LLM Reliability

LLM: Large Language Model

It asks not only whether a model gets an answer right, but whether it knows when it may be wrong, follows constraints, uses evidence faithfully, and behaves consistently across repeated or multi-turn use. Researchers test these properties with adversarial and perturbation benchmarks, repeated-run and cross-language evaluations, domain-specific tasks, and audits of LLM judges and tool-using agents. Common approaches include estimating uncertainty from logits, hidden representations, or response agreement; selective abstention and conformal calibration; retrieval and symbolic verification; and training methods that reward grounded answers, correction, or hesitation. The central tension is that benchmark accuracy and verbal confidence often fail to predict reliability on individual cases, long tasks, or shifted inputs, while stronger checks and abstention trade coverage, latency, and cost for safer decisions.

Latest papers

802 papers116 papers in the last four weeks, up 18% on the four weeks before. 0.7% of all new papers.

LLM Judges Inconsistently Disagree Across Safety Criteria and Harm Categories
May 29, 2026Krishnapriya Vishnubhotla, Sowmya Vajjala, Akriti Vij +1Multilingual Language Model Evaluation LLM-as-a-Judge
National Research Council, Canada · IMDA, Singapore
LLM-FACETS: A Privacy-Preserving Framework for Evaluating LLM Transparency and Accountability
May 29, 2026Tom Lucas, Alessio Buscemi, Alfredo Capozucca +2LLM Evaluation AI Accountability
Luxembourg Institute of Science and Technology (LIST), Luxembourg, University of Luxembourg, Luxembourg, and Scriptor Artis, France · Luxembourg Institute of Science and Technology (LIST), Luxembourg · University of Luxembourg, Luxembourg +1
Prompt PerturbAItions: Mechanisms of LLM Response Inconsistencies
May 29, 2026Soorya Ram Shimgekar, Agam Goyal, Amruta Parulekar +6Prompt Sensitivity LLM Interpretability
University of Illinois Urbana-Champaign · Nimblemind
The Architecture of Errors: From Universal Impossibility to Patch-Local LLM Reliability
May 28, 2026Mikhail L. Arbuzov, Lee Mosbacker, Sisong Bei +3LLM Reliability
Independent Researcher · Palo Alto Networks
Evaluating using Mock Tool Calls to Quarantine Untrusted Prompt Inputs
May 28, 2026David Gros, Adam GleaveLanguage Model Safety Evaluation Adversarial Attacks on LLMs
SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones?
May 28, 2026Sy-Tuyen Ho, Minghui Liu, Huy Nghiem +6AI Agent Benchmarks LLM Evaluation
University of Maryland · All Purpose AI
CommunityFact: A Dynamic, Multilingual, Multi-domain Benchmark for Misinformation Detection in the Wild
May 28, 2026Sahajpreet Singh, Insyirah Mujtahid, Min-Yen Kan +1Multilingual Language Model Evaluation LLM Evaluation
National University of Singapore
Harnessing non-adversarial robustness in large language models
May 28, 2026Qinghua Zhou, Ellina Aleshina, Andrey Lovyagin +6LLM Fine-Tuning Neural Network Robustness
International Joint Laboratory of AI for Industry, QUST, Qingdao, China · King’s College London, London, UK · Applied AI Institute, Moscow, Russia +2
Can LLMs Use Linguistic Uncertainty Markers to Reliably Reflect Intrinsic Confidence?
May 27, 2026Gabrielle Kaili-May Liu, Arman CohanConfidence Estimation in Language Models Language Model Calibration
Yale University
Entropy Distribution as a Fingerprint for Hallucinations in Generative Models
May 27, 2026Mattia J. Villani, Pranav Deshpande, Akshay Seshadri +2Language Model Error Detection Language Model Generation Evaluation
Global Technology Applied Research, JPMorganChase, New York, NY 10001, USA
The Fragility of Chain-of-Thought Monitoring Across Typologically Diverse Languages
May 27, 2026Eric Onyame, Runtao Zhou, Kowshik Thopalli +2CoT Faithfulness Multilingual Language Model Evaluation
University of Virginia · Lawrence Livermore National Laboratory
A Paired Testing Protocol for Batch-Conditioned Refusal Robustness in LLM Serving
May 26, 2026Sahil KadadekarLLM Inference Language Model Safety Evaluation
Independent Researcher.
Same Answer, Different Confidence: Protocol Sensitivity in LLM Confidence Calibration
May 26, 2026Hankyeol Kim, Pilsung KangLLM Evaluation Confidence Estimation in Language Models
Seoul National University
Chain-based Adaptive Reconfiguration Over Lattices for Hallucination Reduction
May 26, 2026Joan Vendrell Gallart, Solmaz Kia, Russell Bent +1LLM Hallucination Mitigation Hallucination in Language Models
Department of Mechanical and Aerospace University of California Irvine Irvine, CA 92617-4322, USA · T-5 Los Alamos National Laboratory Los Alamos, NM 88220, USA · CAI-4 Los Alamos National Laboratory Los Alamos, NM 88220, USA
How Do Uncertainty Estimators Align with Hallucination Occurrence in LLMs?
May 26, 2026Yedidia Agnimo, Anna Korba, Annabelle Blangero +2LLM Evaluation Hallucination in Language Models
Ekimetrics France · Centre Inria de l’Université Grenoble Alpes France · CREST, ENSAE Institut Polytechnique de Paris France
Innovation: An Almost Characterization of Hallucination
May 26, 2026Nishant P. Das, Piyush SrivastavaHallucination in Language Models Language Model Calibration
