Selective Prediction

Follow this topic Ask about this topic

Momentum

32 papers in the last four weeks, up 88% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 176

All topics

System Switch: When Should a Fast Decision Model Stop and Think?
Oct 7, 2026Gian Luca BailoLLM Decision-Making Selective Prediction
Independent Researcher, Recco (Genoa), Italy
Certified by Abstention: Distribution-Free Guarantees for Chain-of-Thought Verifiers at Small Calibration Budgets
Oct 7, 2026Arjun BalajiSelective Prediction Conformal Prediction
Columbia University
Epistemic Uncertainty-Aware Defect Detection for Quality Control in Medical Device Manufacturing
Oct 6, 2026Raham A. Butt, Marco Romanelli, Roche C. de GuzmanSelective Prediction Epistemic Uncertainty
Department of Engineering, Hofstra University, Hempstead, NY 11549 USA · Department of Computer Science, Hofstra University, Hempstead, NY 11549 USA
Careful Judge: Safe and Efficient Human-AI Collaborative Decision Making
Oct 6, 2026Chenyu Zhang, Rachel Luo, Boyi Li +3Human-AI Decision Making Human-in-the-Loop AI
MIT · NVIDIA · NVIDIA, Stanford University
Knowing When to Trust a Prior: Reliability-Gated Cue Fusion for Video Gaze Prediction
Oct 6, 2026Lichen Zhu, Yueqian Lin, Yiheng Wang +2Gaze Estimation Selective Prediction
Duke University, Durham, NC, USA
Structure-Aware Graph Abstention for Reliable Selective Forecasting
Oct 6, 2026Jianxiang Xie, Belal AlsinglawiMultivariate Time Series Forecasting Long-Term Time Series Forecasting
University of New South Wales · Zayed University
SAFE-MR: Evidence Sufficiency Learning for Selective Multimodal Rumor Detection
Oct 5, 2026Shiwen NiMultimodal Robustness Selective Prediction
Artificial Intelligence Research Institute, Shenzhen University of Advanced Technology
When to Remember, When to Abstain: Category-Conditioned Retention for Reliable Agent Memory
Oct 5, 2026Olukunle Owolabi, Pulkit Gupta, Fei WangSelective Prediction LLM Agent Memory
Meta AI
Benchmarking candidate coverage and rejection policy transfer in typed decision models
Oct 2, 2026Jiawen Lu, Tongtong WuLLM Evaluation Selective Prediction
Monash University
Grounding with Confidence: Controllable Generative Video Temporal Grounding
Sep 30, 2026Jinhao Chen, Benlei Cui, Ruijian Jia +7Temporal Video Grounding Selective Prediction
Alibaba Group · Beihang University · Fudan University
The Geometry of Randomized Smoothing on Feasible Sets
Sep 30, 2026Syed Izhan Khilji, Alireza Furutanpey, Schahram DustdarRandomized Smoothing Selective Prediction
Technische Universität Wien · NeverBlink · Technische Universität Wien Universitat Pompeu Fabra
When the Right Answer Is Missing: An Arithmetic-Dependent Rejection Bottleneck in Jev
Sep 30, 2026Jike Zhong, Ming Li, Yuxiang LaiNumerical Reasoning in Language Models Selective Prediction
University of Southern California · University of Florida · Emory University
RAGScope: A Leakage-Controlled, Cost-Aware Evidence-Gating Protocol for RAG Hallucination Triage
Sep 30, 2026Zeming Liu, Qibai Chen, Jingtao Zhang +1Selective Prediction Hallucination Detection
Brown University, United States · Independent Researcher, United States · Georgia Institute of Technology, United States
Benchmarking System One decision models against trained classifiers and language models for automated decision gates
Sep 29, 2026Amir Rafe, Subasish DasLLM Decision-Making LLM Evaluation
Texas State University, 601 University Drive, San Marcos, 78666, Texas, USA
HARISSA: Inference-Time Self-Checks for Efficient and Safe Local Language Model Deployment
Sep 29, 2026Kenan Alkiek, Moontae Lee, David Jurgens +1On-Device Language Model Inference Selective Prediction
School of Information University of Michigan Ann Arbor, MI 48109, USA · SNU-LG AI Research Center Seoul, South Korea
One Threshold Does Not Fit All Languages: Language-Conditional Deferral for Reliable and Efficient Low-Resource Text Classification
Sep 29, 2026Bhanu Prakash Vangala, Vangala NavyaSelective Prediction Group-Conditional Conformal Prediction
