Surprisal

Ask about this topic

Momentum

4 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 51

All topics
CardsList

  1. Reader Proficiency Shapes Layer-wise Surprisal Profiles

    Sep 29, 2026Akio Hayakawa, Horacio SaggionReadabilityProficiency

    Universitat Pompeu Fabra Barcelona, Spain

  2. TRACE: Single-Pass Decoding-Trace Risk Localization for Generation Calibration

    Sep 28, 2026Yuebin Xu, Xuemei Peng, Junlan Chen +2Large Language Model UncertaintyConformal Risk Control

    The Hong Kong University of Science and Technology (Guangzhou)

  3. Next-token functional estimation

    Sep 17, 2026Milind Nakul, Vidya Muthukumar, Ashwin PananjadyNext-Token DistributionSurprisal

    Schools of Industrial and Systems Engineering and Electrical and Computer Engineering Georgia Institute of Technology

  4. Psychosis involves a deficit of information compression in connected speech

    Sep 14, 2026Samuele Vallisa, Claudio Palominos, Rui He +6LinguisticsSurprisal

    Grammar and Cognition Lab, Department of Translation & Language Sciences, Universitat Pompeu Fabra, Barcelona, Spain · Department of Neurosciences, Health Sciences Institute, Dokuz Eylul University, Izmir, Turkey. · Department of Psychiatry, Dokuz Eylul University, Izmir, Turkey. +4

  5. Representation Trajectories Matters: Complementary Evidence for OOD Detection and Image Classification

    Jul 29, 2026Ignacio M. De la Jara, Cristian Rodriguez-Opazo, Hamed Damirchi +2Out-Of-Distribution DetectionVision Foundation Models

    University of Adelaide · Naval Group Pacific · Australian National University

  6. Surprisal Theory is Tautological (without Rational Grounding)

    Jul 23, 2026Ryan CotterellSurprisalLinguistics

    ETH Zürich

  7. surprisal is Not a Theory

    Jul 22, 2026Andrés Buxó-Lugo, Aniello De Santo, Morgan Grobol +2SurprisalLinguistics

    aUniversity at Buffalo, Buffalo, NY, USA · bUniversity of Utah, Salt Lake City, UT, USA · cUniversité Paris Nanterre, Paris, France +1

  8. Structured Output Collapses Answer Diversity Across 44 Language Models

    Jul 20, 2026Tapan ParikhLarge Language Model ResponsesAnswer

    Cornell Tech

  9. Surprise Forcing: What to Remember, When to Skip in Long Video Generation

    Jul 20, 2026Shuwei Shi, Zhen Li, Muyao Niu +4Long Video GenerationAutoregressive Diffusion

    Alaya Lab · The University of Tokyo

  10. Principled Direction-Free Intrinsic Motivation through Model-Free Epistemic Free-Energy Estimators

    Jul 18, 2026Alireza Furutanpey, Schahram DustdarEntropy Regularized Reinforcement LearningIntrinsic Motivation

    Coovally, Barcelona, Spain · Distributed Systems Group, TU Vienna, Austria · ICREA Barcelona, Spain

  11. Contextual Semantic Relevance Tracks fMRI BOLD Responses During Naturalistic Speech Comprehension

    Jul 17, 2026Kun Sun, Rong WangSurprisalSemantic Relationships

    Department of Linguistics, Tongji University · Department of Computational Linguistics, Tuebingen University

  12. Converge to Surprise: Evolutionary Self-supervised Image Clustering

    Jul 8, 2026Canlin Zhang, Xiuwen LiuClusteringDeep Learning

    Independent Researcher · Department of Computer Science Florida State University

  13. A Bayesian framework for the uncanny valley in humanoid robot design

    Jul 7, 2026Shimon Honda, Rin Shibano, Hideyoshi YanagisawaAnthropomorphismPerception Gap

    Department of Mechanical Engineering, Graduate School of Engineering, The University of Tokyo, Tokyo, Japan.

  14. Geographic Diversity Beats Data Volume for Cross-Domain Generalization in Zero-Label JEPA Driving World Models

    Jul 5, 2026Santosh JaiswalNaturalistic Driving DataWorld Models

  15. Agent Step Value: Auditing Evaluator-Channel Reversals in Black-Box Agent Traces

    Jul 5, 2026Andrew Zhang, Chengzhan LiTracesAgentic Evaluations

    KTH Royal Institute of Technology · University of Electronic Science and Technology of China

  16. Contextual Semantic Relevance and Word Surprisal Predict N400 and P600 Dynamics During Naturalistic Reading

    Jul 5, 2026Kun Sun, Rong WangSurprisal

    Tongji University · University of Tuebingen

  17. Feeling the Unexpected: ResTacVLA for Contact-Rich Manipulation via Residual Tactile Representation

    Jul 3, 2026Pengwei Zhang, Bin Xie, Ce Hao +5TactileContact-Rich Manipulation

    Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China · Zhongguancun Academy, Beijing 100094, China · Dexmal, Beijing 100096, China

  18. Which Tokens Matter? Adaptive Token Selection for RLVR with the Relative Surprisal Index

    Jun 30, 2026Outongyi Lv, Yanzhao Zheng, Yuanwei Zhang +5Token-Level EntropyReinforcement Learning With Verifiable Reward

    1ModelScope Team, 2Alibaba Group, Hangzhou, China. · 3Shanghai Jiao Tong University, Shanghai, China.

