cs.CL · 2026-10-26 · No. 154

Computation and Language, 2026-10-26.

12 new papers in cs.CL. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

12 entries
  1. 01

    Measure Before You Train: Typed Decision Models vs. a Classical Baseline vs. a Generative LLM for Routing a Personal Multilingual Inbox

    Federico Lucca

    cs.CL · cs.HC · cs.LG

    Personal email agents decide, for every message, what it is, whether it is urgent, whether to draft a reply, create a task, or ignore it. Their error rate is rarely measured: the stored labels were written by the system itself. We present Foyer, a self-hosted personal inbox agent in daily use, and a measurement protocol (stratified sampling, frozen snapshots, thread-grouped splits, pre-registered hypotheses, human labels in the agent's review...

    arxiv.org/abs/2610.32955 · PDF

  2. 02

    Yalda-Embedding: Open Development of a Competitive Persian Retrieval Model

    Yalda Taheri, Mohammad Hassan Heydari, Armon Rasooli

    cs.CL · cs.AI

    Despite advances in multilingual text representations, effective dense retrieval for Persian remains constrained by the limited availability of language-specific training resources and compact embedding models. We present Yalda Embedding, a 595.8-million-parameter Persian retrieval model adapted from Qwen3-Embedding-0.6B using more than one million query-document pairs. On eight Persian retrieval tasks from FaMTEB, the model achieves the...

    arxiv.org/abs/2610.32933 · PDF

  3. 03

    Adaptive Frequency Threshold Byte Pair Encoding for Mixed Natural Language and Structured Symbolic Corpora

    Pietro Di Nicco, Lucio La Cava, Andrea Tagarelli

    cs.CL · cs.LG

    Modern language models rely on subwording tokenization to define the discrete units of input processing, typically using methods like Byte Pair Encoding (BPE) that treat whitespace as a fixed semantic boundary. This design is inherently limited, as many meaningful concepts---including multiword expressions and the structured environments of formal languages like LaTeX---frequently span across whitespaces. While recent superword tokenization...

    arxiv.org/abs/2610.32921 · PDF

  4. 04

    Every Edge Needs a Quote: Building a Quote-Grounded Knowledge Graph of Healthcare Software Adoption with Language-Model Agents

    Juan Felipe Duran, Arthur Tobler, Martin Vallières

    cs.CL · cs.AI · cs.IR

    Hospitals regularly buy software that clinicians and patients depend on. Because these purchases are costly, hard to reverse and can affect patient care, buyers look for evidence of which peer institutions already use a product and which systems it connects to. This evidence is public but scattered across vendor websites, press releases and third-party pages. Language-model agents can now collect it at low cost, but the correctness of the...

    arxiv.org/abs/2610.32781 · PDF

  5. 05

    On-Policy Self-Training: Data-Free Self-Improvement in Large Language Models

    Leon Sick, Lukas Hoyer, Yannick Strümpler, Christian Reisswig, Timo Ropinski, Federico Tombari

    cs.CL · cs.AI · cs.LG

    On-policy self-distillation enables post-training foundation models without relying on stronger external teachers. However, existing approaches rely on ground-truth question-answer pairs, human-curated problem sets, or other supervised signals. In this work, we reformulate on-policy self-distillation as a self-training framework, driven by self-generated question-answer pairs and privileged reasoning demonstrations. We push supervision to the...

    arxiv.org/abs/2610.32770 · PDF

  6. 06

    Ontology-Guided Knowledge Graph Construction from Structured Metadata and Climate Science Publications

    Aayush Acharya, Qi Zhang, Eduard Dragut, Longin Jan Latecki

    cs.CL · cs.AI

    The rapid expansion of scientific literature far outpaces the speed of manual curation, creating a fundamental bottleneck in extracting structured knowledge from scientific texts. To address this, we introduce an agentic, ontology-guided framework for knowledge graph (KG) construction. Our framework utilizes specialized agents for document understanding, information extraction, ontology conformance, and entity linking. First, an LLM extracts...

