arXiv cs.CL

Computation and Language daily digest.

53 past editions, oldest first by date. Atom feed → · all categories

01 — Past editions

most recent first

2026-07-19 SciDiagramEdit: Learning to Edit Scientific Diagrams from Paper Revisions 15 papers · No. 58
2026-07-18 SciDiagramEdit: Learning to Edit Scientific Diagrams from Paper Revisions 15 papers · No. 57
2026-07-17 SciDiagramEdit: Learning to Edit Scientific Diagrams from Paper Revisions 15 papers · No. 56
2026-07-16 Analogical Deep Research: Retrieving and Integrating Historical Analogies... 13 papers · No. 55
2026-07-15 PalmClaw: A Native On-Device Agent Framework for Mobile Phones 13 papers · No. 54
2026-07-14 Metacognition in LLMs: Foundations, Progress, and Opportunities 14 papers · No. 53
2026-07-13 Task-Specific Multimodal Question Answering Agents via Confidence... 14 papers · No. 52
2026-07-12 Validity of LLMs as data annotators: AMALIA on authority 22 papers · No. 51
2026-07-11 Validity of LLMs as data annotators: AMALIA on authority 22 papers · No. 50
2026-07-10 Validity of LLMs as data annotators: AMALIA on authority 22 papers · No. 49
2026-07-09 Accurate, Interdisciplinary and Transparent Structure-property Understanding... 15 papers · No. 48
2026-07-08 RSF-GLLM: Bridging the Semantic Gap in Multi-Hop Knowledge Graph QA via... 19 papers · No. 47
2026-07-07 SPEARBench: A Benchmark for Naturalness Evaluation in Streaming... 16 papers · No. 46
2026-07-06 LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning 13 papers · No. 45
2026-07-05 LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning 13 papers · No. 44
2026-07-04 LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning 13 papers · No. 43
2026-07-03 LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning 13 papers · No. 42
2026-07-02 Measuring the Gap Between Human and LLM Research Ideas 18 papers · No. 41
2026-07-01 Introspective Coupling: Self-Explanation Training Tracks Behavioral Change... 14 papers · No. 40
2026-06-30 Uncertainty-Aware Generation and Decision-Making Under Ambiguity 11 papers · No. 39
2026-06-29 Cognitive Episodes in LLM Reasoning Traces Enable Interpretable Human Item... 25 papers · No. 38
2026-06-28 Empowering GUI Agents via Autonomous Experience Exploration and Hindsight... 17 papers · No. 37
2026-06-27 Empowering GUI Agents via Autonomous Experience Exploration and Hindsight... 17 papers · No. 36
2026-06-26 Empowering GUI Agents via Autonomous Experience Exploration and Hindsight... 17 papers · No. 35
2026-06-25 Same Evidence, Different Answer: Auditing Order Sensitivity in Multimodal... 20 papers · No. 34
2026-06-24 L3Cube-MahaPOS: A Marathi Part-of-Speech Tagging Dataset and BERT Models 23 papers · No. 33
2026-06-23 War in the Abstract: The Rise and Consequences of Militarized Language in... 11 papers · No. 32
2026-06-22 Your Mouse and Eyes Secretly Leak Your Preference: LLM Alignment using... 9 papers · No. 31
2026-06-21 Your Mouse and Eyes Secretly Leak Your Preference: LLM Alignment using... 9 papers · No. 30
2026-06-20 Your Mouse and Eyes Secretly Leak Your Preference: LLM Alignment using... 9 papers · No. 29
2026-06-19 Your Mouse and Eyes Secretly Leak Your Preference: LLM Alignment using... 9 papers · No. 28
2026-06-18 Freeing the Law with LOCUS: A Local Ordinance Corpus for the United States 18 papers · No. 27
2026-06-17 ReproRepo: Scaling Reproducibility Audits with GitHub Repository Issues 10 papers · No. 26
2026-06-16 KVEraser: Learning to Steer KV Cache for Efficient Localized Context Erasing 19 papers · No. 25
2026-06-15 SIMMER: Benchmarking Latent Failures in LLM Executable Planning with a World Model 8 papers · No. 24
2026-06-14 Learning to Reason by Analogy via Retrieval-Augmented Reinforcement Fine-Tuning 14 papers · No. 23
2026-06-13 Learning to Reason by Analogy via Retrieval-Augmented Reinforcement Fine-Tuning 14 papers · No. 22
2026-06-12 Learning to Reason by Analogy via Retrieval-Augmented Reinforcement Fine-Tuning 14 papers · No. 21
2026-06-11 Context-Driven Incremental Compression for Multi-Turn Dialogue Generation 16 papers · No. 20
2026-06-10 Provenance-Grounded Gating and Adaptive Recovery in Synthetic Post-Training... 16 papers · No. 19
2026-06-09 Data Synthesis and Parameter-Efficient Fine-Tuning for Low-Resource NMT: A... 13 papers · No. 18
2026-06-08 How reliable are LLMs when it comes to playing dice? 15 papers · No. 17
2026-06-07 Operation-Guided Progressive Human-to-AI Text Transformation Benchmark for... 19 papers · No. 16
2026-06-06 Operation-Guided Progressive Human-to-AI Text Transformation Benchmark for... 19 papers · No. 15
2026-06-05 Operation-Guided Progressive Human-to-AI Text Transformation Benchmark for... 19 papers · No. 14
2026-06-02 From Layers to Submodules: Rethinking Granularity in Replacement-Based LLM... 18 papers · No. 13
2026-05-30 LLMSurgeon: Diagnosing Data Mixture of Large Language Models 17 papers · No. 12
2026-05-28 OmniVerifier-M1: Multimodal Meta-Verifier with Explicit Structured Recalibration 19 papers · No. 11
2026-05-27 It's Not Always Sycophancy: Measuring LLM Conformity as a Function of... 30 papers · No. 10
2026-05-25 OnePred: Next-Query Prediction via Recursive Intent Memory in Multi-Turn... 21 papers · No. 9
2026-05-23 Reducing Political Manipulation with Consistency Training 15 papers · No. 8
2026-05-22 Reducing Political Manipulation with Consistency Training 15 papers · No. 7
2026-05-21 Attention Is All You Need 3 papers · No. 3

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.