pith. sign in

archive

Every paper Pith has read. Search by title, abstract, or pith.

7661 papers in cs.CL · page 15

  1. cs.CL 2026-05-14 reviewed
    Geometry scores pick shallow layers for diffusion insertion in transformers

    Where Should Diffusion Enter a Language Model? Geometry-Guided Hidden-State Replacement

    Injin Kong +2

  2. cs.CL 2026-05-14 reviewed
    Semantic RL adds low-resource languages without erasing prior skills

    Reinforcement Learning with Semantic Rewards Enables Low-Resource Language Expansion without Alignment Tax

    Zeli Su +9

  3. cs.HC 2026-05-14 reviewed
    Short concern texts track with activity drops and sleep issues

    A Formative Study of Brief Affective Text as a Complement to Wearable Sensing for Longitudinal Student Health Monitoring

    Tamunotonye Harry +9

  4. cs.CL 2026-05-14 reviewed
    LLM filter and clustering finds 41 manipulative narrative clusters

    LLM-based Detection of Manipulative Political Narratives

    Sinclair Schneider +2

  5. cs.CL 2026-05-14 reviewed
    Prompt filter and clustering finds 41 narrative clusters

    LLM-based Detection of Manipulative Political Narratives

    Sinclair Schneider +2

  6. cs.CL 2026-05-14 reviewed
    Transformers score German texts on left-right scale

    Ideology Prediction of German Political Texts

    Sinclair Schneider +3

  7. cs.LG 2026-05-14 reviewed
  8. cs.CL 2026-05-14 reviewed
    Exact prefix factorization removes errors in diffusion language models

    Factorization-Error-Free Discrete Diffusion Language Model via Speculative Decoding

    Xun Fang +3

  9. cs.LG 2026-05-14 reviewed
    Minimal KV scorer tweak beats complex cache redesigns

    Minimal-Intervention KV Retention via Set-Conditioned Diversity

    Libo Sun +3

  10. cs.LG 2026-05-14 reviewed
    Simple diversity penalty in KV scorer beats complex designs

    Minimal-Intervention KV Retention via Set-Conditioned Diversity

    Libo Sun +3

  11. cs.CR 2026-05-14 reviewed
    Hidden noise stops vision-language models learning real content

    To See is Not to Learn: Protecting Multimodal Data from Unauthorized Fine-Tuning of Large Vision-Language Model

    Chengshuai Zhao +4

  12. cs.CR 2026-05-14 reviewed
    Web agents should plan before seeing page content

    Web Agents Should Adopt the Plan-Then-Execute Paradigm

    Julien Piet +7

  13. cs.LG 2026-05-14 reviewed
    MetaMoE combines independently trained expert models into one Mixture-of-Experts system…

    MetaMoE: Diversity-Aware Proxy Selection for Privacy-Preserving Mixture-of-Experts Unification

    Weisen Jiang +2

  14. cs.CL 2026-05-14 reviewed
    Agent harnesses break rules mid-task despite safe final answers

    Auditing Agent Harness Safety

    Chengzhi Liu +10

  15. cs.CL 2026-05-14 reviewed
    Agent harnesses allow unsafe actions even with correct final outputs

    Auditing Agent Harness Safety

    Chengzhi Liu +10

  16. cs.AI 2026-05-14 reviewed
    Hypergraph reasoner hits 94.7% on supply chain RCA

    Hypergraph Enterprise Agentic Reasoner over Heterogeneous Business Systems

    Ling Wang +10

  17. cs.CL 2026-05-14 reviewed
    Spelling and test design confound KVL word difficulty ratings

    Sakura at BEA 2026 Shared Task 1: What Makes Vocabulary Difficult?

    Adam Nohejl +5

  18. cs.CL 2026-05-14 reviewed
    LLM rates vocab difficulty at r > 0.91

    Sakura at BEA 2026 Shared Task 1: What Makes Vocabulary Difficult?

    Adam Nohejl +5

  19. cs.LG 2026-05-14 reviewed
    Active learners raise NDCG@10 per call in PRP reranking

    Active Learners as Efficient PRP Rerankers

    Jerem\'ias Figueiredo Paschmann +5

  20. cs.LG 2026-05-14 reviewed
    Active rankers lift NDCG@10 per call in PRP reranking

    Active Learners as Efficient PRP Rerankers

    Jerem\'ias Figueiredo Paschmann +5

  21. cs.LG 2026-05-14 reviewed
    Transformer predicts next disease with 0.871 median AUC across 896 categories

    DT-Transformer: A Foundation Model for Disease Trajectory Prediction on a Real-world Health System

    Yunying Zhu +3

  22. cs.LG 2026-05-14 reviewed
    Small mismatches in LLM RL rollout and optimization cause collapse

    Diagnosing Training Inference Mismatch in LLM Reinforcement Learning

    Tianle Zhong +7

  23. cs.LG 2026-05-14 reviewed
    Prefill-only adapters deliver 1.9x throughput for 512 users

    PreFT: Prefill-only finetuning for efficient inference

    Andrew Lanpouthakoun +6

  24. cs.CL 2026-05-13 reviewed
    Filter drops harmful examples to hold LLM attack rate below 6 percent

    GradShield: Alignment Preserving Finetuning

    Zhanhao Hu +6

  25. cs.CL 2026-05-13 reviewed
    RAG succeeds when evidence flows deeper and more distributed

    Why Retrieval-Augmented Generation Fails: A Graph Perspective

    Kai Guo +7

  26. quant-ph 2026-05-13 reviewed
    Engineered texts recover exact backbones on 100-atom quantum processor

