method · first seen 4 Oct 2026
selective prediction
Also: abstention, rejection option, refusal to answer, risk-coverage tradeoff, confidence thresholding, learning with rejection, selective classification
Letting a model abstain from predicting on uncertain inputs to trade coverage for accuracy on retained samples.
Mentions per week
PapersCodeDiscussion
Rank 91 on 16 Nov 2026 · 30 mentions in 28 days · 30 independent groups · papers → code · first seen 6 weeks ago · acceleration +0.12
Earliest sources
- The Margin Knows the Background: Uneven Abstention in Frozen Vision-Language ModelsPapers · 4 Oct 2026 · Satwik Sai Prakash Sahoo, Bibhor Puhan, Shubhankar Mahanta
- When to Remember, When to Abstain: Category-Conditioned Retention for Reliable Agent MemoryPapers · 5 Oct 2026 · Olukunle Owolabi, Pulkit Gupta, Fei Wang
- SAFE-MR: Evidence Sufficiency Learning for Selective Multimodal Rumor DetectionPapers · 5 Oct 2026 · Shiwen Ni
- Unanimously Wrong: Certified Abstention from How Medical LLM Consensus FormsPapers · 6 Oct 2026 · Xiaoyang Wang, Tianrui Wang, Christopher C. Yang
- Epistemic Uncertainty-Aware Defect Detection for Quality Control in Medical Device ManufacturingPapers · 6 Oct 2026 · Raham A. Butt, Marco Romanelli, Roche C. de Guzman
- VERDICT: Visual Extraction-Result Decoder with Integrated Confidence and Traceable EvidencePapers · 7 Oct 2026 · Harikrishnan P M, Goutham Vignesh, Siva Prasad, Zishan Ahmad, Mahesh Basveshwar…
Latest sources
- Stability-Compensated Threshold Calibration for Selection-Conditioned Risk Control in Large Language ModelsPapers · 16 Nov 2026 · Zhiyuan Wang, Yuanchang Ye, Jiahao Yuan, Jinhao Duan, Xiaoshuang Shi, Weijun Xie…
- When to Trust Simulated Patient Responses:Support-Gated World Models for Vasopressor Decision SupportPapers · 13 Nov 2026 · Yifan Jin, Tao Liu
- PRISM: A Post-Prediction Reliability Framework for Evidence-Guided Correction and Selective AbstentionPapers · 13 Nov 2026 · Omm Swarup, Shrishail M. Hiremath
- Recalibrating a Typed-Decision Model in an Afternoon: A Hands-On Recipe for Laya's Confidence ScoresPapers · 12 Nov 2026 · Mohammed Nayeem Khan, Aliyas Ahmad Misri
- One Model, Two Precisions: Does Disagreement Between Quantized Copies Tell You When a Small Model Is Wrong?Papers · 12 Nov 2026 · Mohammed Nayeem Khan, Allan Kevin T
- Abstention Is Not Threshold Compliance: Stated Scoring Rules in Open Language ModelsPapers · 10 Nov 2026 · Dongsun Moon
- Multimodal Abstention That Preserves Acquired Correct AnswersPapers · 10 Nov 2026 · Jinyuan Zhang
- ShiftGuard: Evaluating Confidence and Feature Distance for Risk-Controlled Image ClassificationPapers · 10 Nov 2026 · Mitra Varun
- Answer or Defer? Testing VLMs' Stated Confidence on Brain MRIPapers · 9 Nov 2026 · Amir Sabbaghziarani, Parsa Ghazvinian, Sepehr Salem, Sergey Plis
- RADE: Risk-Adjusted Deployment Efficiency, A Framework for Routing, Memory, and Escalation in Safe LLM SystemsPapers · 8 Nov 2026 · Chaymaa Abbas, Kareem Hassani, Mariette Awad
- Selective Surgical Action-Center Localization:Retaining Localization Gains through Supervised ScoringPapers · 8 Nov 2026 · Yanchong Xue, Wanting Zhang, Lingtao Yu, Guochao Zhang
- ProtoCouncil: Multi-Encoder Anatomical Prototypes for Prostate Cancer Detection in Micro-UltrasoundPapers · 6 Nov 2026 · Mohammad Mahdi Abootorabi, Nooshin Maghsoodi, Armin Saadat, Obed Dzikunu, Zhuoxi…