  19. Surprise as a Signal for Plasticity and Metacognition

    Jun 30, 2026Louis MouchonEpisodic MemoryPlasticity

    Independent Research

  20. Fast Numbers, Slow Language: Bridging Quantitative and Qualitative Earnings Signals

    Jun 29, 2026Ding Yu, Zhuo Liu, Hao Zhang +1Financial Sentiment AnalysisQuantifying

    University of Rochester · Rochester Institute of Technology

  21. Evidence-Informed LLM Beliefs for Continual Scientific Discovery

    Jun 28, 2026Dhruv Agarwal, Reece Adamson, Andrew McCallum +3Scientific DiscoveryLLM Reasoning Strategies

    University of Massachusetts Amherst · Allen Institute for AI

  22. Surprises in Proper Positive-Only Learning

    Jun 26, 2026Shai Ben-David, Farnam Mansouri, Anay Mehrotra +1LearnabilityPositive--Unlabeled Learning

    University of Waterloo and Vector Institute · Stanford University · Yale University

  23. Syntactic Belief Update as the Driver of Garden Path Processing Difficulty

    Jun 25, 2026Alan Zhou, Miloš Stanojević, John T. HaleSurprisalSyntactic Structure

    Johns Hopkins University · University College London

  24. Light-weight Pronunciation Assessment via Discrete Speech Token Surprisal

    Jun 18, 2026Syeda Faiza Ahmed Sara, Shammur Absar ChowdhuryPronunciation AssessmentSurprisal

    Qatar Computing Research Institute, Doha, Qatar

  25. STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability

    Jun 17, 2026Haipeng Luo, Qingfeng Sun, Songli Wu +4Token-Level EntropyOffline Reinforcement Learning

    Shenzhen International Graduate School, Tsinghua University · Tencent Hunyuan

  26. Surprise-Guided MergeSort: Budget-Efficient Human-in-the-Loop Ranking via Adaptive Comparison Scheduling

    Jun 14, 2026Yujin Park, Haejun Chung, Ikbeom JangRankingSchedulers

    Hanyang University, Seoul, Republic of Korea · Hankuk University of Foreign Studies, Yongin, Republic of Korea

  27. Trajectory Dynamics in Language Model Hidden States Predict Human Processing Costs Beyond Surprisal

    Jun 3, 2026Elan BarenholtzSurprisalLanguage Modeling

    Machine Perception & Cognitive Robotics Laboratory Department of Psychology / Center for Complex Systems Florida Atlantic University

  28. Noisy memory encoding explains negative polarity illusions

    Jun 3, 2026Yuhan Zhang, Edward GibsonNegationSurprisal

    Department of Linguistics, Stanford University · BIO-X Interdisciplinary Biosciences Institute, Stanford University · Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology

  29. Worth Remembering: Surprise-Gated Robot Episodic Memory

    Jun 2, 2026Nicolas Gorlo, Derek K. Wise, Alberto Speranzon +1Episodic MemorySurprisal

    Massachusetts Institute of Technology · Lockheed Martin

  30. "I've Seen How This Goes": Characterizing Diversity via Progressive Conditional Surprise

    Jun 1, 2026Matthew Khoriaty, David Williams-King, Shi FengDiversityCreativity

    ERA Fellowship · George Washington University

  31. AnyEdit++: Adaptive Long-Form Knowledge Editing via Bayesian Surprise

    May 31, 2026Bowen Tian, Caixue He, Jiemin Wu +4Multimodal Knowledge EditingEdit

    The Hong Kong University of Science and Technology (Guangzhou), Guangzhou 511400, China · Southeast University, Nanjing, China · Knowin AI, Shenzhen, China +2

  32. Relational Intervention During Functional Collapse in Large Language Models: A Lexical-Statistical Ablation and a Structure x Register Factorial

    May 31, 2026Franco Santana, Horacio VicoDissociationLarge Language Models Fail

    Universidad de la República (UDELAR), Montevideo, Uruguay · DigitalIA Cloud, Montevideo, Uruguay

  33. YoCausal: How Far is Video Generation from World Model? A Causality Perspective

    May 28, 2026You-Zhe Xie, Yu-Hsuan Li, Jie-Ying Lee +3Video Diffusion ModelsCausal Reasoning

    National Yang Ming Chiao Tung University · Shanda AI Research Tokyo

  34. Creative Quality Alignment: Expert Tacit Knowledge Transfer via Chain-of-Thought Fine-Tuning

    May 25, 2026Bo Zou, Chao XuLarge Language Model AlignmentChain-of-Thought Reasoning

