cs.CL · 2026-11-14 · No. 171

Computation and Language, 2026-11-14.

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
  1. 01

    ArchSpace: Recording, Reviewing, and Referencing LLM Architecture Research

    Jie Wang, Tong Zhu, JiaHao Kuang, Zhe Xu, Yunkai Chai, Dehong Zheng, Yu Cheng, Tao Ji, ZhouHan Lin, Qi Zhang, Bowen Zhou

    cs.CL · cs.LG

    Model architecture shapes the scaling behavior, training efficiency, and inference cost of LLMs, making it a central focus of both industry and academia. In industry, teams such as those behind DeepSeek, Qwen, and Kimi routinely introduce architectural innovations, yet public reports rarely document which ideas succeeded, which were abandoned, and why. In academia, limited compute and inconsistent baselines often restrict evaluations to...

    arxiv.org/abs/2611.17332 · PDF

  2. 02

    Goal Encoding in LLMs

    Arnab Sen Sharma, Eric Todd, Sheridan Feucht, Andy Arditi, Rohit Gandikota, Natalie Shapira, Gabriele Sarti,...

    cs.CL · cs.AI · cs.LG

    We investigate whether and how LLMs encode goals: internal neural representations that precede and guide action, and that are flexible enough to be realized through many different execution paths. We construct a coding setting with multiple sub-tasks that allows us to evaluate goal-seeking behavior and the selection of sub-goals. In this setting, we localize an encoding of the next sub-goal in the outputs of a sparse set of attention heads....

    arxiv.org/abs/2611.17297 · PDF

  3. 03

    Synthesis Smuggling: Maliciously Hiding Inferred Personal Attributes in LLM Outputs

    Gautam Galada, Supreeth Shastri, Sagnik Ray Choudhury

    cs.CL · cs.AI

    We propose Synthesis Smuggling, a novel threat model in which an adversarial LLM infers sensitive information about a user from routine assistance-seeking interactions and steganographically encodes that into innocuous-looking model-generated content. The user may then unknowingly transmit that information by sharing the generated artifact, say as an email, social-media post, or message, through ordinary communication channels. An adversary...

    arxiv.org/abs/2611.17280 · PDF

  4. 04

    Parsed, Plausible, Wrong: Output Format Controls Silent Errors in Small-Model Semantic Parsing

    Umar Ahmed, Maxim Dunaev, Mohammad Nour Al Awad, Sergey Ivanov, Ivan Khodnenko

    cs.CL · cs.LG

    A small fine-tuned parser that emits a well-formed but wrong tree fails silently: nothing downstream can tell. We ask whether the output format, a free design choice, controls how often this happens. On the PIZZA ordering benchmark we fine-tune two sub-billion models (Qwen3.5-0.8B and LFM2.5-350M) with LoRA on six lossless encodings of the same target tree, from 44.3 down to 10.9 tokens per order, including two matched-length pairs that vary...

    arxiv.org/abs/2611.17169 · PDF

  5. 05

    Parameter-Efficient Conciseness Adaptation: Differentiable Length Control for Concise Clinical Reasoning in Smaller Language Models

    Tanzeel Abbas, Ahmad Kamran Malik, Nafees Qamar, Sana Liaqat

    cs.CL · cs.AI

    Smaller language models (SLMs) make it feasible to deploy clinical natural language processing where large proprietary models are too costly, and parameter-efficient fine-tuning allows them to be specialised on commodity hardware. One obstacle persists after training: on medical tasks these models answer at far greater length than the clinical question requires. In clinical decision support and point-of-care use, where time is short, such...

    arxiv.org/abs/2611.17128 · PDF

  6. 06

    Discovering Effective Agent Memory Designs through Program Evolution

    Xinheng Ding, Seyyed Saeid Cheshmi, Ziyang Zhang, Tairan Chen, Wenya Xie, Yu Hou, Rui Zhang, Zirui Liu

    cs.CL · cs.AI

    Program evolution provides a promising approach to discover agent memory designs and study the choices underlying their effectiveness. We introduce MAPE, a framework that evolves whole memory programs from minimal seeds through a standardized lifecycle interface and an iterative diagnosis-proposal loop. Experiments on LoCoMo and LongMemEval yield an absolute accuracy gain of up to 12% over manually designed baselines at 35% of the serving...

    arxiv.org/abs/2611.17068 · PDF

  7. 07

    Evaluating Pretrained Language Semantics for Structured EHR Prediction Tasks

    Ashvin Gupta, Brendan Delaney, Alessandra Russo

    cs.CL · cs.LG

    Structured Electronic Health Records (EHR) models typically treat each clinical concept as a dataset-specific token, discarding the natural-language semantics associated with the event. As a result, relationships between concepts must largely be learned from EHR co-occurrence, without directly exploiting any prior semantic knowledge. We investigate how pretrained causal language models can be adapted for longitudinal EHR prediction by...

