cs.CL · 2026-07-31 · No. 70
Computation and Language, 2026-07-31.
15 new papers in cs.CL. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
15 entries-
01
AskChem: Claim-Centered Infrastructure for Chemistry Literature Synthesis
Bing Yan, Gregory Wolfe, Stefano Martiniani, Kyunghyun Cho
cs.CL · cs.AI · cs.IR · cs.LG
Chemistry literature synthesis often requires assembling specific findings scattered across many publications, yet existing literature-search systems primarily return ranked document lists. As a result, scientists and AI agents need to locate relevant information, verify their provenance, and assemble cross-paper answers manually. We present AskChem, a claim-centered infrastructure for cross-paper chemistry search. AskChem changes the unit of...
-
02
Sample More, Reflect Less: Self-Refine and Reflexion Lose to Repeated Sampling at Equal Token Cost, from 1.5B to 7B
Iliya Mirzaei
cs.CL · cs.AI · cs.LG
Methods that make a language model plan, criticise and rewrite its own answer, reflect on mistakes, pick the best of several attempts, or debate with copies of itself nearly all make it generate far more text than a single chain of thought. Because generating more text raises accuracy by itself, a gain over one chain of thought does not show the method's idea is what helped. Wang et al. (2024) reported that a simple baseline, sampling the...
-
03
ORCA-bench: How Ready Are Language Model Agents for Oncall?
Albert Gong, Kyuseong Choi, Abhineet Agarwal, Jason Schechner, Ryan Huang, Raj Agrawal, Anish Agarwal, Raaz Dwivedi
cs.CL · cs.AI · cs.SE
Large language models can write, patch, and search code, but oncall root cause analysis (RCA) demands something different: reasoning over noisy metrics, logs, traces, and source code, starting from ambiguous user-facing reports, often hours after the incident began. We introduce ORCA-bench, a benchmark that puts general-purpose coding agents in a production-fidelity oncall setting. ORCA-bench pairs a live OpenTelemetry-instrumented...
-
04
Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations
Pere Martra, Eugenio Martínez Cámara, Alfonso Ureña López
cs.CL · cs.CY · cs.LG
This work presents Fairness Pruning, a lightweight structural intervention method designed for the management and future mitigation of demographic bias in large language models (LLMs). As a foundational empirical validation of this method, this work focuses on causal bias localization. Using minimally contrastive prompt pairs and inference-time activation capture, the method identifies neurons that react differentially when processing...
-
05
CACHE-UK: A Stability-Aware Memory Editor for Sequentially Updated Quantized LLMs in Finance
Anubhav Lakra, Yue Feng
cs.CL · cs.AI · cs.CE · cs.LG
Large Language Models (LLMs) deployed in dynamic financial environments face a critical challenge: maintaining factual accuracy as market conditions, regulations, and corporate facts change continuously. While 4-bit quantization enables efficient deployment, it severely limits the viability of sequential memory editing: existing methods undergo catastrophic performance degradation under this "quantization stability crisis." We introduce...
-
06
(Towards) Scalable Reliable Automated Evaluation with Large Language Models
Bertil Braun, Martin Forell
cs.CL · cs.LG
Evaluating the quality and relevance of textual outputs from Large Language Models (LLMs) remains challenging and resource-intensive. Existing automated metrics often fail to capture the complexity and variability inherent in LLM-generated outputs. Moreover, these metrics typically rely on explicit reference standards, limiting their use mostly to domains with objective benchmarks. This work introduces a novel evaluation framework designed to...
-
07
MORFES: A Benchmark for Productive Inflectional Competence in Modern Greek
Ioakeim Perros, Cleopatra Papadopoulou, Ayoub Kirouane, Christos Petrocheilos
cs.CL · cs.LG
Modern Greek is a richly inflected language, yet the language models built for it are evaluated mainly on factual knowledge, and no benchmark is dedicated to their inflectional competence. We introduce MORFES (Morphological Open-class Recognition-and-Formation Evaluation Suite), a benchmark of 500 expert-verified items that tests the recognition and production of Greek inflected forms, favoring lower-frequency lemmas so that a correct answer...
-
08
EMBL AI Librarian: Life-Sciences Knowledge Layer for AI Agents
Luigi Sigillo, Matteo Silvestri, Francesco Tabaro, Rajat Bhatnagar, Syed Irtaza Mubashar, Matt Jeffryes, Daljit...
cs.CL · cs.AI · cs.IR · cs.LG
The web is increasingly accessed by AI agents rather than humans. Every agent needs knowledge, especially in the life-sciences, where agentic pipelines are growing fast. Access to the literature is a crucial part of that need, and resources such as Europe PMC, with over 40M indexed records, are widely used to meet it. Yet these resources were not built for AI agents: they take keywords and complex syntax and return whole papers, so every...
