LLM Abstention

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

11 papers in the last four weeks, up 120% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 61

All topics

TIPS: Topological Ill-Posedness Probing and Steering in Large Language Models
Jun 22, 2026Guangyu Jiang, Sizhe Tang, Mahdi Imani +2Language Model Steering Question Answering
The George Washington University · Northeastern University
Coherence Under Commitment: Probing Generalization and Vacuous Memorization in LLM Logical Reasoning
Jun 19, 2026Noor Islam S. Mohammad, Mahmudul HasanLLM Evaluation Reasoning Consistency in Language Models
Department of Computer Science, Informatics Institute, Istanbul Technical University, ˙Istanbul, Türkiye · School of Information Technology, Deakin University, Geelong, VIC 3220, Australia
EARS: Explanatory Abstention for Reliable Sub-Agent Modeling in Large-scale Multi-Agent Systems
Jun 17, 2026Shuang Xie, Yunan Lu, Han Li +1AI Agent Reliability Multi-Agent LLM Systems
Shopify · Columbia University
DiagFlowBench: Evaluating How Language Models Handle Off-Procedure Inputs in Grounded Diagnostic Dialogue
Jun 16, 2026Guillermo Gil de Avalle, Laura Maruster, Shaina Raza +1LLM Evaluation LLM Grounding
University of Groningen, PO Box 72, 9700 AB Groningen, The Netherlands · Vector Institute for Artificial Intelligence, MaRS Centre, Toronto, ON, Canada
Substrate Asymmetry in User-Side Memory: A Diagnostic Framework
Jun 10, 2026Youwang DengRetrieval-Augmented Generation LLM Personalization
EpistemicaLab — Independent Research
PhantomBench: Benchmarking the Non-existential Threat of Language Models
Jun 9, 2026Haeji Jung, Hila GonenLLM Evaluation Hallucination in Language Models
University of British Columbia · Canada CIFAR AI Chair, Amii
Cherry-pick Override: Unsafe Directional Commitment in LLM Judges under Mixed Evidence
Jun 5, 2026Haoran XuLLM-as-a-Judge Evidence-Grounded Reasoning
University of Glasgow
What Benchmarks Don't Measure: The Case for Evaluating Abstention Competence in Autonomous Agents
Jun 1, 2026Victor Ojewale, Suresh VenkatasubramanianAgent Evaluation AI Agent Safety
Brown University Providence, Rhode Island, USA
Towards Lightweight Reliability: Using Soft Prompts for Hallucination Mitigation in Large Language Models
May 30, 2026S M Tahmid Siddiqui, Akib Jawad Ononto, Anoop Singhal +1LLM Hallucination Mitigation Question Answering
The University of Texas at Dallas, Richardson, TX 75080, USA · National Institute of Standards and Technology, Gaithersburg, USA
OCC-RAG: Optimal Cognitive Core for Faithful Question Answering
May 30, 2026Maksim Savkin, Mikhail Goncharov, Alexander Gambashidze +7Multi-Hop QA LLM Grounding
OCC Team
Bridging the Detection-to-Abstention Gap in Reasoning Models under Insufficient Information
May 27, 2026Renjie Gu, Jiaxu Li, Yihao Wang +8LLM Abstention Large Reasoning Models
1Fudan University · 4Tsinghua University · 2Ant Group +1
Auditable Decision Models with Learned Abstention and Real-Time Steering
May 26, 2026Sankaranarayanan Palamadai ChandrasekaranAI-Assisted Decision Making AI Accountability
Simple Machine Mind
TIAR: Trajectory-Informed Advantage Reweighting for LLM Abstention Learning
May 25, 2026Muyu Pan, Shu Zhao, Nan Zhang +4RL for Language Models Hallucination Mitigation
Department of Computer Science, The Pennsylvania State University State College, PA, USA
Second Guess: Detecting Uncertainty Through Abstention and Answer Stability in Small Language Models
May 25, 2026Ashwath Vaithinathan Aravindan, Mayank KejriwalConfidence Estimation in Language Models Multiple-Choice Question Answering
University of Southern California Los Angeles, 90007, California, United States of America · Information Sciences Institute 4676 Admiralty Way #1001, Los Angeles, 90292, California, United States of America
Interpretation, Learning, and Empathy as One Constraint: A Residual-Adequacy Architecture with Accountable Abstention
May 24, 2026Chainarong AmornbunchornvejCognitive Architectures for AI Agents Computational Cognitive Modeling
National Electronics and Computer Technology Center (NECTEC), 112 Phahonyothin Road, Khlong Nueng, Khlong Luang, Pathum Thani 12120, Thailand
Claim-Selective Certification for High-Risk Medical Retrieval-Augmented Generation
May 21, 2026Shao KanClaim Verification Healthcare
Jinglue Technology Development (Nanjing) Co., Ltd.
Task Abstention for Large Language Models in Code Generation
May 16, 2026Yanke Zhou, Yuhao Tan, Senrong Xu +4Selective Prediction LLM Hallucination Mitigation
State Key Laboratory of Novel Software Technology Nanjing University · School of Computing and Mathematical Sciences University of London
Quantifying and Mitigating Premature Closure in Frontier LLMs
May 14, 2026Rebecca Handler, Suhana Bedi, Nigam ShahHealthcare LLM Prompting
Department of Medicine, Stanford University · Department of Biomedical Data Science, Stanford University
Trust or Abstain? A Self-Aware RAG Approach
May 11, 2026Xi Zhu, Ziqi Wang, Kai Mei +5Retrieval-Augmented Generation Knowledge Conflicts in Language Models
Rutgers University · University of Illinois Urbana-Champaign
CLEAR: Revealing How Noise and Ambiguity Degrade Reliability in LLMs for Medicine
May 1, 2026Kevin H. Guo, Chao Yan, Avinash Baidya +5Healthcare LLM Reliability
Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN, USA · Intuit AI Research, Mountain View, CA, USA · Department of Electrical and Computer Engineering, Vanderbilt University, Nashville, TN, USA +2
Geometry-Calibrated Conformal Abstention for Language Models
Apr 30, 2026Rui Xu, Yi Chen, Sihong Xie +1Uncertainty Quantification Selective Prediction
Information Hub, AI Thrust Hong Kong University of Science and Technology (Guangzhou) Guangzhou, Guangdong, China
Know2Guess: A Contamination-Aware Multi-Zone Benchmark for Knowledge-Boundary Evaluation in Large Language Models
Apr 30, 2026Renwei Meng, Bowen Zhang, Jian Wang +4LLM Evaluation LLM Auditing
Anhui University, Hefei, China
Four-Axis Decision Alignment for Long-Horizon Enterprise AI Agents
Apr 21, 2026Vasundra SrininvasanLong-Horizon Agent Evaluation AI Agent Benchmarks
Stanford School of Engineering
Knowing When to Quit: A Principled Framework for Dynamic Abstention in LLM Reasoning
Apr 20, 2026Hen Davidov, Nachshon Cohen, Oren Kalinsky +4RL for Language Model Reasoning LLM Abstention
University of Oxford. Work done partly during an internship at amazon. · 2Amazon.
Learning from AVA: Early Lessons from a Curated and Trustworthy Generative AI for Policy and Development Research
Apr 20, 2026Nimisha Karnatak, Mohamad Chatila, Daniel Alejandro Pinzón Hernández +3Retrieval-Augmented Generation Evidence-Grounded Generation
University of Oxford · The World Bank Group · Nouswise, Inc.
Abstain-R1: Calibrated Abstention and Post-Refusal Clarification via Verifiable RL
Apr 18, 2026Skylar Zhai, Jingcheng Liang, Dongyeop KangLLM Hallucination Mitigation RL for Language Model Reasoning
University of Minnesota
Decomposed Prompting Does Not Fix Knowledge Gaps, But Helps Models Say "I Don't Know"
Feb 4, 2026Dhruv Madhwal, Lyuxin David Zhang, Dan Roth +2LLM Prompting Question Decomposition
Arizona State University · University of Pennsylvania · Oracle AI
Honesty over Accuracy: Trustworthy Language Models through Reinforced Hesitation
Nov 14, 2025Mohamad Amin Mohamadi, Tianhao Wang, Zhiyuan LiRL for Language Models LLM Hallucination Mitigation
Toyota Technological Institute at Chicago · University of California, San Diego
Check Yourself Before You Wreck Yourself: Selectively Quitting Improves LLM Agent Safety
Oct 18, 2025Vamshi Krishna Bonagiri, Ponnurangam Kumaragurum, Khanh Nguyen +1LLM Agent Evaluation Tool-Using Agents
University of California, Berkeley · Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) · International Institute of Information Technology, Hyderabad (IIIT Hyderabad)
When Guessing is Rewarded: Rethinking Language Model Evaluation with Distributional Uncertainty Scoring
Oct 5, 2025Thomas F BurnsLLM Evaluation Language Model Generation Evaluation
Aleph Alpha Research