  35. From Simulation to Enaction: Post-trained language models recognize and react to their own generations

    May 25, 2026Asvin G., Jack LindseySurprisal

    Institute for Advanced Study, Princeton · Anthropic

  36. Swift Sampling: Selecting Temporal Surprises via Taylor Series

    May 21, 2026Dahye Kim, Bhuvan Sachdeva, Karan Uppal +3Surprisal

    Boston University · Microsoft Research India

  37. Why are language models less surprised than humans? Testing the Parse Multiplicity Mismatch Hypothesis

    May 14, 2026William Timkey, Brian Dillon, Tal LinzenSurprisalNatural Language

    Department of Linguistics, New York University, 10 Washington Pl, New York, NY 10003, USA · Department of Linguistics, University of Massachusetts Amherst, 650 N Pleasant St, Amherst, MA 01002, USA · Center for Data Science, New York University, 60 5th Ave, New York, NY 10011, USA

  38. The Frequency Confound in Language-Model Surprisal and Metaphor Novelty

    May 7, 2026Omar Momen, Sina ZarrießSurprisalImplicit Association Test

    CRC 1646 – Linguistic Creativity in Communication · Bielefeld University, Germany

  39. The grip of grammar on meaning uncertainty: cross-linguistic evidence, neural correlates, and clinical relevance

    May 2, 2026Rui He, Claudio Palominos, Samuele Vallisa +16SurprisalUncertainty

    Grammar and Cognition Lab, Department of Translation & Language Sciences, Universitat Pompeu Fabra, Barcelona, Spain. · School of Foreign Studies, Guangzhou University, Guangzhou, China. · Department of Neurology Sant Pau Memory Unit, Hospital de la Santa Creu i Sant Pau Biomedical Research Institute Sant Pau, Barcelona, Spain. +18

  40. Surprisal Minimisation over Goal-directed Alternatives Predicts Production Choice in Dialogue

    May 1, 2026Tom Utting, Mario Giulianelli, Arabella SinclairUtterancesSurprisal

    University of Aberdeen · University College London

  41. On the Proper Treatment of Units in Surprisal Theory

    Apr 30, 2026Samuel Kiegeland, Vésteinn Snæbjarnarson, Tim Vieira +1SurprisalPredictability

    ETH Zürich · CHI-FRO · University of Copenhagen

  42. Calibrated Surprise: An Information-Theoretic Account of Creative Quality

    Apr 29, 2026Bo Zou, Chao XuSurprisalLiterature

  43. Probing for Reading Times

    Apr 20, 2026Eleftheria Tsipidi, Samuel Kiegeland, Francesco Ignazio Re +4ReadabilityEye Tracking

    ETH Zürich · Toyota Technological Institute at Chicago · University College London

  44. Dual Alignment Between Language Model Layers and Human Sentence Processing

    Apr 20, 2026Tatsuki Kuribayashi, Alex Warstadt, Yohei Oseki +1Natural LanguageSurprisal

    MBZUAI · Tohoku University · UC San Diego +2

  45. An Existence Proof for Neural Language Models That Can Explain Garden-Path Effects via Surprisal

    Apr 20, 2026Ryo Yoshida, Shinnosuke Isono, Taiga Someya +2SurprisalLinguistics

    ♠The University of Tokyo · ♡NINJAL · ♢NII LLMC +1

  46. LLM surprisal is necessary but not sufficient to capture English garden-path effects: Evidence from joint latent modeling of reading paradigms

    Feb 4, 2026Dario Paape, Tal Linzen, Shravan VasishthSurprisalReadability

    Department of Linguistics, University of Potsdam · Department Linguistik, Universität Potsdam, Karl-Liebknecht-Straße 24–25, D-14476, Germany. · Center for Data Science/Department of Linguistics, New York University

  47. Black-Box Detection of LLM-Generated Text Using Generalized Jensen-Shannon Divergence

    Oct 8, 2025Shuangyi Chen, Ashish KhistiMachine-Generated Text DetectionBlack Box

    Department of Electrical and Computer Engineering, University of Toronto, Toronto, Canada.

  48. Mutual Information Surprise: Rethinking Unexpectedness in Autonomous Systems

    Aug 24, 2025Yinsong Wang, Quan Zeng, Xiao Liu +1SurprisalMutual Information

    H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta & 30332, USA.

  49. Learning by Surprise: Adaptive Mitigation of Model Collapse in Large Language Models

    Oct 16, 2024Daniele Gambetta, Gizem Gezici, Fosca Giannotti +3CollapseGenerative Artificial Intelligence

    University of Pisa, Pisa, Italy · ISTI-CNR, Pisa, Italy · Scuola Normale Superiore, Pisa, Italy +1

  50. Timing is Everything: Temporal Scaffolding of Semantic Surprise in Humor

    Date pendingYuxi Ma, Yongqian Peng, Junchen Lyu +2HumorSurprisal

  51. When Context Misleads: Surprisal, Energy and Attention Entropy as Metrics of Coherence Illusions in LLMs

    Date pendingEce Takmaz, Nitin Kumar, Li Kloostra +1Discourse CoherenceSurprisal

    Utrecht University