Overview

Selective prediction studies how models should decide whether to make a prediction, abstain, or escalate an uncertain case to a person or another system. Common approaches use confidence and uncertainty scores, ensembles or verifiers, and calibration methods such as conformal prediction to set risk–coverage trade-offs. Applications range from image classification and clinical triage to language-model question answering and agent actions, where benchmarks increasingly assess accepted-case errors, coverage, review costs, and subgroup outcomes. A central challenge is that useful confidence rankings do not by themselves guarantee safe decisions: calibration and risk guarantees can depend on data assumptions, shift across domains or groups, and sharply reduce coverage.

Latest papers

CardsList

325 papers46 papers in the last four weeks, down 30% on the four weeks before. 0.3% of all new papers.

  1. Less Than Meets the Eye: Action-Set Identifiability and Principled Abstention for 3D Physical Geometry

    Nov 19, 2026Reshad Ul Karim, Abrar Samin, Sammam Mahdi +23D Scene UnderstandingSelective Prediction

  2. ADAPT: Adaptive Decision and Abstention with Pool-Size-Aware Thresholds for Service Routing

    Nov 19, 2026Manile Srun, Muntasir Adnan, Arslan Shaukat +1Adaptive Model RoutingSelective Prediction

  3. AeroBelief: Budgeted First-Action Verification for Evidence-Guided Aerial Sensing

    Nov 19, 2026Tianren Li, Dongbo Li, Hongkai Chen +2UAV Remote SensingBelief-Space Planning

  4. Cross-Question Reliable Reinforcement Learning

    Nov 18, 2026Hector G. Rodriguez, Marcus RohrbachLLM AbstentionConfidence Estimation in Language Models

  5. Blind Spots Travel, Knowledge Stays Home: What RL Inherits from an LLM Judge

    Nov 18, 2026Liang Yue, Eric A. VanceLLM-as-a-JudgeBias in LLM-as-a-Judge

  6. SCOUT: Risk-Guided Foundation-Model Escalation for Robust Tissue Detection in Whole-Slide Images

    Nov 18, 2026Cristian Tommasino, Antonio M. RinaldiHistopathology Image SegmentationWhole-Slide Image Analysis

  7. Stability-Compensated Threshold Calibration for Selection-Conditioned Risk Control in Large Language Models

    Nov 16, 2026Zhiyuan Wang, Yuanchang Ye, Jiahao Yuan +5Selective PredictionLanguage Model Calibration

  8. PRISM: A Post-Prediction Reliability Framework for Evidence-Guided Correction and Selective Abstention

    Nov 13, 2026Omm Swarup, Shrishail M. HiremathSelective Prediction

  9. BARS: Budget-Aware Sequential Sampling with Refusal for Majority Identification under Unknown Distributions

    Nov 10, 2026Shenxi Liu, Yiwei Li, Mingyang Zhao +2Adaptive SamplingSelective Prediction

  10. Free Lunch Uncertainty: Sequence-Level Rényi Entropy from Particle Decoding for Adaptive LLM Reasoning

    Nov 10, 2026Erfan Baghaei Potraghloo, Milad Heidari Sorkhehdizaj, Shahab Rahimirad +6LLM Uncertainty EstimationAdaptive Reasoning in Language Models

  11. Certify, Report, or Refuse: Harm-Constrained Conformal Prediction for Clinical Actions

    Nov 9, 2026Zhiyuan Li, Lequan YuConformal PredictionConformal Risk Control

  12. Instance-preserving graded semantic reporting for surgical action triplets

    Nov 9, 2026Yanchong Xue, Wanting Zhang, Lingtao Yu +1Surgical Video UnderstandingSelective Prediction

  13. Selective Surgical Action-Center Localization:Retaining Localization Gains through Supervised Scoring

    Nov 8, 2026Yanchong Xue, Wanting Zhang, Lingtao Yu +1Selective Prediction

  14. Selective Prediction Intervals: Jointly Learning to Predict, Bound, and Abstain

    Nov 4, 2026Lidor Rubi, Gilad KatzSelective PredictionRegression Prediction Intervals

  15. METRIC-GS: Selective Metric-Scale Estimation for 3D Gaussian Splatting

    Nov 4, 2026Sooyeun Yang, Jongseong Brad Choi3D Reconstruction3D Gaussian Splatting

  16. Selective, Risk-Controlled Emotion Forecasting in Conversation: From a Persistence Barrier to Departure Detection with Conformal Guarantees

    Nov 4, 2026Bin Wen, Dai-Qiao Zhang, Tien-Ping TanEmotion Recognition in ConversationsSelective Prediction

  17. Risk Control Certifies Rates, Not Magnitudes: An Audit of Selective Fetal Biometry

    Nov 4, 2026Zhengshuai Yang, Linna Jiang, Changyun Li +1Selective PredictionUltrasound Imaging

  18. MAGAR: Multimodal Agents for GUI-Based 3D Mechanical Assembly and Minimal Rework

    Nov 2, 2026Jingxuan Wei, Jiahao Fu, Fuqiang Wang +5Multimodal AgentsAI Agent Reliability

  19. Local or Escalate? Post-Training Expert Routing for Real-Time Duplex Speech Models

    Nov 1, 2026Ruoyu He, Jisen Li, Anthony Ji +5LLM RoutingFull-Duplex Spoken Dialogue Systems

  20. Principled Human-AI Collaboration in Agentic Workflows

    Nov 1, 2026Young Hyun Cho, Will Wei SunHuman-AI CollaborationAgentic Workflows