cs.CL · 2026-10-13 · No. 142
Computation and Language, 2026-10-13.
6 new papers in cs.CL. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
6 entries-
01
Task Context Shapes Component Roles in Language Models
Sovesh Mohapatra, Dani S Bassett
cs.CL · cs.AI
Large language models reuse the same attention heads across tasks, but identifying these shared heads does not explain what they do differently in each task. A natural source of inspiration is task-dependent interactions among shared brain regions, which motivate a network view of language-model computation. Here, we compare fixed model components across tasks using identical graph facts, statements specifying which directed connections are...
-
02
Inject a Turn, Not a Token: Learning Where to Redirect LLM Reasoning for Self-Correction
Jiwon Jeon, Myungsik Cho, Jeonghye Kim, Youngchul Sung
cs.CL · cs.AI
Large language models struggle to reliably identify and correct errors in their own reasoning. Unlike prior training-based approaches that fine-tune an LLM to generate revisions or feedback, we learn where to intervene in failed rollouts and determine how to redirect them. To choose where to intervene, we train a 130K-parameter MLP head on a frozen encoder using only final-answer correctness. For redirection, we find that under a fixed...
-
03
Overcoming Data Imbalances with Expert Selection Biases
Ayush K. Tarun, Clara Meister, Antoine Bosselut
cs.CL · cs.LG
Mixture-of-Experts (MoE) models have become the standard architecture for frontier LLMs. The multiple parallel experts in each transformer block theoretically enable expert specialization according to categories such as domains, languages, or modalities during pretraining. However, when data is imbalanced across categories, minority categories can become concentrated in a small fraction of the expert pool or spread inefficiently across them,...
-
04
Agreement Without Alignment: Label-Free Rubric Clarification Increases LLM-Judge Consensus but Not Agreement with Humans
Sangdo Han, Moonsoo Kim
cs.CL · cs.AI
LLM judges are increasingly deployed as panels, and disagreement among panel members is often read as a symptom of an unclear rubric. We test a label-free procedure that turns this disagreement into rubric repairs. The procedure decomposes each rubric into sub-criteria, ranks them by cross-judge disagreement on a development split, and has an editor model rewrite only the most contested ones. An additional stage that moves text-checkable...
-
05
Do Prompt Optimizers Break Requirements They Are Not Scored On? A Preregistered Study
Sangdo Han, Moonsoo Kim
cs.CL · cs.LG
Prompt optimizers rewrite a prompt to raise one target metric, but prompts also state requirements the metric does not score, such as an output format, citations, or abstention. In a preregistered study, we run GEPA, MIPROv2, and TextGrad on HotpotQA, SQuAD 2.0, and IFEval and count per-item violations of unscored requirements with deterministic checks. By the preregistered criterion, all three optimizers produce regressions, substantially on...
-
06
How Reliable are AMR Parser Outputs? Uncertainty Estimation for AMR Parsing
Anuj Kumar, Shintaro Ozaki, Yamuna Prasad, Katsuhiko Hayashi, Hidetaka Kamigaito, Taro Watanabe
cs.CL · cs.AI
Recent advances have significantly improved the performance of Abstract Meaning Representation (AMR) parsers, yet determining when their outputs can be trusted remains largely unexplored. This work presents the first study of uncertainty estimation for AMR parsers in a black-box setting using top-k beam-search candidates. Uncertainty is estimated from pairwise candidate similarities and evaluated using the Prediction Rejection Ratio. This...
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.