-
09
Causal Discovery with Inverted Self-attention for Multivariate Time Series
Yusen Liu, Yong Wang, Yifan Yin, Tianqing Zhu, Xiufeng Liu, Huan Huo
cs.CL · cs.LG
Causal discovery in multivariate time series data is challenging due to complex interactions, high dimensionality, and nonlinear dependencies among variables. Existing methods often struggle to capture these complexities, resulting in inaccurate causal structures. To address this issue, we propose a novel framework that leverages self-attention mechanisms within the transformer architecture for causal discovery. Our approach introduces a...
-
10
The MADRS Pipeline: Supporting Depression Assessment in Clinical Trials
Mila Fodor, Katalin Ócsai, Francesco Periti, Rien Sonck, Alex Boudreau
cs.CL · cs.AI
Depression is a major mental disorder for which diagnosis relies primarily on clinical assessments. Automated methods to support its detection via the psychiatric MADRS scale are getting more and more attention. While existing solutions primarily focus on detecting the disorder from different text sources (e.g., online text, social media), there is still limited support for clinical trials, where clinical assessments are conducted through...
-
11
Where and When to Commit: Candidate-Aware Decoding for Diffusion Language Models
Chia-Ming Lee, Ming-Ching Chang, Xin Li, Yu-Lun Liu, Chih-Chung Hsu
cs.CL · cs.AI
Diffusion language models (DLMs) expose a provisional prediction at every denoising step, creating an opportunity for generation-time early exit that stops decoding before the schedule is exhausted. Existing early-exit gates decide termination from fixed-region confidence statistics or schedule-dependent rules, evidence too coarse for a decision that freezes every remaining position at once, so they fire prematurely on long chain-of-thought...
-
12
Can Agents Deceive? Evaluating Reasoning and Deception in ParliamentBench using a Social Deduction Game
Niklas Bauer, Lars Benedikt Kaesberg, Akiko Aizawa, Jan Philip Wahle, Bela Gipp, Terry Ruas
cs.CL · cs.AI
As large language models (LLMs) are deployed as agents in high-stakes settings, such as medical and legal systems, understanding their deceptive capabilities is fundamental to safety. Controlled social deduction games provide a reproducible proxy for isolating and evaluating these complex adversarial behaviors. We present the open-source benchmark framework ParliamentBench based on the game Secret Hitler to evaluate LLMs in scenarios that...
-
13
Rethinking LLM-Judged Helpfulness as a Pedagogy Signal: A Pre-Registered Audit Across Tutor Models
Shuyi Fan, Boyuan Deng, Mengyu Xu, Jiale Liu, Hongyang Zhang, Qiaoxin Yang, Chongyang Gao
cs.CL · cs.AI · cs.CY
LLM tutoring poses a measurement problem: can a general-purpose helpfulness rubric distinguish direct answer-giving from pedagogical guidance? We audit this signal in a pre-registered study. Within each of three tutor bases, we compare conversational and pedagogical policies instantiated with the same underlying model and paired with one fixed weak simulated student. Deterministic detectors measure answer leakage and next-turn independent...
-
14
FinSMART: Financial Sentiment Analysis for Algorithmic Trading through Market-Aligned Reinforcement Learning
Giorgos Iacovides, Wuyang Zhou, Danilo Mandic
cs.CL · cs.LG · q-fin.ST · q-fin.TR
Recent advances in Generative AI have substantially improved financial sentiment analysis through post-trained financial large language models (LLMs). However, existing approaches remain confined to a market-agnostic, supervised learning paradigm that relies on limited, static and human-annotated datasets, and thus are incapable of adapting to evolving market conditions. To address this limitation, we introduce FinSMART, the first...
-
15
RepBench: Compiling Benchmarks into Capability Representations for Large Language Models
Yanshi Li, Xueru Bai, Shuman Liu, Long Zhang
cs.CL · cs.AI
Representation engineering reads and steers capability directions in large language models, yet methods are typically evaluated on paper-specific synthetic data. The resulting measurements are difficult to compare or reproduce and may reflect surface patterns rather than capabilities. We present RepBench, a benchmark-grounded data layer for capability-aligned representation probing. Crawling 13,427 benchmark papers yields a taxonomy of 182...
This edition is part of The Daily Abstract — cs.CL archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.