model performance for different ABSA subtasks. The evaluation focuses on Aspect Category Sentiment Analysis (ACSA) and Target Aspect Sentiment Detection (TASD). We apply State-of-the-Art (SOTA) methods for ABSA, including BERT-, T5-, and LLaMA-based approaches to assess performance differences, spanning fine-tuning and in-context learning with instruction prompts. The findings provide practical insights into trade-offs between annotation reliability and efficiency, offering guidance for dataset construction in under-resourced Natural Language Processing (NLP) scenarios.
Read the full abstract

All authors Niklas Donhauser, Jakob Fehle, Nils Constantin Hellwig, Markus Weinberger, Udo Kruschwitz, Christian Wolff

Computation and Language

BIT.UA-AAUBS at ArchEHR-QA 2026: Evaluating Open-Source and Proprietary LLMs via Prompting in Low-Resource QA

Richard A. A. Jonker, Alexander Christiansen, Alexandros Maniatis et al. (+4 more)

This paper presents the joint participation of the BIT.UA and AAUBS groups in the ArchEHR-QA 2026 shared task, which focuses on clinical question answering and evidence grounding in a low-resource setting. Due to the absence of training data and the strict data privacy constraints inherent to the healthcare domain (e.g. GDPR), we investigate the capabilities of Large Language Models (LLMs) without weight updates. We evaluate several state-of-the-art proprietary models and locally deployable open-source alternatives using various prompt engineering strategies, including task decomposition, Chain-of-Thought, and in-context learning. Furthermore, we explore majority voting and LLM-as-a-judge ensembling techniques to maximize predictive robustness. Our results demonstrate that while proprietary models exhibit strong resilience to prompt variations, domain-adapted open-source models (such as MedGemma 3 27B) achieve highly competitive performance when paired with the right prompt. Overall, our prompt-based approach proved highly effective, securing 1st place in Subtask 4 (evidence citation alignment) and 3rd place in Subtask 3 (patient-friendly answer generation). All code, results, and prompts are available on our GitHub repository: https://github.com/bioinformatics-ua/ArchEHR-QA-2026.
Read the full abstract

All authors Richard A. A. Jonker, Alexander Christiansen, Alexandros Maniatis, Rúben Garrido, Rogério Braunschweiger de Freitas Lima, Roman Jurowetzki, Sérgio Matos

Computation and Language · Cross-listed from cs.AI

Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies

Zirui Tang, Xuanhe Zhou, Yumou Liu et al. (+19 more)

Workspace learning requires AI agents to identify, reason over, exploit, and update explicit and implicit dependencies among heterogeneous files in a worker's workspace, enabling them to complete both routine and advanced tasks effectively. Despite its importance, existing relevant benchmarks largely evaluate agents on pre-specified or synthesized files with limited real-world dependencies, leaving workspace-level evaluation underexplored. To this end, we introduce Workspace-Bench, a benchmark for evaluating AI agents on Workspace Learning involving Large-Scale File Dependencies. We construct realistic workspaces with 5 worker profiles, 74 file types, 20,476 files (up to 20GB) and curate 388 tasks, each with its own file dependency graph, evaluated across 7,399 total rubrics that require cross-file retrieval, contextual reasoning, and adaptive decision-making. We further provide Workspace-Bench-Lite, a 100-task subset that preserves the benchmark distribution while reducing evaluation costs by about 70%. We evaluate 4 popular agent harnesses and 7 foundation models. Experimental results show that current agents remain far from reliable workspace learning, where the best reaches only about 60%, substantially below the human result of 80.7%, and the average performance across agents is only 43.3%.
Read the full abstract

All authors Zirui Tang, Xuanhe Zhou, Yumou Liu, Linchun Li, Yukai Wu, Weizheng Wang, Hongzhang Huang, Wei Zhou, Jun Zhou, Jiachen Song, Shaoli Yu, Jinqi Wang, Zihang Zhou, Hongyi Zhou, Yuting Lv, Jinyang Li, Jiashuo Liu, Ruoyu Chen, Chunwei Liu, GuoLiang Li, Jihua Kang, Fan Wu

