cs.CL · 2026-10-17 · No. 146
Computation and Language, 2026-10-17.
17 new papers in cs.CL. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
17 entries-
01
Knowledge That Is Linear Before Fine-Tuning Generalizes After It
Faridoun Mehri, Hinrich Schütze
cs.CL · cs.AI · cs.LG
Not all facts a language model can recall support further learning equally well. We distinguish active facts, which support generalization beyond their own recall, from inert facts, which can be recalled but do not support such generalization in a given task. We study this distinction by constructing new relations from existing ones. Take the relation that maps a place to its continent (Paris -> Europe) and assign each of its answers an...
-
02
AI Consilium: a Benchmark of LLM Clinical Multidisciplinary Second Opinions
Alexey A. Bokov, Ivan I. Panin, Nikolay B. Nechaev, Mikhail Yu. Valkov, Valeria Yu. Chernina, Natalia Gombolevskaya,...
cs.CL · cs.AI
Large language models (LLMs) can generate differential diagnoses for complex cases, but a useful second opinion must also be factually grounded, clinically coherent, actionable, and safe. We developed a multidimensional benchmark using 300 diagnostically resolved NEJM--MedQA cases: 110 for physician reference ratings and Judge calibration and 190 for held-out evaluation. Eight single-model pipelines generated independent role-specific...
-
03
Beyond Downstream QA: Rethinking How We Evaluate Agent Memory
Sebastian-Antonio Toma, Jean de Kernier, Mike Ply, Oliviu Matei
cs.CL · cs.AI · cs.LG
Agent memory benchmarks evaluate whether an agent's responses reflect correct knowledge, measuring downstream question-answering accuracy as a proxy for memory quality. We show this evaluation paradigm is incomplete: it conflates memory correctness with retrieval and generation quality, producing both false positives where correct responses mask broken memory and false negatives where incorrect responses blame correct memory for retrieval...
-
04
Change the Number, Change the Answer: Assessing Rating Scale Sensitivity in LLM-Based Text Scoring
Wonjeong Jo, Gyuwan Kim, Ming Shan Hee
cs.CL · cs.AI · math.NA
Large language models (LLMs) are increasingly used in computational social science to assign scalar scores to social and psychological constructs. However, studies use different rating scales, and whether their scores remain comparable across scale designs is understudied. To address this gap, we define and systematically investigate scale sensitivity, the variation in LLM-generated scores caused by rating scale design. We distinguish...
-
05
Mosaic: Multi-Session Agentic Reinforcement Learning
Yilong Xu, Minrui Xu, Xinyu Zhou, Xiang Long, Haochen Tan, Zhijiang Guo
cs.CL · cs.AI · cs.LG
Most existing agentic reinforcement learning methods assume single-session trajectories, where interaction proceeds within one continuously accumulated context. However, agentic techniques such as context compaction and subagent forking may produce trajectories spanning multiple sessions, creating a mismatch between the single-session training assumption and inference-time execution. Therefore, we introduce Multi-Session Agentic Reinforcement...
-
06
Lexical Reference Frames: Interpreting LM Residual Streams in Native Semantics
Jian Gu, Hongyu Zhang, Chunyang Chen, Aldeida Aleti
cs.CL · cs.LG
The vocabulary of a language model is its native semantics: the embedding and the unembedding fix the meaning of a state at the two ends of the residual stream. Between them, existing methods either reuse a fixed lens or treat the states as a point cloud, and neither reads a state the way the model does. We argue that every hidden state has a native reference frame, induced by the layers that read it next and adaptive to the context. Lexical...
-
07
EMO: A Closed-Loop Test-Time Computation Framework via Alternating Context Optimization and Logits Steering
Wei Xia, Yehui Tang, Zhi-Hong Deng
cs.CL · cs.AI
Test-time context optimization adapts frozen language models through textual feedback, but ordinary conditional generation provides no separate control over how strongly to reinforce the distributional changes induced by a context update. We introduce EMO, a training-free framework inspired by expectation--maximization that alternates question-specific context estimation (E-step) and distribution refinement (M-step). The E-step revises a...
-
08
Explaining the Roles of Experts in Mixture-of-Experts LLMs for Personalization
Sekh Mainul Islam, Pepa Atanasova, Isabelle Augenstein
cs.CL · cs.AI
Personalization of Large Language Models (LLMs) is increasingly important for user-centric applications, yet prior methods mainly adapt dense LLMs, whose polysemantic neurons, each encoding multiple unrelated concepts, hinder localizing the components behind personalization, and thus understanding and controlling it. We propose to personalize Mixture-of-Experts (MoE) LLMs, which sparsely route each token to a few specialized experts, reducing...
