cs.CL · 2026-05-25 · No. 9
Computation and Language, 2026-05-25.
21 new papers in cs.CL. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
21 entries-
01
OnePred: Next-Query Prediction via Recursive Intent Memory in Multi-Turn Conversations
Jiangwang Chen, Bowen Zhang, Zixin Song, Jiazheng Kang, Xiao Yang, Da Zhu, Guanjun Jiang
cs.CL · cs.AI
Although large language model (LLM) conversational systems process millions of multi-turn dialogues daily, they remain fundamentally reactive: they respond only after the user types a query. A key step toward proactive interaction is next-query prediction, which anticipates the user's subsequent query based solely on the preceding dialogue. Progress on this task is hindered by the lack of dedicated benchmarks and a fundamental...
-
02
SSDAU: Structured Semantic Data Augmentation for Joint Entity and Relation Extraction
Jiawei He, Mengyu Shi, Chunrong Fang
cs.CL · cs.AI
Joint Entity and Relation Extraction (JERE) is highly susceptible to weak generalization due to low-quality training data. Data augmentation is a common strategy to enhance model generalization across different domains. However, existing data augmentation methods often overlook text relevance and may disrupt semantic structures and dependencies, making it difficult to generate effective augmented data for improving model generalization. In...
-
03
Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation Signals
Sirui Chen, Lei Xu, Yuying Zhao, Yutian Chen, Yu Wang, Beier Zhu, Hanwang Zhang, Shengjie Zhao, Chaochao Lu
cs.CL · cs.AI
Recent RL methods have substantially improved the reasoning abilities of LLMs. Existing reward designs mainly follow two paradigms: (1) Reinforcement learning with verifiable rewards (RLVR) derives outcome signals from executable checks or ground-truth answers, but provides limited guidance for intermediate reasoning behaviors. (2) Rubrics-as-reward (RaR) goes beyond final-answer checking by using natural-language rubrics to assess reasoning...
-
04
Convergence Without Understanding: When Language Models Agree on Representations but Disagree on Reasoning
Muhammad Usama, Dong Eui Chang
cs.CL · cs.AI
Large language models trained under diverse objectives and architectures have been shown to develop increasingly similar internal representations, an observation formalized as the Platonic Representation Hypothesis. Whether this representational convergence extends to the reasoning processes that operate over shared representations remains untested. We evaluate representational similarity across 16 language models from 8 families (1.5B to 72B...
-
05
Positional Failures in Long-Context LLMs: A Blind Spot in Reasoning Benchmarks
Chuyifei Zhang, Hongyu Cui, Xiaowen Huang, Jitao Sang
cs.CL · cs.AI · cs.LG
Position-controlled evaluation is standard for retrieval tasks such as Needle-in-a-Haystack and RULER, but mainstream reasoning benchmarks do not control positional placement of target tasks in long contexts. We audit 11 long-context benchmarks and find none jointly controls task position, filler content, and context length for reasoning. An audit of four flagship long-context releases finds no main result-table entry for NIAH, RULER, or...
-
06
As X, Do Y: How Persona and Task Combine in Instruction-Tuned LLMs
Eric Xu
cs.CL · cs.AI
Role prompts of the form As X, do Y admit a clean linear decomposition at one specific site in the residual stream: the prompt-to-answer transition -- the last prompt token together with the first two generated tokens -- in an early/mid layer band. There, persona and task contribute through partially orthogonal additive directions. Forming a pure persona effect $Δ_X$, a pure task effect $Δ_Y$, and substituting $h_{BB} + Δ_X + Δ_Y$ for the...
-
07
A Fine-Tuned BERT Classifier for Personal-Letter Titles in Late-Ming and Early-Qing Collected Works
Queenie Luo
cs.CL · cs.AI · cs.CY · cs.DB
I present Lepton (Letter Prediction), a fine-tuned BERT classifier that predicts whether a title in a Classical Chinese wenji table of contents is a personal letter or a closely confusable preface (particularly the farewell-preface). Lepton fine-tunes bert-base-chinese on 5438 hand-labeled wenji titles from thirty-three late-Ming and early-Qing literati. I've deployed the model on Hugging Face and has been used at the China Biographical...