Computation and Language

AfriVox-v2: A Domain-Verticalized Benchmark for In-the-Wild African Speech Recognition

Busayo Awobade, Gabrial Zencha Ashungafac and Tobi Olatunji

Recent large language models (LLMs) show strong speech recognition and translation capabilities for high-resource languages. However, African languages remain dramatically underrepresented in benchmarks, limiting their practical use in low-resource settings. While early benchmarks tested African languages and accents, they lacked exhaustive real-world noise and granular domain evaluations. We present AfriVox-v2, a comprehensive benchmark designed to test speech models under realistic African deployment conditions. AfriVox-v2 introduces "in the wild" unscripted audio for all supported languages. We also introduce strict domain verticalization, evaluating model accuracy across ten sectors including government, finance, health, and agriculture and conducting targeted tests on numbers and named entities. Finally, we benchmark a new generation of speech models, including Sahara-v2, Gemini 3 Flash, and the Omnilingual CTC models. Our results expose the true generalization gap of modern speech models in specialized, noisy African contexts and provide a reliable blueprint for developers building localized voice AI.
Read the full abstract

Computation and Language

PatRe: A Full-Stage Office Action and Rebuttal Generation Benchmark for Patent Examination

Qiyao Wang, Xinyi Chen, Longze Chen et al. (+4 more)

Patent examination is a complex, multi-stage process requiring both technical expertise and legal reasoning, increasingly challenged by rising application volumes. Prior benchmarks predominantly view patent examination as discriminative classification or static extraction, failing to capture its inherently interactive and iterative nature, similar to the peer review and rebuttal process in academic publishing. In this paper, we introduce PatRe, the first benchmark that models the full patent examination lifecycle, including Office Action generation and applicant rebuttal. PatRe comprises 480 real-world cases and supports both oracle and retrieval-simulated evaluation settings. Our benchmark reframes patent examination as a dynamic, multi-turn process of justification and response. Extensive experiments across various LLMs reveal critical insights into model performance, including differences between proprietary and open-source models, as well as task asymmetries between examiner analysis and applicant-side rebuttal. These findings highlight both the potential and current limitations of LLMs in modeling complex, real-world legal reasoning and technical novelty judgment in patent examination. We release our code and dataset to facilitate future research on patent examination modeling.
Read the full abstract

All authors Qiyao Wang, Xinyi Chen, Longze Chen, Hongbo Wang, Hamid Alinejad-Rokny, Yuan Lin, Min Yang

Computation and Language

SURE-RAG: Sufficiency and Uncertainty-Aware Evidence Verification for Selective Retrieval-Augmented Generation

Jingxi Qiu, Zeyu Han and Cheng Huang

Retrieval-augmented generation (RAG) grounds answers in retrieved passages, yet relevance does not guarantee sufficiency: a topical passage may still fail to justify the answer. We study evidence sufficiency verification for selective RAG answering, in which a verifier receives a question, a candidate answer, and retrieved evidence and decides whether the evidence supports, refutes, or is insufficient for the answer, answering only when support is established. We present SURE-RAG, an aggregation protocol that treats evidence sufficiency as a set-level property: missing hops and unresolved conflicts cannot be detected by scoring passages independently. A shared claim-evidence verifier produces a local relation distribution for each (claim, passage) pair, which SURE-RAG aggregates into four interpretable answer-level feature blocks (coverage, relation strength, uncertainty, and retrieval), producing a three-way decision and an auditable selective score. We evaluate on HotpotQA-RAG v3, a controlled multi-hop benchmark, under an artifact-aware protocol (shortcut baselines, counterfactual swaps, no-oracle checks, and GPT-4o audits). Calibrated SURE-RAG attains 0.9075 Macro-F1 (raw 0.8951 +/- 0.0069), well above DeBERTa mean-pooling (0.6516) and a GPT-4o judge (0.7284), and on par with a strong concat cross-encoder (0.8888 +/- 0.0109) while remaining fully auditable. At 30% coverage, risk falls from 0.2588 to 0.1642, a 37% relative reduction. As a boundary-mapping experiment, we contrast SURE-RAG with GPT-4o on HaluBench unsafe detection: the ranking reverses (0.3343 vs. 0.7389 unsafe-F1), indicating that controlled sufficiency verification and natural hallucination detection are distinct problems.
Read the full abstract

