cs.CL · 2026-09-23 · No. 122
Computation and Language, 2026-09-23.
8 new papers in cs.CL. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
8 entries-
01
SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue
Haobo Zheng, Tan Tang, Yan Chen, Weijie Wang, Yingcai Wu
cs.CL · cs.AI · cs.IR · cs.LG
Long-term conversational memory in multi-party settings requires more than retrieving relevant content from long-term conversations: it must distinguish who said what, whom each statement concerns, how individuals perceive one another, what information is shared by the group, and how states change over time. Recent studies on multi-party dialogue benchmarks show that existing general-purpose LLM memory systems tend to lose person and group...
-
02
Beyond Repeated Sampling: Learning Search Policies for LLM Reasoning
Ismail Labiad, Matthieu Kowalski, Marc Schoenauer, Rémi Munos, Julia Kempe
cs.CL · cs.AI
Large language models increasingly tackle hard reasoning problems by spending more test-time compute, yet the dominant strategy remains naive repeated sampling: draw many independent solutions and hope one is correct. Because such sampling explores only through local decoding noise, it tends to produce many near duplicate attempts rather than genuinely different ideas. We ask whether exploration can instead be steered at a semantic level, by...
-
03
Measuring the Serving Stack Instead of the Model: Hidden Confounds in Local Tool-Use Evaluation
Lijuan Tang, Yuemeng Zheng
cs.CL · cs.AI · cs.SE
A coding agent must emit a valid tool call--a parseable invocation of a tool in the provided schema--before the harness can execute its chosen action. We study how local serving stacks affect this protocol step and show that measured outcomes can depend on the serving layer rather than model behavior alone. In Ollama, the default tools= request is gated per model by a static template flag: some models are accepted and return calls as text,...
-
04
Capable yet Parsimonious: Extracting and Characterizing Hidden Chain-of-Thought in Frontier Models
Xiaoyu Luo, Tao Ren, Wenrui Yu, Xiao Li, Qiongxiu Li, Johannes Bjerva
cs.CL · cs.AI · cs.CR
The rapid capability gains of frontier language models are widely attributed to improved reasoning abilities, yet this cannot be verified as raw CoT traces in closed-source systems are hidden. By registering a simple custom tool through a standard API feature, we induce frontier models to externalize intermediate reasoning. Because these traces may reflect post-hoc rationalization rather than genuine reasoning, we first evaluate against...
-
05
Receptiveness, Not Sycophancy: Distinguishing Engagement from Deference in Language Models
Calvin Isley, Johann Gaebler, Max Lamparth, Julia Minson, Sharad Goel
cs.CL · cs.AI · cs.HC
A central concern with language models is sycophancy: their tendency to defer to users' views at the expense of independent substantive judgment. In parallel, work on social sycophancy has focused on behaviors such as validation and positivity that may signal inappropriate deference. Yet the markers of social sycophancy are also characteristic of conversational receptiveness, a construct from social psychology shown to improve interactions...
-
06
A Semiotics-Aware Framework for Evaluating Fidelity and Coverage in Natural Language Generation
Lorenzo Zangari, Davide Picca
cs.CL · cs.AI
When two texts describe the same expression, standard metrics based on lexical overlap or whole-text similarity may fail to detect meaningful differences in how that expression is framed. We propose a framework to evaluate semiotic alignment between texts, where a semiotic profile encompasses both the contextual meaning and the discourse references made salient by a text. Our approach yields two scores, Semiotic Fidelity and Semiotic...
-
07
TransBERT: A Framework for Synthetic Translation in Domain-Specific Language Modeling
Julien Knafou, Luc Mottin, Anaïs Mottaz, Alexandre Flament, Patrick Ruch
cs.CL · cs.AI · cs.LG
The scarcity of non-English language data in specialized domains significantly limits the development of effective Natural Language Processing (NLP) tools. We present TransBERT, a novel framework for pre-training language models using exclusively synthetically translated text, and introduce TransCorpus, a scalable translation toolkit. Focusing on the life sciences domain in French, our approach demonstrates that state-of-the-art performance...
-
08
Syndrome, Synergy, and Safety: Structured Reasoning and Knowledge-Driven Alignment for TCM Prescription Generation
Zheng Chen, ZhiCheng Du, Haoxuan Li, Peiwu Qin
cs.CL · cs.AI
Applying large language models to Traditional Chinese Medicine (TCM) prescription generation reveals three clinically critical gaps: models produce end-to-end mappings without auditable reasoning following the li-fa-fang-yao paradigm (SR Gap), treat each encounter in isolation without follow-up adjustment via sui zheng jia jian (LA Gap), and fail to enforce absolute contraindication rules such as Shi Ba Fan (SC Gap). We propose a progressive...
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.