University of Missouri · Amar Bio Tech Pvt Ltd
SafeVantage: Vantage-Aware Memory for Reliable Embodied Decisions
Sep 29, 2026Sean Hardesty Lewis, Zuyi Guo, Benwang Chen +3Next-Best-View Planning Selective Prediction
Massachusetts Institute of Technology · Korea Advanced Institute of Science and Technology · Nanyang Technological University +1
Mixed-Prior Decision Risk for Open-Set Recognition
Sep 28, 2026L. A. Erlygin, P. D. Proskura, A. A. ZaytsevSelective Prediction Open-Set Recognition
Skolkovo Institute of Science and Technology (Skoltech), Moscow, Russia · Risk Management, Sber, Moscow, Russia · The Institute for Information Transmission Problems (IITP RAS), Moscow, Russia
Do Not Cut When Uncertain: Rejectable and Calibrated Decision Heads for VLA Policies in Robotic Harvesting
Sep 28, 2026Heng ZhangUncertainty Estimation for VLA Models Selective Prediction
Certified Selective Automation of LLM Agent Evaluation
Sep 28, 2026Chengguang Gan, Yunhao Liang, Qinghao Zhang +1LLM-as-a-Judge Selective Prediction
Independent Researcher · University of Chinese Academy of Sciences · Pusan National University +1
Curating Merchant-Matching Training Data with Two Confidence-Gated Local LLM Judges
Sep 27, 2026Donghao Huang, Jinling Pei, Zhaoxia WangLLM-as-a-Judge Selective Prediction
Research and Development, Mastercard, Arlington, VA, USA · School of Computing and Information Systems, Singapore Management University, Singapore
Laya as a Typed Probabilistic Assessor: An Independent Reproduction and a Preregistered Study of Calibration and Selective Escalation
Sep 27, 2026Gowthamkumar NandakishoreLLM Evaluation Selective Prediction
Evaluating System One Models for Agent Security Decisions: Reliability, Calibration, and Selective Automation
Sep 27, 2026Yixuan LiuProbability Calibration Selective Prediction
TraceStone and Nanyang Technological University, Singapore
RAEGL: Risk-Aware Evidence-Gated Learning for Selective Contextual Routing under Temporal Shift
Sep 27, 2026Yifan GuoDistribution Shift Selective Prediction
Stony Brook University
UQ-LOB: Uncertainty-Aware Limit Order Book Mid-Price Forecasting
Sep 25, 2026Derrick Gilchrist Edward Manoharan, Eljas Linna, Kestutis Baltakys +2Uncertainty Quantification Selective Prediction
Data Science Research Centre Tampere University Tampere, Finland
JEV vs. LLMs as Rubric Judges: Cheaper, Faster, and Wrong in the Same Places
Sep 24, 2026Delip Rao, Chris Callison-BurchLLM Inference Efficiency LLM Evaluation
University of Pennsylvania
GCUL: Ambiguity Identification in Text Emotion Classification via Cluster-Guided Learning
Sep 24, 2026Zhongqi Fan, Tianyou Zhang, Fei ChenSelective Prediction
Beijing Normal-Hong Kong Baptist University
JEV-as-a-Judge: Accept When Confident, Escalate When Unsure
Sep 22, 2026Yubo Li, Yidi Miao, Ramayya Krishnan +1LLM-as-a-Judge Language Model Generation Evaluation
Carnegie Mellon University
When Are Aggregate Agent Traces Diagnosable? Traffic-Governed Interpretation and Calibrated Abstention
Sep 22, 2026Peiying Zhu, Sidi ChangAgent Failure Analysis Selective Prediction
Blossom AI San Francisco, CA, USA
Intrinsic Sequence-Likelihood Confidence in Retrieval-Dominated Extractive QA: Two Pre-Specified Negatives, and What They Do and Do Not Attribute
Sep 17, 2026Gunwoo Lee, Changmin Sung, Sang-Hwan Gwak +3LLM Evaluation Selective Prediction
Large-scale AI Research Center, Korea Institute of Science and Technology Information (KISTI), 245 Daehak-ro, Yuseong-gu, Daejeon, 34141, Republic of Korea. · Department of Applied AI, University of Science and Technology (UST), 217 Gajeong-ro, Yuseong-gu, Daejeon, 34113, Republic of Korea.
How Many Labels Does Model Choice Need? Certificates and Budgets for Selective Prediction
Sep 16, 2026Tetsuji KuboyamaModel Selection Selective Prediction
Computer Centre, Gakushuin University
When to Call an LLM: A Confidence-Gated Hybrid for Cost-Effective Emotion Recognition in Conversational AI
Sep 16, 2026Sai Babu Udayagiri, Arjun Chouhan, Ravisekhar Kanagala +1LLM Inference Efficiency Selective Prediction