-
08
Model Collapse as Cultural Evolution
Dongxin Guo, Jikun Wu, Siu Ming Yiu
cs.CL · cs.AI · cs.LG
Model collapse, the progressive degradation of LLMs trained on their own outputs, has been characterized statistically but lacks a linguistic explanation for which structures degrade, in what order, and why. We show that iterated learning theory from cultural evolution fills this gap. We derive five falsifiable predictions, distinguish those uniquely discriminative for the theory from confirmatory ones, and test them by self-training...
-
09
DreamerNLplus: Interpretable Modeling of Mental Health Dynamics from Social Media Timelines using Hybrid Rule-Based and RAG Methods
Maryia Zhyrko, Daisy Monika Lal, Erik van Mulligen, Lifeng Han
cs.CL · cs.AI
We present DreamerNLplus, a hybrid framework for modeling mental health dynamics from social media timelines in the CLPsych 2026 shared task. Our system addresses three tasks: psychological state modeling, temporal change detection, and sequence-level summarization. For Task 1, we combine LLM-based data augmentation, DeBERTa classification, and Random Forest regression for structured state prediction. For Task 2, we use few-shot prompting...
-
10
Do Language Models Know What Not to Say? Causal Evidence for Statistical Preemption in LLMs
Dongxin Guo, Jikun Wu, Siu Ming Yiu
cs.CL · cs.AI · cs.LG
How do learners acquire knowledge of what is unacceptable without negative evidence? Construction Grammar proposes statistical preemption: exposure to a conventional form (e.g., "donated the books to the library") preempts structurally possible but unattested alternatives ("*donated the library the books"). We present a computational study that, for the first time, directly dissociates statistical preemption from the competing entrenchment...
-
11
Sparse Autoencoders Map Brain-LLM Alignment onto Cortical Semantic Topography
Dongxin Guo, Jikun Wu, Siu Ming Yiu
cs.CL · cs.AI · q-bio.NC
Intermediate layers of large language models (LLMs) best predict human brain responses to language, one of the most robust findings in computational neurolinguistics, yet why remains mechanistically unexplained. We address this gap by bridging sparse autoencoders (SAEs) from mechanistic interpretability with neural encoding models, decomposing GPT-2 XL and Llama-3.1-8B into 16K-32K interpretable features per layer. A human-validated taxonomy...
-
12
Brain-LLM Alignment Tracks Training Data, Not Typology
Dongxin Guo, Jikun Wu, Siu Ming Yiu
cs.CL · cs.AI · q-bio.NC
Brain-LLM alignment is well established in English, yet the brain's language network is neuroanatomically universal across languages. Does alignment also generalize cross-linguistically, and what governs the variation? We test this using fMRI data from 112 participants across English, Chinese, and French (the Le Petit Prince corpus) and seven LLMs spanning English-dominant, Chinese-dominant, and multilingual architectures. Our central finding...
-
13
A Proactive Multi-Agent Dialogue Framework for Assessing Social Language Disorder Traits in Autism
Chuanbo Hu, Minglei Yin, Bin Liu, Wenqi Li, Lynn K. Paul, Shuo Wang, Xin Li
cs.CL · cs.AI
Characteristic linguistic behaviors associated with Social Language Disorder (SLD) in autism spectrum disorder, including echoic repetition, pronoun displacement, and stereotyped media quoting, are largely absent from spontaneous conversation and only emerge under specific conversational conditions. In structured clinical assessments, this latency means that questioning strategy selection is a critical yet underappreciated determinant of how...
-
14
Memorization Dynamics of Fill-in-the-Middle Pretraining
Tobias von Arx, Tanguy Dieudonné
cs.CL · cs.AI · cs.LG
Fill-in-the-middle (FIM) is a pretraining objective widely used to equip causal language models with infilling ability, yet its effect on verbatim memorization remains underexplored. We study the memorization dynamics of FIM in a controlled setting by pretraining matched Llama 3.2 models with FIM and standard left-to-right (LTR) objectives on a FineWeb-Gutenberg corpus containing repeated Gutenberg excerpts. With prefix-based probes, FIM more...