    arxiv.org/abs/2610.32725 · PDF

  7. 07

    Analysing Austrian Parliamentary Speeches by Predicting Party Affiliations

    Sarah Sulollari, Vanja Karan, Benjamin Roth

    cs.CL · cs.AI · cs.CY · cs.LG

    This paper examines speech characteristics of the Austrian National Council members (CMs). We introduce analysis methodology based on a fine-tuned BERT-Model which assigns to every speech a probability distribution over Austrian parties. These are then aggregated at the speaker and party level. We perform an extensive evaluation to ensure the quality of the generated distributions prior to further analysis. Instead of considering...

    arxiv.org/abs/2610.32515 · PDF

  8. 08

    Decoupling Patient Personas and Clinical Workflows: A Dual-Agent Approach to Realistic Medical Dialogue Generation

    Qiyuan Li, Xiaomei Guo, Chao Gao, Haijiang Liu, Deyu Chen, Caicai Guo, Jinguang Gu

    cs.CL · cs.AI · cs.LG

    Pre-consultation medical dialogues are essential for collecting comprehensive patient information, but are costly to obtain at scale due to privacy and ethical constraints. Existing LLM-based synthesis methods often rely on prompt engineering or rigid rules, limiting their ability to balance clinical relevance with realistic patient diversity. We propose CoRPS-Dial, a controllable dual-agent framework for pre-consultation medical dialogue...

    arxiv.org/abs/2610.32443 · PDF

  9. 09

    Acoustic and Lexical Signals for Native Language Identification of Language Learners

    Ahmet Yavuz Uluslu, Mengjie Qian, Kate Knill, Mark Gales

    cs.CL · cs.LG

    Spoken native language (L1) identification for second language learners has traditionally relied on acoustic attributes of speech. Comparatively little attention has been paid to analysing speech transcripts for L1 traces. In this paper, we present a study of L1 identification using both speech and corresponding transcripts from a spoken learner English corpus. We compare a WavLM-based audio L1 classifier with a zero-shot GPT-4o classifier...

    arxiv.org/abs/2610.32382 · PDF

  10. 10

    "Not" is Not Lost in Translation: A Causal Analysis of Negation Representations in Multilingual LLMs

    Giang Son Nguyen, Wray Buntine, Dung D. Le, Wenya Wang

    cs.CL · cs.AI

    Negation occurs in every language, yet its surface realization differs drastically. Despite this, multilingual large language models (LLMs) translate negation robustly, raising the question of whether they share an underlying representation of negation across languages. We study this question in six open models across English, French, Vietnamese, and Chinese, using causal interventions on a synthetic contrastive dataset and a negation...

    arxiv.org/abs/2610.32281 · PDF

  11. 11

    Do Halting Heads Really Save Compute in Looped Language Models?

    Tsung-Han Wu, Minsuk Heo, Kenny Tan

    cs.CL · cs.LG

    Looped language models run each token through the same layers several times, and each run is one iteration. To save compute, an extra layer, the halting head, gives after each iteration the probability that the token stops there, so that easy tokens can stop early. Pretraining models from scratch, up to 1.3B parameters, we find two problems. First, heads trained on a mix of all iterations predict that tokens need under half the iterations,...

    arxiv.org/abs/2610.32246 · PDF

  12. 12

    SOPO: Socratic Guided Policy Optimization for Span-Level Hallucination Detection

    Jiawei Dong, Zilong Bai, Pengtian zhu, Peng Zhou

    cs.CL · cs.AI

    Large Language Models (LLMs) have gained widespread adoption in various natural language processing tasks, but suffer from hallucination issues where they generate unfaithful or inconsistent content. While Reinforcement Learning with Verifiable Rewards (RLVR) has shown promising applications in reasoning tasks, its application to span-level hallucination detection is challenged by localization ambiguity, reward sparsity on hard examples, and...

    arxiv.org/abs/2610.32212 · PDF

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.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.