Five9
When Should LLMs Abstain? Chain-of-Self-Questioning for Selective Risk Control
Sep 15, 2026Ali ŞenolSelective Prediction LLM Prompting
Department of Computer Engineering, Tarsus University, Tarsus, Türkiye
Predicting Human Disagreement for Calibrated Dynamic Facial Expression Recognition
Sep 15, 2026Yiming Wang, Frederick W. B. Li, Jingyun WangAnnotator Disagreement Uncertainty Quantification
Department of Computer Science, Durham University
Symmetry-Aware Likelihood-Orbit Aggregation for Selective Left-Right Claim Verification
Sep 15, 2026Zhouzhi Xiong, Chuxi Zhang, Weizhen He +3VLM Evaluation Visual Spatial Reasoning
Polytechnic Institute, Zhejiang University, Hangzhou, China · College of Artificial Intelligence, Zhejiang University, Hangzhou, China · College of Electrical Engineering, Zhejiang University, Hangzhou, China +1
When Should a World Model Move? Loss-Conditioned State Execution
Sep 14, 2026Jintao Xu, Zhengyu Chen, Ben Zhang +2Selective Prediction Probabilistic Forecasting
Supply Chain Tech Team Y, JD.com
Competence-Gated Pooling of Language Models and Priors for Event Forecasting
Sep 14, 2026Aditi Tiwari, Aashrith Bandaru, Heng JiEvent Time Prediction Selective Prediction
University of Illinois Urbana-Champaign Urbana, Illinois, USA
Efficiency Hallucination: Formalizing and Measuring Behavioral Calibration in LLM-Based Code Optimization
Sep 13, 2026Sarah Wilson, Gail Kaiser, Patrick MusauSelective Prediction Large Language Model-Guided Optimization
Google · Columbia University · Vanderbilt University
Calibration-Aware Uncertainty Cascades for Efficient Heterogeneous Model Collaboration
Sep 12, 2026Yilin Zhang, Han Jiang, Cai Xu +2Selective Prediction Cost-Aware Inference
School of Computer Science and Technology, Xidian University Xi’an, China
Safe to Stop? Risk-Constrained Stopping for Sequential Clinical Diagnosis Agents
Sep 9, 2026Yuexin Wu, Vasile RusSelective Prediction AI Agent Evaluation
Department of Computer Science University of Memphis
SafeRestore: Detector-Relative Risk Certificates for Selective Industrial Image Restoration
Sep 3, 2026Shaoliang Yang, Jun WangSelective Prediction Industrial Inspection
Santa Clara University Santa Clara, CA 95053, USA
RACE-AIMC: Selective Inference for Heterogeneous Analog In-Memory Accelerators at the Edge
Sep 2, 2026Osama Yousuf, Martin Lueker-BodenEfficient Neural Network Inference Compute-in-Memory
WD Research San Jose, CA, USA
Measuring consistency via ensemble margin and local prediction variability: Auditing decision systems in the presence of predictive multiplicity
Sep 1, 2026Sinjini Banerjee, Tim Marrinan, Anand D. SarwateSelective Prediction Ensemble Learning
Department of Electrical and Computer Engineering, Rutgers University · Pacific Northwest National Lab
Verdict Instability of OOD Scores under Reference Resampling
Sep 1, 2026Donghoon Lee, Shinjin KangUncertainty Quantification Selective Prediction
Hongik University
TRUST: Threshold-Recalibrated Uncertainty-Safe Training for Certified Dismissal in Breast Cancer Screening
Aug 31, 2026Parham Hajishafiezahramini, Matthew Hamilton, Edward Kendall +2Breast Cancer Selective Prediction
Department of Computer Science, Memorial University of Newfoundland, Canada · 2Division of Biomedical Sciences, Faculty of Medicine, Memorial University of2026 Newfoundland, Canada · 3Cancer Care, Newfoundland and Labrador Health Services, St. John’s, NL, CanadaAug 31
DreamLedger: Where to Refuse World-Model Imagination Using Execution-Settled Credit
Aug 24, 2026Xianyao Li, Ruitong Tian, Rui Min +2Selective Prediction Robotics
Department of Civil and Coastal Engineering, University of Florida, Gainesville, FL 32611, USA · Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL 32611, USA
Credal Large Language Models for Semantic Commitment under Uncertainty
Aug 24, 2026Shireen Kudukkil Manchingal, Sofiia Nikolenko, Fabio CuzzolinSelective Prediction Confidence Estimation in Language Models