Computation and Language

Revisiting Graph-Tokenizing Large Language Models: A Systematic Evaluation of Graph Token Understanding

Zhongjian Zhang, Yue Yu, Mengmei Zhang et al. (+3 more)

The remarkable success of large language models (LLMs) has motivated researchers to adapt them as universal predictors for various graph tasks. As a widely recognized paradigm, Graph-Tokenizing LLMs (GTokenLLMs) compress complex graph data into graph tokens and treat them as prefix tokens for querying LLMs, leading many to believe that LLMs can understand graphs more effectively and efficiently. In this paper, we challenge this belief: Do GTokenLLMs fully understand graph tokens in the natural-language embedding space? Motivated by this question, we formalize a unified framework for GTokenLLMs and propose an evaluation pipeline, GTEval, to assess graph-token understanding via instruction transformations at the format and content levels. We conduct extensive experiments on 6 representative GTokenLLMs with GTEval. The primary findings are as follows: (1) Existing GTokenLLMs do not fully understand graph tokens. They exhibit over-sensitivity or over-insensitivity to instruction changes, and rely heavily on text for reasoning; (2) Although graph tokens preserve task-relevant graph information and receive attention across LLM layers, their utilization varies across models and instruction variants; (3) Additional instruction tuning can improve performance on the original and seen instructions, but it does not fully address the challenge of graph-token understanding, calling for further improvement.
Read the full abstract

All authors Zhongjian Zhang, Yue Yu, Mengmei Zhang, Junping Du, Xiao Wang, Chuan Shi

Computation and Language

Rational Communication Shapes Morphological Composition

Fengyuan Yang, Yongqian Peng, Yuxi Ma et al. (+2 more)

Human languages expand vocabularies by combining existing morphemes rather than inventing arbitrary forms. Communicative efficiency shapes lexical systems at multiple levels (Gibson et al., 2019), yet morphological composition – combining morphemes through compounding or affixation – has rarely been modeled as a historically situated speaker choice among competing morpheme sequences, leaving unanswered why a language settles on one morpheme combination over other plausible alternatives. We ask whether a trade-off between listener recoverability and speaker production cost can predict attested compositions over contemporaneously available alternatives. Here we show, within the Rational Speech Act (RSA) framework (Frank & Goodman, 2012; Goodman & Frank, 2016) using a time-indexed lexicon constructed from Corpus of Historical American English (COHA) and Corpus of Contemporary American English (COCA), that across 4323 naturally occurring English compounds and derivations spanning 1820–2019, attested compositions are systematically ranked above unattested alternatives generated from contemporaneously available morphemes. Models integrating semantic informativeness with production cost outperform semantic-only and cost-only baselines on Mean Reciprocal Rank (MRR) and top-k accuracy (Acc@k), with the advantage of the Pragmatic Speaker model ($S_1$) over the semantic-only baseline growing as the candidate set expands, where meaning alone leaves morphological choice underdetermined. These findings suggest that lexicalization reflects a communicative trade-off between expressiveness and efficiency, extending rational accounts of communication from utterance-level choice to the internal structure of words.
Read the full abstract

All authors Fengyuan Yang, Yongqian Peng, Yuxi Ma, Chenheng Xu, Yixin Zhu

Computation and Language

CuraView: A Multi-Agent Framework for Medical Hallucination Detection with GraphRAG-Enhanced Knowledge Verification

Severin Ye, Xiao Kong, Xiaopeng He et al. (+2 more)