School of Technology and Computer Science, Tata Institute of Fundamental Research, Mumbai, Maharashtra - 400 005, India.
SeDT: Sentence-Transformer Decision-Transformer Conditioning for Multi-Turn Conversation Reliability
May 26, 2026Ramakrishna Vamsi Setti, Jagadeesh Rachapudi, Sachin Chaudhary +2LLM Reliability Language Model Robustness
Independent Researcher · 2Drone Lab, IIT Mandi · 3UPES, Dehradun
The Attribution Blind Spot: Detecting When Language Models Rely on Memory Rather Than Retrieved Context
May 26, 2026Zhe Yu, Wenpeng Xing, Yunzhao Wei +4Claim Attribution in Language Models Memorization in Language Models
Binjiang Institute of Zhejiang University · Zhejiang University · National Fintech Evaluation Center +2
It's Not the Capability: Harness Sensitivity Is Non-Monotone Across LLM Agent Tiers
May 26, 2026Yong-eun ChoAI Agent Reliability LLM Agent Evaluation
KailosLab · Seoul, Republic of Korea
LLM-as-a-Reviewer: Benchmarking Their Ability, Divergence, and Prompt Injection Resistance as Paper Reviewers
May 25, 2026Lingyao Li, Junjie Xiong, Changjia Zhu +5LLM Evaluation LLM-as-a-Judge
University of South Florida · Missouri University of Science and Technology · University of Alabama +3
ARBITER: Reasoning Trajectory Basins and Majority Vote Failures in Test-Time Sampling
May 25, 2026Meng Cai, Lars Kulik, Farhana ChoudhurySelf-Consistency Decoding Test-Time Scaling
School of Computing and Information Systems University of Melbourne
Trust but Verify: Prover-Verifier Deliberation for Selective LLM Prediction
May 24, 2026João Sedoc, Baotong Zhang, Dean FosterLLM Answer Verification Selective Prediction
New York University
Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth
May 24, 2026Yoav Gur-Arieh, Ana Marasović, Mor GevaCoT Faithfulness LLM Evaluation
Tel Aviv University · University of Utah
Graph Alignment Topology as an Inductive Bias for Grounding Detection
May 21, 2026Paul Landes, Pranav Herur, Adam Cross +1LLM Grounding Hallucination in Language Models
†Department of Pediatrics, University of Illinois College of Medicine Peoria · ♣University of Illinois Urbana-Champaign · ♠Siebel School of Computing and Data Science, University of Illinois Urbana-Champaign +1
Hallucination as Commitment Failure: Larger LLMs Misfire Despite Knowing the Answer
May 21, 2026Jewon Yeom, Jaewon Sok, Heejun Kim +3LLM Interpretability Hallucination in Language Models
Graduate School of Data Science, Seoul National University · Department of Rural Systems Engineering, Seoul National University · Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology +1
Calibration vs Decision Making: Revisiting the Reliability Paradox in Unlearned Language Models
May 20, 2026Divyaksh Shukla, Ashutosh ModiShortcut Learning in Language Models Confidence Estimation in Language Models
Indian Institute of Technology Kanpur (IIT Kanpur)
Do No Harm? Hallucination and Actor-Level Abuse in Web-Deployed Medical Large Language Models
May 20, 2026Sunday Oyinlola Ogundoyin, Muhammad Ikram, Rahat MasoodLanguage Model Safety Evaluation Healthcare
Macquarie University, Sydney, Australia · The University of New South Wales, Sydney, Australia
Reading Calibrated Uncertainty from Language Model Trajectories
May 19, 2026Aliai Eusebi, Alexander Herzog, Xiaoyu Liang +3Confidence Estimation in Language Models LLM Reliability
University College London, London, United Kingdom · Core46, London, United Kingdom
BalanceRAG: Joint Risk Calibration for Cascaded Retrieval-Augmented Generation
May 19, 2026Zijun Jia, Yuanchang Ye, Sen Jia +6Retrieval-Augmented Generation Selective Prediction
Beihang University · Zhejiang University of Finance & Economics · Shenzhen Institute of Advanced Technology +1
LLM Benchmark Datasets Should Be Contamination-Resistant
May 19, 2026Ali Al-Lawati, Jason Lucas, Dongwon Lee +1LLM Evaluation Benchmark Contamination
The Pennsylvania State University, University Park, PA, USA.

May 29, 2026J/K move · Enter open · S save

LLM Judges Inconsistently Disagree Across Safety Criteria and Harm Categories

Krishnapriya Vishnubhotla, Sowmya Vajjala, Akriti Vij, Isar Nejadgholi

National Research Council, Canada · IMDA, Singapore

Multilingual Language Model Evaluation LLM-as-a-Judge Language Model Safety Evaluation LLM Reliability

Open paper AskPDF arXiv

We evaluate the consistency of automated judges in conducting a multi-dimensional safety evaluation in a reference-free setup. Our results indicate that Large Language Models are unreliable judges in identifying safety issues related to machine-generated advice in regulated domains such as finance, although they are more reliable at identifying more overt forms of unsafe/harmful content such as violence. The degree of inconsistency in a model's judgments can vary significantly by the chosen safety criteria and can be impacted by the language of the content and its linguistic style as well. Finally, there is high disagreement among different judges for the same output, across domains, safety criteria, and languages. These findings provide new insights on the practice of using LLMs as evaluators and offer several recommendations for practitioners on how to use automated judges in practical scenarios.