mlsanityData to 7 Oct 2026

Rare Event Analysis of Large Language Models

arXiv 2602.06791 ↗First posted 6 Feb 2026cs.LG cond-mat.dis-nn cond-mat.stat-mechcited by 6

Not on the map. Why?

Abstract (arXiv)

Being probabilistic models, during inference large language models (LLMs) display rare events: behaviour that is far from typical but highly significant. By definition all rare events are hard to see, but the enormous scale of LLM usage means that events completely unobserved during development are likely to become prominent in deployment. Here we present an end-to-end framework for the systematic analysis of rare events in LLMs. We provide a practical implementation spanning theory, efficient generation strategies, probability estimation and error analysis, which we illustrate with concrete examples. We outline extensions and applications to other models and contexts, highlighting the generality of the concepts and techniques presented here.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 24 of its 62 references that are in the map. First posted on arXiv 6 Feb 2026.

Builds on

24 of 62 references.

References · 24

  1. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  2. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  3. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  4. 2024HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusalcited by 1,330
  5. 2024Tulu 3: Pushing Frontiers in Open Language Model Post-Trainingcited by 988
  6. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  7. 2023TinyStories: How Small Can Language Models Be and Still Speak Coherent English?cited by 425
  8. 2022Efficient Training of Language Models to Fill in the Middlecited by 248
  9. 2024A Thorough Examination of Decoding Methods in the Era of LLMscited by 112
  10. 2025Reasoning with Sampling: Your Base Model is Smarter Than You Thinkcited by 84
  11. 2023Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programscited by 79
  12. 2025Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlocited by 45
12 more
  1. 2026Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpeningcited by 27
  2. 2024Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advancescited by 24
  3. 2020A reinforcement learning approach to rare trajectory samplingcited by 21
  4. 2025Sample, Don't Search: Rethinking Test-Time Alignment for Language Modelscited by 21
  5. 2024QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine Translationcited by 16
  6. 2025Forecasting Rare Language Model Behaviorscited by 16
  7. 2024Estimating the Probabilities of Rare Outputs in Language Modelscited by 15
  8. 2021Reinforcement learning of rare diffusive dynamicscited by 14
  9. 2022Combining Reinforcement Learning and Tensor Networks, with an Application to Dynamical Large Deviationscited by 4
  10. 2018Simple Confidence Intervals for MCMC Without CLTscited by 2
  11. 2022Training neural network ensembles via trajectory samplingcited by 2
  12. 2023Bayesian Multistate Bennett Acceptance Ratio Methodscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026Estimating Tail Risks in Language Model Output Distributionscited by 6
  2. 2026Estimating Rare Events in Language Models with Proper Evaluationcited by 1
  3. 2026Training ML Models with Predictable Failurescited by 0
  4. 2026Prioritizing Repeated LLM Evaluation for Hidden Failure Discoverycited by 0
  5. 2026Quantifying Behavioral Tails in Black-Box Language Modelscited by 0
  6. 2026Estimating great expectations under autoregressive language models with potentialscited by 0