Discharge summaries require extracting critical information from lengthy electronic health records (EHRs), a process that is labor-intensive when performed manually. Large language models (LLMs) can improve generation efficiency; however, they are prone to producing faithfulness hallucinations, statements that contradict source records, posing direct risks to patient safety. To address this, we present CuraView, a multi-agent framework for sentence-level detection and evidence-grounded explanation of faithfulness hallucinations in discharge summaries. CuraView constructs a GraphRAG-based knowledge graph from patient-level EHRs and implements a closed-loop generation-detection pipeline with sentence-level evidence retrieval and classification spanning four evidence grades from strong support to direct contradiction (E1-E4), yielding structured and interpretable evidence chains. We evaluate CuraView on a subset of 250 patients from the Discharge-Me benchmark, with 50 patients held out for testing. Our fine-tuned Qwen3-14B detection model achieves an F1 of 0.831 on the safety-critical E4 metric (90.9% recall, 76.5% precision) and an F1 of 0.823 on E3+E4, representing a 50.0% relative improvement over the base model and outperforming RAGTruth-style and QAGS-style baselines. These results demonstrate that evidence-chain-based graph retrieval verification substantially improves the factual reliability of clinical documentation, while simultaneously producing reusable annotated datasets for downstream model training and distillation.
Read the full abstract

All authors Severin Ye, Xiao Kong, Xiaopeng He, Guangsu Yan, Dongsuk Oh

Computation and Language

Auditing Stealth Sycophancy in Mental-Health Dialogue: Structured Clinical-State Diagnostics and Clean Matched Benchmarks

Tianze Han, Beining Xu, Hanbo Zhang et al. (+1 more)

Mental-health dialogue models are increasingly evaluated by AI-based evaluators, yet these evaluators often treat surface empathy, supportiveness, or fluency as evidence of safety. In this paper, we study a hidden failure mode that we call implicit sycophancy: a response may appear empathetic while implicitly reinforcing catastrophizing, avoidance, hopeless prediction, or CBT-style labeling. To examine this problem, we introduce a diagnostic benchmark for implicit-sycophancy detection, built from three representative mental-health dialogue sources covering everyday peer support, counseling-style emotional support, and crisis-oriented interaction, and further construct a leakage-audited clean single-response matched benchmark with 500 contexts and 1,500 matched response windows. We then propose Dynamic Emotional Signature Graphs (DESG), a structured offline audit framework that separates LLM-based state extraction from final scoring and evaluates clinical direction through semantic, affective, and cognitive-distortion state transitions rather than free-form LLM judgment. Unlike metadata, surface-style, lexical, embedding, and rubric-LLM baselines, DESG scores the direction of clinical-state change induced by a response; on the leakage-audited clean matched benchmark, DESG-StateRisk improves over the strongest non-DESG baseline by 0.0488 macro-F1 and achieves the best harmful-risk detection result. These results suggest that evaluating implicit sycophancy requires explicit clinical-state modeling together with leakage checks, shortcut controls, and competitive baselines.
Read the full abstract

All authors Tianze Han, Beining Xu, Hanbo Zhang, Yongming Lu

Computation and Language · Cross-listed from cs.DB

FINER-SQL: Boosting Small Language Models for Text-to-SQL

Thanh Dat Hoang, Thanh Trung Huynh, Matthias Weidlich et al. (+4 more)