-
15
Graph Alignment Topology as an Inductive Bias for Grounding Detection
Paul Landes, Pranav Herur, Adam Cross, Jimeng Sun
cs.CL · cs.AI
Large Language Models (LLMs) are optimized to produce distributionally plausible continuations rather than to explicitly verify whether generated propositions are entailed by source documents. This inductive bias enables generalization, but it does not encode whether responses are grounded with respect to a reference. These issues limit the use of LLMs in domains where strict factual correctness is crucial, such as clinical decision support....
-
16
Reducing Political Manipulation with Consistency Training
Long Phan, Devin Kim, Alexander Pan, Alice Blair, Adam Khoja, Dan Hendrycks
cs.CL · cs.AI
Large language models (LLMs) exhibit systematic political bias across a variety of sensitive contexts. We find that LLMs handle counterpart topics from opposing political sides asymmetrically. We refer to this phenomenon as covert political bias and identify 7 categories of techniques through which it operates. We propose two metrics for covert bias: Sentiment Consistency measures symmetry in rhetoric and framing across paired political...
-
17
Understanding Data Temporality Impact on Large Language Models Pre-training
Pilchen Hippolyte, Fabre Romain, Signe Talla Franck, Perez Patrick, Grave Edouard
cs.CL · cs.AI
Large language models (LLMs) are typically trained on shuffled corpora, yielding models whose knowledge is frozen at train time and whose temporal grounding remains poorly understood. In this work, we study the impact of pre-training dynamics on the acquisition of time-sensitive factual knowledge, focusing specifically on data ordering. Our main contributions are twofold. First, we introduce a comprehensive benchmark of over 7,000 temporally...
-
18
Moral Semantics Survive Machine Translation: Cross-Lingual Evidence from Moral Foundations Corpora
Maciej Skorski
cs.CL · cs.AI
Moral language is subtle and culturally variable, making it difficult to translate faithfully across languages. Idiomatic expressions, slang, and cultural references introduce hard-to-avoid translation artifacts. Yet automated moral values classification depends on language-specific annotated corpora that exist almost exclusively in English. We investigate whether LLM-based translation can bridge this gap, taking Polish as a test case. Using...
-
19
More Context, Larger Models, or Moral Knowledge? A Systematic Study of Schwartz Value Detection in Political Texts
Víctor Yeste, Paolo Rosso
cs.CL · cs.AI · cs.LG
Detecting Schwartz values in political text is difficult because implicit cues often depend on surrounding arguments and fine-grained distinctions between neighboring values. We study when context and explicit moral knowledge help sentence-level value detection. Using the ValuesML/Touché ValueEval format, we compare sentence, window, and full-document inputs; no-RAG and retrieval-augmented settings with a curated moral knowledge base;...
-
20
Agentic CLEAR: Automating Multi-Level Evaluation of LLM Agents
Asaf Yehudai, Lilach Eden, Michal Shmueli-Scheuer
cs.CL · cs.AI
Agentic systems are becoming more capable: agents define strategies, take actions, and interact with different environments. This autonomy poses serious challenges for overseeing and assessing agent behavior. Most current tools are limited, focusing on observability with basic evaluation capabilities or imposing static, hand-crafted error taxonomies that cannot adapt to new domains. To address this gap, we present Agentic CLEAR, an automatic,...
-
21
Beyond Temperature: Hyperfitting as a Late-Stage Geometric Expansion
Meimingwei Li, Yuanhao Ding, Esteban Garces Arias, Christian Heumann
cs.CL · cs.AI · stat.ML
Recent work has identified a counterintuitive phenomenon termed "Hyperfitting", where fine-tuning Large Language Models (LLMs) to near-zero training loss on small datasets surprisingly enhances open-ended generation quality and mitigates repetition in greedy decoding. While effective, the underlying mechanism remains poorly understood, with the extremely low-entropy output distributions suggesting a potential equivalence to simple temperature...
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.