Jun 22, 2026, cs.AIJ/K move · Enter open · S save

TIPS: Topological Ill-Posedness Probing and Steering in Large Language Models

Guangyu Jiang, Sizhe Tang, Mahdi Imani, Nathaniel D. Bastian+1

The George Washington University · Northeastern University

Language Model Steering Question Answering Language Model Probing LLM Abstention

Open paper AskPDF arXiv

Ill-posed questions, including those involving ambiguity, under-specification, or conflicting statements, may admit no valid answer or multiple plausible answers, posing a significant challenge for large language models (LLMs) despite their otherwise strong performance. Existing work often treats LLM reasoning as a black box and focuses on input-output analysis. Can a compact, unified topological representation of internal model states capture diverse sources of ill-posedness and steer reasoning toward responses appropriate to each source? To this end, we study the internal state from a topological perspective by treating the contextual hidden states of its prompt tokens at a single transformer layer as a point cloud, capturing the input problem's relational structure as encoded by the model. Our analysis shows that zero- and one-dimensional persistent homology---tracking how connected components merge as the distance threshold increases (

H_0

) and the emergence and filling of one-dimensional loops in the filtration (

H_1

), respectively---yield seven compact descriptors of ill-posedness that also serve as control signals for steering model reasoning. Thus, we develop a topology-conditioned steering mechanism. It retrieves topologically similar positive and negative examples for each query to form a local activation-space contrast. The resulting query-specific direction modifies internal states during prefill and decoding, guiding the model's responses toward suitable abstention or clarification tailored to the underlying source of ill-posedness. Empirical evaluations on two datasets and open-weight models spanning four families demonstrate the effectiveness of this compact representation for ill-posedness classification, while topology-conditioning significantly improved steering performance.

Momentum

Related topics

Latest papers 61