Large language models have driven major advances in Text-to-SQL generation. However, they suffer from high computational cost, long latency, and data privacy concerns, which make them impractical for many real-world applications. A natural alternative is to use small language models (SLMs), which enable efficient and private on-premise deployment. Yet, SLMs often struggle with weak reasoning and poor instruction following. Conventional reinforcement learning methods based on sparse binary rewards (0/1) provide little learning signal when the generated SQLs are incorrect, leading to unstable or collapsed training. To overcome these issues, we propose FINER-SQL, a scalable and reusable reinforcement learning framework that enhances SLMs through fine-grained execution feedback. Built on group relative policy optimization, FINER-SQL replaces sparse supervision with dense and interpretable rewards that offer continuous feedback even for incorrect SQLs. It introduces two key reward functions: a memory reward, which aligns reasoning with verified traces for semantic stability, and an atomic reward, which measures operation-level overlap to grant partial credit for structurally correct but incomplete SQLs. This approach transforms discrete correctness into continuous learning, enabling stable, critic-free optimization. Experiments on the BIRD and Spider benchmarks show that FINER-SQL achieves up to 67.73% and 85% execution accuracy with a 3B model – matching much larger LLMs while reducing inference latency to 5.57~s/sample. These results highlight a cost-efficient and privacy-preserving path toward high-performance Text-to-SQL generation. Our code is available at https://github.com/thanhdath/finer-sql.
Read the full abstract

All authors Thanh Dat Hoang, Thanh Trung Huynh, Matthias Weidlich, Thanh Tam Nguyen, Tong Chen, Hongzhi Yin, Quoc Viet Hung Nguyen

Computation and Language

Retrieving Floods without Floodlights: Topic Models as Binary Classifiers for Extreme Climate Events in German News

Brielen Madureira, Mariana Madruga de Brito and Andreas Niekler

In studies of media coverage of extreme climate events, NLP methods have become indispensable for identifying relevant texts in large news databases. Still, enough annotated data to train accurate deep learning-based classifiers from scratch is often not available. Topic Models have the advantage of being both unsupervised and interpretable, but are typically used only for exploratory analysis or data characterisation. In this study, we investigate how to employ Topic Models as binary classifiers for refining the retrieval of relevant news about seven types of extreme climate events in the German media. Our method relies on the posterior distributions estimated by Topic Models to select relevant documents, without modifying their training procedure. Using an annotated sample to guide the evaluation, we show that the probabilities assigned to keywords used to query news databases can also be informative for selecting relevant topics and improve sample precision. We compare our results to a fine-tuned text embedding classifier and an open-weight LLM, discussing observed trade-offs, e.g. the LLM's lowest precision. Moreover, we show that results are hazard-dependent, which speaks against considering climate events as a single category in NLP tasks.
Read the full abstract

Computation and Language

An ERP Study of Recursive Possessive Parsing in ASD Children and Its Cognitive Neuro Mechanisms

Fu Chenxi, Wang Xiaoyi, Zhuang Ziman et al. (+1 more)

Recursive structures are a core property of human language, yet little is known about how children with autism spectrum disorder (ASD) process complex recursion. This ERP study investigated the online processing of two-level recursive possessive structures in Mandarin-speaking children with ASD (n = 12) compared to typically developing (TD) peers (n = 12) using a sentence-picture matching paradigm. ERPs were analyzed for P200 (150-250 ms), N400 (300-500 ms), and P600 (500-1000 ms). Results showed that ASD children exhibited significantly reduced P200 amplitudes and failed to show the typical posterior grammaticality effect, indicating atypical early perceptual processing. No robust N400 violation effect was observed in either group, confirming the mismatch was not a semantic anomaly; however, ASD children showed a reversed anterior effect and an attenuated posterior effect. For the P600, ASD children had significantly reduced amplitudes, no posterior grammaticality effect, and a trend toward delayed latency, reflecting a core deficit in syntactic reanalysis. These findings demonstrate that while lexical-semantic processing is relatively preserved in ASD, the online syntactic computation required for recursion is severely impaired, supporting modular dissociation accounts of language in autism.
Read the full abstract

All authors Fu Chenxi, Wang Xiaoyi, Zhuang Ziman, Yang Caimei

Computation and Language

Sentiment Analysis of Indonesian Spotify Reviews Using Machine Learning and BiLSTM

Uliano Wilyam Purba, Andre Hadiman Rotua Parhusip, Sahid Maulana et al. (+3 more)

