cs.CL · 2026-10-05 · No. 134

Computation and Language, 2026-10-05.

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
  1. 01

    FALCON: A Model and Dataset Agnostic Framework for Synthetic Data Generation for NL2SQL Pairs

    Darian Lee, Shannon Rumsey, Jack St. Clair, Xinyi Tang, Aditya Bansal, Yuanming Shi

    cs.CL · cs.DB · cs.LG

    Relational databases are among the most widely deployed forms of structured knowledge, and natural language access to them requires grounding language onto schema entities and relations while handling the ambiguity inherent in how people phrase requests. Existing synthetic NL-to-SQL data generation methods largely ignore this ambiguity and produce oversimplified queries that fail to prepare models for the complexity of real-world structured...

    arxiv.org/abs/2610.03625 · PDF

  2. 02

    SyntaxBench: A Statistical Diagnostic Framework for Character-Level Reasoning in Large Language Models

    Mohsen Larni, Sobhan Ebrahimi Azar, Pouyan Nahed, Kazem Taghva

    cs.CL · cs.AI · cs.LG

    Large language models are increasingly used where small syntactic errors matter, yet character-level reasoning is still evaluated mostly through isolated probes and aggregate accuracy. We introduce SyntaxBench, a diagnostic benchmark and statistical evaluation framework for character-level reasoning. It contains five core tasks, character counting, letter containment, palindrome detection, edit distance, and longest-string selection, plus...

    arxiv.org/abs/2610.03329 · PDF

  3. 03

    Not Until the Evidence Says So: Teaching LLM Investigators When to Close a Case

    Tingzhu Bi, Ping Wang, Meng Ma

    cs.CL · cs.AI · cs.LG

    Accident, defect and outage investigations end with a decision that ordinary question answering never faces: whether the evidence gathered so far is enough to close the case. We study this decision for LLM investigators, which request evidence from a case file, revise their hypotheses, and either close the case with a conclusion grounded in what they read or leave it open and name what is missing. This judgment does not come with capability:...

    arxiv.org/abs/2610.03190 · PDF

  4. 04

    Predicting Steering Vectors and Adapter Weights for Few-Shot Author-Style Transfer

    Leonard Popp, Danni Liu, Supriti Sinhamahapatra, Jan Niehues

    cs.CL · cs.AI

    Adapting large language models to an individual author's style from a few examples is challenging, and scientific writing sharpens the difficulty: formal conventions leave little surface variation, and authors write about their own topics, so extracted ``style'' easily entangles with content. We study style-conditioned abstract generation from a few example abstracts per author and propose three methods: (1) contrastive activation steering,...

    arxiv.org/abs/2610.03163 · PDF

  5. 05

    Ask, Relax, or Act? Evaluating Actionable Indeterminacy in LLM Preference Reasoning

    Ang Li, Yue Lin, Feifei Kou, Zhan Su, Prayag Tiwari, Wenhao Li, Shuhui Zhu, Hongyuan Zha, Baoxiang Wang

    cs.CL · cs.AI

    An LLM agent can recognize uncertainty yet still choose the wrong next step: asking when action is already justified, or seeking clarification when the constraints must change. We formalize actionable indeterminacy: act when an accepted action is shared across all admissible preferences or objectives, clarify when each possibility is feasible but no action is shared, and propose a minimum-cost permitted constraint repair when the request is...

    arxiv.org/abs/2610.03102 · PDF

  6. 06

    HyperThink: Text-to-Parameter Hypernetworks for Efficient Reasoning

    Donggyun Kim, Jack Lu, Chanwoo Kim, Mengye Ren, Seunghoon Hong

    cs.CL · cs.LG

    Long-form thinking traces can substantially improve the multi-step reasoning performance of large language models (LLMs), but they introduce high inference-time overhead, with latency dominated by sequential decoding. We propose HyperThink, a text-to-parameter approach that amortizes this reasoning computation into a single query-conditioned parameter update: a lightweight hypernetwork reads the question and predicts updates to a small subset...

    arxiv.org/abs/2610.03039 · 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.