    arxiv.org/abs/2611.17053 · PDF

  8. 08

    Auditing AI peer reviewers: a benchmark on real scientific papers

    Íñigo Zubeldia, Boris Bolliet, Francisco Villaescusa-Navarro, Pablo Villanueva-Domingo, Miles Cranmer

    cs.CL · astro-ph.IM · cs.AI · cs.DL

    LLM-based peer review is now used at production scale, but its evaluation remains limited. We introduce a benchmark that injects objective, localisable errors of four types (general issues, mathematics, numerics, citations) at three severity levels into real papers and measures each reviewer's detection rate by error type and severity, together with its false-positive rate on clean copies. We also present Skepthical, a multi-agent reviewer...

    arxiv.org/abs/2611.17052 · PDF

  9. 09

    Lara Mini Base: Language Diversity as a Resource, Not a Trade-off

    Translated, Maria Pia Adinolfi, Isabelle Andrieu, Grazia Fiorella Anfuso, Melania Annunziata, Daniele Antonini,...

    cs.CL · cs.AI

    General-purpose language models are trained mostly on English: over open models we review, at most, non-English pretraining data makes up only a 12% share. Models built for European languages give them far more, but score well below general-purpose models of the same size. A common concern is that, in small models, languages compete for capacity. We present Lara Mini base, a model trained from scratch on 6T tokens in English and 44 other...

    arxiv.org/abs/2611.16956 · PDF

  10. 10

    SPADE: Soft Prompts for Ai-text DEtection

    Alex Jiang, Didier Schwab, Chuyuan Li

    cs.CL · cs.AI

    The easy access to Large Language Models (LLMs) has made AI-generated texts on the web increasingly ubiquitous, making AI-text detection a crucial task. Prompts greatly influence the generation process, but existing detectors focus solely on the generated texts --- supervised methods learn from labeled texts only, and zero-shot methods rely on the text's probability distributions --- ignoring the underlying generation process, which limits...

    arxiv.org/abs/2611.16929 · PDF

  11. 11

    Human or Synthetic? What a Fixed Budget Buys for Post-Training

    Shourik Banerjee, Ethan Mendes, Mohit Raghavendra, Wei Xu, Alan Ritter

    cs.CL · cs.LG

    Post-training of large language models typically combines supervised fine-tuning (SFT) with preference-based fine-tuning such as Direct Preference Optimization (DPO). Human-annotated and synthetically generated preference data differ substantially in per-sample cost, but prior work typically holds sample count fixed when comparing the two. In this work, we explicitly study the interplay between cost and performance by comparing the effect of...

    arxiv.org/abs/2611.16895 · PDF

  12. 12

    Pretraining Data Statistics Shape the Phases of Learning Entity Comparison in Language Models

    Yik Siu Chan, Jing Huang, Yanai Elazar, Atticus Geiger

    cs.CL · cs.LG

    How does data shape language model (LM) behavior throughout pretraining? We investigate this question through a case study on entity comparison, e.g., Between France and Brazil, which country is larger?, across nine comparison tasks spanning five entity types. We begin with controlled experiments in which we train small LMs (163M parameters) on mixtures of natural text from pretraining corpora and synthetic task data. Our analysis identifies...

    arxiv.org/abs/2611.16882 · PDF

  13. 13

    MuSeToM: Multi-Sensory Evaluation of Belief Revision with Textual Cues Across Six Senses

    Chunkit Chan, Kawai Chung, Sze Heng Douglas Kwok, Yuxuan Liu, Yauwai Yim, Tianshi Zheng, Haochen Shi, Qing Zong,...

    cs.CL · cs.AI

    Theory of Mind (ToM), the ability to infer mental states in others, is pivotal for human social cognition. Existing evaluations of ToM in large language models (LLMs) mainly focus on static belief attribution and false-belief reasoning, leaving a critical aspect of social reasoning underexplored: can LLMs decide whether perceptual evidence is sufficient to justify another person's belief revision? To address this gap, we present MuSeToM, a...

    arxiv.org/abs/2611.16662 · PDF

  14. 14

    Where in the Input Does a One-Pass Decision Encoder Look?

    Mohammed Nayeem Khan, Allan Kevin T

    cs.CL · cs.AI

    Laya is a small model that answers a multiple-choice question about a text in one pass: the question, the options (each with a name and a description) and the text form one sequence of at most 512 tokens, the window, in the English release. A longer text is silently cut at the end, and we measure what that costs. Test documents place a held-out row's text, the evidence, at a chosen token offset among distractor text; 177 items, five tasks,...

    arxiv.org/abs/2611.16477 · PDF

  15. 15

    Beyond Compressing Everything: Contrastive Memory Learning for Selective Context Compression

    Sikui Zhang, Haowei Liu, Ziyun Gan, Chunfeng Yuan, Guangze Gao, Nian Liu, Boyu Cai, Bo Li, Xiaolei Lv, Jun Gao, Bing...

    cs.CL · cs.AI

    As large language models (LLMs) advance toward increasingly long inputs, soft context compression offers a promising approach to efficient inference by converting long inputs into compact memory slots. Under limited memory budgets, effective context compression remains challenging because task-relevant evidence varies substantially across queries, ranging from localized evidence to multiple distant spans or information dispersed throughout...

    arxiv.org/abs/2611.16384 · 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.