This paper benchmarks classical machine learning and deep learning approaches for three-class sentiment classification of Indonesian Spotify reviews. Using 100,000 scraped reviews and 70,155 cleaned samples, the study compares Support Vector Machine, Multinomial Naive Bayes, and Decision Tree models with a two-layer BiLSTM. Both approaches use the same preprocessing pipeline, including slang normalization, stopword removal, and stemming. Decision Tree achieves the best performance among the classical models, while BiLSTM attains the highest weighted F1-score overall but fails on the minority neutral class. The paper concludes that BiLSTM is stronger for overall sentiment detection, whereas machine learning with SMOTE provides more balanced three-class performance.
Read the full abstract

All authors Uliano Wilyam Purba, Andre Hadiman Rotua Parhusip, Sahid Maulana, Luluk Muthoharoh, Ardika Satria, Martin C. T. Manullang

Computation and Language · Cross-listed from cs.CR

Exposing LLM Safety Gaps Through Mathematical Encoding:New Attacks and Systematic Analysis

Haoyu Zhang, Mohammad Zandsalimy and Shanu Sushmita

Large language models (LLMs) employ safety mechanisms to prevent harmful outputs, yet these defenses primarily rely on semantic pattern matching. We show that encoding harmful prompts as coherent mathematical problems – using formalisms such as set theory, formal logic, and quantum mechanics – bypasses these filters at high rates, achieving 46%–56% average attack success across eight target models and two established benchmarks. Crucially, the effectiveness depends not on mathematical notation itself, but on whether a helper LLM deeply reformulates the harmful content into a genuine mathematical problem: rule-based encodings that apply mathematical formatting without such reformulation perform no better than unencoded baselines. We introduce a novel Formal Logic encoding that achieves attack success comparable to Set Theory, demonstrating that this vulnerability generalizes across mathematical formalisms. Additional experiments with repeat post-processing confirm that these attacks are robust to simple prompt augmentation. Notably, newer models (GPT-5, GPT-5-Mini) show substantially greater robustness than older models, though they remain vulnerable. Our findings highlight fundamental gaps in current safety frameworks and motivate defenses that reason about mathematical structure rather than surface-level semantics.
Read the full abstract

Computation and Language

A Comparison of Traditional Machine Learning Algorithms and LSTM-Based Deep Learning Models for Email Sentiment Analysis

Virdio Samuel Saragih, Baruna Abirawa, Kartini Lovian Simbolon et al. (+3 more)

The rapid growth of electronic communication has necessitated more robust systems for email classification and sentiment detection. This study presents a comparative performance analysis between traditional machine learning algorithms and deep learning architectures, specifically focusing on Support Vector Machines (SVMs), Logistic Regression, Naive Bayes, and Long Short-Term Memory (LSTM). Utilizing Word2Vec embeddings for feature representation, our experimental results indicate that the SVM model with a linear kernel achieves the highest efficiency and accuracy, reaching a peak performance of 98.74%. While the LSTM model demonstrates exceptional recall capabilities in detecting spam-related sentiments, it requires significantly more computational time compared to discriminative statistical models. Detailed evaluations via confusion matrices further reveal that traditional classifiers remain highly robust for dense vector spaces. This research concludes that for email detection tasks, SVM offers the most optimal balance between predictive precision and processing speed. These findings provide critical insights for developing high-performance automated email filtering systems in professional and academic environments.
Read the full abstract

All authors Virdio Samuel Saragih, Baruna Abirawa, Kartini Lovian Simbolon, Luluk Muthoharoh, Ardika Satria, Martin C.T. Manullang

Computation and Language

Benchmarking Logistic Regression, SVM, Naive Bayes, and IndoBERT Fine-Tuning for Sentiment Analysis on Indonesian Product Reviews

Nabila Zakiyah Zahra, Salwa Farhanatussaidah, Nasywa Nur Afifah et al. (+3 more)