-
09
Patch where the text is new: a compression view of where byte-level models should spend compute
Nicolás Vera Zúñiga
cs.CL · cs.LG
Byte-level language models such as the Byte Latent Transformer (BLT) run their large global model once per patch and start a patch where a small model's next-byte entropy is high. This rule rarely starts a patch at in-line computed results, such as the number after "=" in a worked solution, and accuracy on them collapses under tight patch budgets. We propose novelty patching, motivated by LZ77-style compression: start a patch where the...
-
10
Multi-SFT: Permissively-Licensed Multilingual Instruction-Following
Daniela Baiamonte, Kamyar Zeinalipour, Elena Fano, Stefano Simonazzi, Andrea Zugarini
cs.CL · cs.AI
Supervised fine-tuning datasets remain overwhelmingly English-centric and commercially restricted, as their content is frequently generated by proprietary models whose terms of service forbid training competing systems. We introduce Multi-SFT, a commercially permissive collection of 502,818 instruction-response pairs across five European languages, built via translation and regeneration pipelines for tasks where translation is insufficient....
-
11
The Right Byte First: How UTF-16 Helps Multilingual Boundary Prediction
Hyunsik Kim
cs.CL · cs.LG
Many hierarchical byte-level language models group bytes into patches using a learned boundary predictor whose view of the next codepoint depends on encoding and lookahead. In UTF-8, codepoints of many scripts take three bytes: 8 of 24 bits mark length and continuation, and the first byte carries only 4 high codepoint bits. After the same left context, a mark extending a grapheme cluster and a letter starting the next can thus share their...
-
12
Priming Base Models for Agentic Post-Training: An Open Midtraining Recipe
Soumye Singhal, Joseph Jennings, Ka Shun Shum, Alexander Bukharin, Khushi Bhardwaj, Zirui Liu, Venkat Srinivasan,...
cs.CL · cs.AI · cs.LG
Frontier models, general-purpose and domain-specific alike, now include a midtraining stage between pretraining and post-training, but little has been published about how this stage is built. We present an open midtraining recipe that primes base models for agentic post-training, and we show its effectiveness on two Nemotron models of different sizes. Pretraining typically runs at short context and sees almost no agent interactions, while SFT...
-
13
In the Guise of Correction: How Framing and Cultural Adaptation Erode LLM Safety on Real-World Criminal Cases
Mohsinul Kabir, Md. Tariquzzaman, Karam S. R. Elradie, Polydoros Giannouris, Yuechen Jiang, Shaoxiong Ji, Sophia Ananiadou
cs.CL · cs.AI · cs.CY
Existing safety benchmarks rely largely on synthetic prompts with loosely grounded taxonomies and offer little focused analysis of severe crime categories. We introduce GUISE, a benchmark of criminal-assistance scenarios sourced from real-world cases and organised under a taxonomy from the UNODC International Classification of Crime for Statistical Purposes (ICCS). Each scenario is rendered under three linguistic framings and evaluated across...
-
14
Reliable Knowledge Acquisition for Continual Learning Agents
Yixu Huang, Jiaqi W. Ma
cs.CL · cs.AI · cs.LG
As agents powered by foundation models move into open-ended environments, continual learning from experience becomes essential. For agents built on models with fixed parameters, this learning requires reusing prior task experience in context to improve performance and efficiency on future tasks. Existing memory and experience-learning systems typically focus on either retained facts or procedures, and lack a mechanism for establishing the...
-
15
Retrieved but Not Read: Understanding Why Search-Augmented LLMs Fail to Use Available Evidence
Owen Walters, Lihu Chen, Francesca Toni
cs.CL · cs.AI · cs.IR
Web search allows LLMs to access up-to-date information, but it remains unclear why they sometimes produce outdated answers even when relevant evidence is available. To study this problem, we construct temporal facts whose values changed after the models' training cutoffs. We evaluate one proprietary model under deployed web search and six open-weight model configurations under controlled retrieval. We find that models often answer from...
-
16
ContextLift: Breaking the Spurious Correlation Behind Conditional Emergent Misalignment
Florian Mai, David Kaczér
cs.CL · cs.LG
Finetuning a language model on narrowly misaligned data can make it broadly misaligned. Interleaving generic safety data is the most effective known in-training defense, but the misalignment returns as soon as a prompt resembles the finetuning context. We argue that this conditional misalignment is a spurious correlation: in the training mix, the context of the finetuning domain occurs only with misaligned answers, so the model keys its...
-
17
Rethinking the Role of Tool Graph Memory in Multi-Turn Tool Use
Uiji Hwang, Richeng Xuan, Taeuk Kim
cs.CL · cs.AI
Large language model (LLM) agents solve complex tasks by calling external tools over multiple turns. Recent work has proposed tool graph memory, which stores past experience as tool transitions to guide subsequent selection. However, it remains unclear whether this component consistently improves agents' tool use or undermines it. We evaluate tool graph memory on nine models and two benchmarks, finding that it seldom improves significantly...
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.