Oxford Dynamics Oxford · Ludwig-Maximilians-Universität München Munich · Institute for Artificial Intelligence, Data Analysis and Systems (AIDAS) School of Engineering Computing & Mathematics Oxford Brookes University, Oxford, UK
Verifiable abstention makes AI leak diagnosis accountable in urban water distribution networks
Aug 19, 2026Tianwei Mu, Yue Wang, Mingzhe Yuan +8Selective Prediction Anomaly Localization
School of Municipal Engineering and Environment, Shenyang Jianzhu University, Shenyang 110168, China. · Guangzhou Institute of Industrial Intelligence, Guangzhou 510000, China. · Key Laboratory of Ecological Restoration of Regional Contaminated Environment, Ministry of Education, College of Environment, Shenyang University, Shenyang 110044, China. +3
Conditional Validity for Adaptive Modality Acquisition: When the Policy Chooses Its Own Calibration Group
Aug 16, 2026Melika BaghiEfficient Multimodal Inference Selective Prediction
Georgia Institute of Technology Atlanta, GA, USA
Regime-Conditional Verification: Correctness Estimation for Adapting and Monitoring Safety Classifiers
Aug 14, 2026Thiago Sandoval, Ufuk TopcuDistribution Shift Selective Prediction
The University of Texas at Austin
Predictive Memory Localization: Forecasting Selective Intervention Paths from Internal Signals
Aug 13, 2026Jinhao Jing, Tian Zeyu, Lucas Qingyang Fang +4Selective Prediction Mechanistic Interpretability
The Chinese University of Hong Kong, Shenzhen · Shanghai Jiao Tong University · University of California, Santa Cruz +3
Non-Degenerate Risk Certification for Automated Security Decisions: A Decision-Contract Theory with ATT&CK-Aligned Triage as a Worked Instance
Aug 12, 2026Zhenpeng LiAI Assurance Selective Prediction
Guangzhou Health Science College, No. 248 Guangyuan Middle Road, Guangzhou, Guangdong 510405, China
Evaluating and Calibrating Diffusion Model-derived Uncertainty for Quantitative MRI Mapping
Aug 12, 2026Shishuai Wang, Stefan Klein, Juan A. Hernandez-Tamames +1Uncertainty Quantification Selective Prediction
Department of Radiology and Nuclear Medicine, Erasmus MC, Rotterdam, The Netherlands · Department of Imaging Physics, TU Delft, Delft, The Netherlands
Robust Ambiguity Detection (RAD) From Model- and Feature-Space Consistency
Aug 12, 2026Manya Singh, Mark T. Keane, Arjun PakrashiSelective Prediction Interpretable ML
School of Computer Science, University College Dublin, Dublin, Ireland
Certify or Refuse: A Cross-Model Map for Selective Risk Control with Coverage Floors under Covariate Shift
Aug 11, 2026Jiamiao Liu, Dewen Qiao, Yu Zhang +1Selective Prediction Covariate Shift
Department of Information, Xinqiao Hospital Army Medical University (Third Military Medical University) Chongqing 400037, China
ConfTriage: A Calibration-Aware LLM Triage Framework for Pulmonary Nodule Malignancy with Selective Specialist Deferral
Aug 11, 2026Md Rabiul Islam, Samir Abdaljalil, Erchin Serpedin +1Selective Prediction Clinical Decision Support
Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX, USA · College of Science and Engineering, Hamad Bin Khalifa University, Doha, Qatar
Rethinking LLM Verification: Evidence Structure, Uncertainty, and Selective Refinement
Aug 11, 2026Uma Ranjan, Kunal Tilaganji, Aditya Koul +9LLM Grounding LLM Answer Verification
Indian Institute of Technology Jammu · Microsoft Research · SCB Dental College and Hospital, Cuttack
Metadata Reconstruction from Values Alone: Recovering Column Semantics in Undocumented Warehouses
Aug 8, 2026Mike HelwigSelective Prediction Text-to-SQL
Independent Researcher USA
TelemetrySuffBench: Is Agent Telemetry Sufficient for Failure-Origin Diagnosis?
Aug 8, 2026Yuxuan Zhu, Peng PuSelective Prediction Fault Detection
School of Data Science and Engineering East China Normal University Shanghai, China
RibAssist 3D: Biplanar Rib-Fracture Detection, Addressing, and Selective 3D Localization from CT-Derived Projections
Aug 7, 2026Kabila Haile SobokaSelective Prediction Medical Image Analysis
The University of Texas at Austin Austin, Texas, USA