    QOuLiPo: What a quantum computer sees when it reads a book

    Christophe Jurczak

  27. cs.IR 2026-05-13 reviewed
    Imagined future steps triple recall of distant memories

    Thinking Ahead: Prospection-Guided Retrieval of Memory with Language Models

    Harshita Chopra +4

  28. cs.CL 2026-05-13 reviewed
    Search-based bookmarks beat summarization for role-play memory

    BOOKMARKS: Efficient Active Storyline Memory for Role-playing

    Letian Peng +6

  29. cs.CL 2026-05-13 reviewed
    Safety refusals rise with Korean language but drop with Korean context

    ROK-FORTRESS: Measuring the Effect of Geopolitical Transcreation for National Security and Public Safety

    Michael S. Lee +15

  30. cs.CL 2026-05-13 reviewed
    Distance and direction encode relations in LLM embeddings

    Polar probe linearly decodes semantic structures from LLMs

    Pablo J. Diego-Sim\'on +4

  31. cs.CL 2026-05-13 reviewed
    LLMs encode relations as distances and directions in embeddings

    Polar probe linearly decodes semantic structures from LLMs

    Pablo J. Diego-Sim\'on +4

  32. cs.LG 2026-05-13 reviewed
    Routed small models add value to AlphaEarth on hydrology questions

    Mini-JEPA Foundation Model Fleet Enables Agentic Hydrologic Intelligence

    Mashrekur Rahman

  33. cs.CL 2026-05-13 reviewed
    LLM with verifiable RL rewards meets room sizes and connections

    Generative Floor Plan Design with LLMs via Reinforcement Learning with Verifiable Rewards

    Luis Lara +7

  34. cs.CL 2026-05-13 reviewed
    Reversing conflicting document order flips 11-25% of LLM answers

    When Evidence Conflicts: Uncertainty and Order Effects in Retrieval-Augmented Biomedical Question Answering

    Yikun Han +2

  35. stat.ML 2026-05-13 reviewed
    Conformal method bounds confident errors in CoT reasoning

    Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning

    Yu Gu +3

  36. cs.CL 2026-05-13 reviewed
    DExperts blocks explicit toxicity but slips on implicit hate speech

    Measuring and Mitigating Toxicity in Large Language Models: A Comprehensive Replication Study

    Mokshit Surana +2

  37. cs.CL 2026-05-13 reviewed
    DExperts hits 100% safety on explicit toxicity but drops on implicit

    Measuring and Mitigating Toxicity in Large Language Models: A Comprehensive Replication Study

    Mokshit Surana +2

  38. cs.SE 2026-05-13 reviewed
    Constrained edits merge checkpoints to lift code agent scores

    CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing

    Mingzhi Zhu +3

  39. cs.LG 2026-05-13 reviewed
    Cosine similarity misleads on which layers matter in LLMs

    Rethinking Layer Relevance in Large Language Models Beyond Cosine Similarity

    Cristian Hinostroza +6

  40. cs.CL 2026-05-13 reviewed
    Adaptive weights fix distribution drift in LLM reasoning distillation

    Distribution Corrected Offline Data Distillation for Large Language Models

    Yumeng Zhang +3

  41. eess.AS 2026-05-13 reviewed
    Benchmark standardizes early Parkinson's speech detection

    A Benchmark for Early-stage Parkinson's Disease Detection from Speech

    Terry Yi Zhong +5

    2 Piths
  42. cs.AI 2026-05-13 reviewed
    Early rejection cuts LLM synthetic data tokens by 11-77%

    Know When To Fold 'Em: Token-Efficient LLM Synthetic Data Generation via Multi-Stage In-Flight Rejection

    Anjir Ahmed Chowdhury +2

  43. cs.CL 2026-05-13 reviewed
    Dual RL agents learn to probe like Supreme Court justices

    Dual Hierarchical Dialogue Policy Learning for Legal Inquisitive Conversational Agents

    Xubo Lin +4

  44. cs.CL 2026-05-13 reviewed
    Dual RL agents learn to probe like Supreme Court justices

    Dual Hierarchical Dialogue Policy Learning for Legal Inquisitive Conversational Agents

    Xubo Lin +4

  45. cs.CL 2026-05-13 reviewed
    New method lifts multi-task LLM accuracy by 6.67 percent

    PEML: Parameter-efficient Multi-Task Learning with Optimized Continuous Prompts

    Anjir Ahmed Chowdhury +4

  46. cs.CL 2026-05-13 reviewed
    Logic rules in prompts cut RAG errors via derivation trees

    Derivation Prompting: A Logic-Based Method for Improving Retrieval-Augmented Generation

    Ignacio Sastre +2

  47. cs.AI 2026-05-13 reviewed
    Formal checks can keep AI legal reasoning inside the text

    Bridging Legal Interpretation and Formal Logic: Faithfulness, Assumption, and the Future of AI Legal Reasoning

    Olivia Peiyu Wang +1

  48. cs.CL 2026-05-13 reviewed
    Audited data lifts 8B model 18 points on physics olympiads

    Physics-R1: An Audited Olympiad Corpus and Recipe for Visual Physics Reasoning

    Shan Yang

  49. cs.LG 2026-05-13 reviewed
    Learned predictor prunes KV cache 3-10x on the fly

    Self-Pruned Key-Value Attention: Learning When to Write by Predicting Future Utility

    Gergely Szilvasy (1) +10

  50. cs.AI 2026-05-13 reviewed
    Unary recoding enables polynomial-time rule learning for LLMs

    Enhanced and Efficient Reasoning in Large Learning Models

    Leslie G. Valiant