The exponential growth of e-commerce platforms in Indonesia has generated a massive volume of user-generated product reviews. Analyzing the sentiment of these reviews is critical for measuring customer satisfaction and identifying product issues at scale. This paper benchmarks traditional Machine Learning (ML) approaches against a Transformer-based Deep Learning model for a three-class sentiment analysis task (positive, neutral, negative) on the Tokopedia Product Reviews 2025 dataset. We implemented Term Frequency-Inverse Document Frequency (TF-IDF) feature extraction coupled with three algorithms: Logistic Regression, Linear Support Vector Machine (SVM), and Multinomial Naive Bayes as robust baselines. Subsequently, we fine-tuned the IndoBERT model (indobenchmark/indobert-base-p1) for contextual sequence classification. To computationally address the severe class imbalance inherent in e-commerce feedback, we applied balanced class weights for the baseline models and engineered a custom weighted cross-entropy loss function within the IndoBERT training loop, following the broader motivation of imbalanced-learning research. Our comprehensive evaluation using Accuracy, Macro F1-score, and Weighted F1-score revealed that the traditional Linear SVC model significantly outperformed the IndoBERT model in our experimental setup, achieving an Accuracy of 97.60% and a Macro F1-score of 0.5510, compared to IndoBERT's 88.70% and 0.5088. Detailed analysis indicates that this performance gap was primarily driven by discrepancies in the data sampling regimes, where baselines utilized the full corpus while the Transformer was constrained to a sampled subset. Finally, we demonstrate the practical viability of our pipeline by deploying the final sentiment classification model as an interactive Gradio web application.
Read the full abstract

All authors Nabila Zakiyah Zahra, Salwa Farhanatussaidah, Nasywa Nur Afifah, Luluk Muthoharoh, Ardika Satria, Martin C.T. Manullang

Computation and Language

Geolocating News about Extreme Climate Events: A Comparative Analysis of Off-the-Shelf Tools for Toponym Identification in German

Brielen Madureira, Mariana Madruga de Brito and Andreas Niekler

Determining the geolocation of extreme climate events and disasters in texts is a common problem in climate impact and adaptation research. Named-entity recognition (NER) tools are typically used to identify a pool of toponyms that serve as candidate event locations. In this study, we conduct a comparative analysis of three off-the-shelf NER tools, namely Flair, Spacy and Stanza. We describe and quantify differences between their outputs for German news articles and evaluate them extrinsically based on three methods to determine the country where events took place. We show how their contrasts are propagated into downstream tasks and can yield distinct decisions about a document's geographical focus, which, in turn, can impact conclusions about countries' prominence in German media.
Read the full abstract

Computation and Language

From prompting to evidence-based translation: A RAG+prompt system for Japanese-Chinese translation and its pedagogical potential

Wenshi Gu

Large language models perform well on high-resource pairs but are less reliable for Japanese-Chinese sentences containing noun-modifying clause constructions (NMCCs). This study evaluates a retrieval-augmented generation RAG+Prompt translation system that integrates linguistic analysis, embedding-based retrieval, prompt construction, and LLM generation without modifying the base model. The analysis module outputs A1 (inner vs. outer NMCC) and A2 (risk predictions: lexical choice/NMCC handling/word order/style/register); top-k = 5 similar Ja-Zh examples (L2 distance) and A1/A2 are inserted into an enhanced prompt. Using GPT-4o and a 66-sentence test set, we compare six knowledge-base sizes (0/100/200/500/1,000/2,000). Macro-averaged sentence-level BLEU (1-4-gram with brevity penalty; cased; Chinese at the character level) is the sole metric. Mean BLEU increases from 24.28 at 0 (RAG disabled) to 29.96 at 2,000 (+5.68; +23.4%). The upward trend holds across sizes, with larger knowledge bases yielding higher scores. We conclude that the RAG+Prompt translation system improves Ja-Zh translation of sentences containing NMCCs in an interpretable and auditable manner. Limitations include one base model, one metric, and reliance on published texts and commercial APIs; future work will broaden genres, language pairs, and evaluation metrics.
Read the full abstract