cs.CL · 2026-11-09 · No. 168

Computation and Language, 2026-11-09.

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

01 — The papers

9 entries
  1. 01

    Are These Programmers Ripe Enough to Eat? Evaluating How LLMs Handle Lexical Knowledge Conflicts in Translation

    Dongxu Wu, Sara Court, Micha Elsner

    cs.CL · cs.LG

    External lexical resources can help large language models (LLMs) translate texts in low-resource languages and specialized domains, but these resources may conflict with models' prior lexical knowledge. To isolate this conflict, we construct a controlled Mandarin-to-English translation task in which familiar source words are assigned new meanings within and across semantic categories. We treat these prompt-supplied meanings as contextual...

    arxiv.org/abs/2611.09785 · PDF

  2. 02

    ROSE: Risk-Aware Orthogonal Subspace Navigation for Lifelong Knowledge Editing in Multimodal Large Language Models

    Lingyun Song, Ziyao Chen, Kang Pan, Xiaolin Han, Yifei Zhang, Xiaoqi Wang, Yudai Pan, Xuequn Shang

    cs.CL · cs.AI · cs.CV

    Multimodal Large Language Models (MLLMs) require continuous factual updates to stay current, yet lifelong knowledge editing remains a daunting challenge. The primary obstacle is the severe Locality Erosion and Catastrophic Forgetting, where sequential edits inevitably interfere with pre-trained capabilities and prior updates. In this paper, we propose \textbf{ROSE}, a \textbf{R}isk-aware \textbf{O}rthogonal \textbf{S}ubspace navigation...

    arxiv.org/abs/2611.09770 · PDF

  3. 03

    Language as Trait, Politeness as Strategy: Controlled Tests of Linguistic Effects in LLM Social-Deduction Agents

    Yuchen Li, Lisa Liu, Runqi Zou, Shuxuan Kuang, Qingquan Zhang, Julian Togelius

    cs.CL · cs.AI

    Large language model (LLM) agents coordinate through conversation, and the same message can be phrased in simpler or more complex language, bluntly or politely. We test whether such differences change how other agents judge and act, using the LURK Werewolf framework, which separates each utterance's speech-act predicate from its natural-language realization. We rewrite only the realization, check that the game content is preserved, and replay...

    arxiv.org/abs/2611.09768 · PDF

  4. 04

    How Much Conversation History Does an AI Agent Need?

    Danny Kim, Fernando Koch

    cs.CL · cs.AI

    How does using less conversational history change reader-token use and benchmark scores? We examine this question on 1,100 BEAM questions. We held the retrieval ranking and reader constant across five fixed passage budgets, and mean assigned scores rose as the passage budget grew. The score gain per additional token became smaller at the upper tested budgets. Answerable questions generally received higher scores with more context. Pooled...

    arxiv.org/abs/2611.09662 · PDF

  5. 05

    Steerable Multi-Objective Group-Relative Preference Optimization with Jointly Trained Low-Rank Adapters

    Constantinos Karouzos, Nikolaos Aletras

    cs.CL · cs.AI · cs.LG

    Language model deployment often requires different trade-offs between competing objectives as user preferences change, yet standard post-training methods typically produce a single policy for a fixed objective weighting. We introduce LambdaMix, a new parameter efficient method for learning a preference conditioned family of policies with group-relative online reinforcement learning. LambdaMix jointly trains one low-rank adapter per objective...

    arxiv.org/abs/2611.09634 · PDF

  6. 06

    Query-Guided RoPE Modulation for Lost-in-the-Middle Mitigation in Long-Context LLMs

    Peiyu Zhang, Heng Ping, Shinibali Bhattacharyya, Anwesan Pal, Nikos Kanakaris, Kevin Cheang, Shixuan Li, Wei Yang,...

    cs.CL · cs.AI · cs.LG

    Long-context language models often neglect information in the middle of the input, a phenomenon known as "lost-in-the-middle". Part of this gap may stem from the long-range decay of rotary position embedding (RoPE), which weakens the positional signal between distant tokens. Existing input compression deletes low-importance tokens, and attention reweighting acts only after RoPE has weakened this signal. RoPE-level methods modify positions...

    arxiv.org/abs/2611.09554 · PDF

  7. 07

    Syn2DRE: Synergistic Dual Teacher-Student Framework for Document-level Relation Extraction

    Khai Phan Tran, Xue Li

    cs.CL · cs.AI

    Document-level Relation Extraction (DocRE) aims to identify relations between entities across a document but typically relies on costly large-scale annotations. While pseudo-labelling enables the use of low-quality data, existing methods often suffer from inefficiency and confirmation bias. To address these challenges, we propose Syn2DRE, a semi-supervised framework that combines self-supervised learning with cross-supervision in a...

    arxiv.org/abs/2611.09342 · PDF

  8. 08

    Representational drift in a code model: behaviour settles, which neurons carry it does not

    Piotr Wilam

    cs.CL · cs.LG

    In neuroscience, representational drift is a change in which neurons carry a representation while behaviour stays the same; we measure its analogue in OpenCoder-1.5B during pretraining, for 169 Python constructs over two trillion tokens at a constant learning rate, with a noise unit on every change, at checkpoints as close as 1,000 training steps. For 16 of the 169, those whose grammar fixes a next token, the loss at those positions reaches...

    arxiv.org/abs/2611.09204 · PDF

  9. 09

    Calibrated concept profiles: making the reading of a model's neurons a measurement

    Piotr Wilam

    cs.CL · cs.LG

    Interpretability has largely moved from reading a model's neurons directly to reading a second model trained on the first: a probe, a sparse autoencoder, a crosscoder. The move answered real faults -- mixed meanings, thresholds without a unit, readings that did not transfer from one study to the next -- but gave up what a direct reading alone provides: nothing trained in between, the neurons themselves named, and a reading that can be...

    arxiv.org/abs/2611.09196 · 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.