Oct 7, 2026, cs.AIJ/K move · Enter open · S save

System Switch: When Should a Fast Decision Model Stop and Think?

Gian Luca Bailo

Independent Researcher, Recco (Genoa), Italy

LLM Decision-Making Selective Prediction VLM Reasoning Language Model Calibration

Open paper AskPDF arXiv

Dual-process agents pair a fast policy with a slow deliberative model. In real-time settings the slow model usually runs continuously; in turn-based agents and robot planners it is invoked on events such as uncertainty or a detected failure. We study a fast learned actor that takes every decision and hands control to a reasoning vision-language model only when a gate opens, while the game keeps running. We use closed-loop Doom and the new open "System One" typed-decision models, served through a common llama.cpp interface. On 900 held-out questions, (i) zero-shot decision models from 0.15B to 9B parameters choose to collect items 1.6-1.8 times more often than chance among their errors, in any option order, although the order changes some models' accuracy; (ii) accuracy, calibration and sensitivity (how well confidence separates right from wrong answers) are distinct: models of similar accuracy differ widely in AUROC, and the confidence of the most sensitive one tracks which kinds of situation it fails, not which answers are wrong; (iii) offline, deferring the least confident 30% of decisions to a reasoning model gains over random deferral in proportion to the actor's AUROC (rank correlation 0.87); with actor and rate chosen on held-out games the gain is +0.13 [0.08, 0.18] with doomLaya's option order and +0.08 [0.02, 0.14] with shuffled options, and reasoning carries about half of it; (iv) in closed loop (33 games, three seeds) no variant reaches the exit. Committing to plans, the reasoner's or a fixed explore rule's, opens more doors and makes an actor that stands still play; with the rule the agent dies more often. Told that some doors need keys, the reasoner takes ordinary doors for locked ones, which the state cannot tell apart; without that knowledge it goes back to collecting. We release code, prompts, data and logs.

Momentum

Related topics

Latest papers 176