Conformal Risk Control
Not on the map. Why?
Abstract (arXiv)
We extend conformal prediction to control the expected value of any monotone loss function. The algorithm generalizes split conformal prediction together with its coverage guarantee. Like conformal prediction, the conformal risk control procedure is tight up to an O(1/n) factor. We also introduce extensions of the idea to distribution shift, quantile risk control, multiple and adversarial risk control, and expectations of U-statistics. Worked examples from computer vision and natural language processing demonstrate the usage of our algorithm to bound the false negative rate, graph distance, and token-level F1-score.
Key facts. Cited by 299 papers in the map (data through 14 Oct 2026). Builds on 26 of its 44 references that are in the map. First posted on arXiv 4 Aug 2022.
Builds on
26 of 44 references.
References · 26
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2014Microsoft COCO: Common Objects in Contextcited by 17,608
- 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
- 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
- 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 792
- 2016Distribution-Free Predictive Inference For Regressioncited by 668
- 2019Conformalized Quantile Regressioncited by 629
- 2019Conformal Prediction Under Covariate Shiftcited by 519
- 2020PraNet: Parallel Reverse Attention Network for Polyp Segmentationcited by 460
- 2020Classification with Valid and Adaptive Coveragecited by 396
- 2021Adaptive Conformal Inference Under Distribution Shiftcited by 375
- 2020Uncertainty Sets for Image Classifiers using Conformal Predictioncited by 366
14 more
- 2022Conformal prediction beyond exchangeabilitycited by 355
- 2022Confident Adaptive Language Modelingcited by 310
- 2021Distribution-Free, Risk-Controlling Prediction Setscited by 288
- 2021Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Controlcited by 271
- 2020Conformal Inference of Counterfactuals and Individual Treatment Effectscited by 151
- 2020TResNet: High Performance GPU-Dedicated Architecturecited by 119
- 2022Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imagingcited by 107
- 2021Consistent Accelerated Inference via Confident Adaptive Transformerscited by 74
- 2019PAC Confidence Sets for Deep Neural Networks via Calibrated Predictioncited by 60
- 2021Conformalized Survival Analysiscited by 53
- 2022Conformal Prediction Sets with Limited False Positivescited by 28
- 2019Conformal prediction with localizationcited by 23
- 2022Semantic uncertainty intervals for disentangled latent spacescited by 22
- 2022Recommendation Systems with Distribution-Free Reliability Guaranteescited by 13
Built on by
Citing papers per year: 2022: 8; 2023: 30; 2024: 54; 2025: 61; 2026: 146.
299 papers.
Sort:
By area:
- 2023Conformal Language Modelingcited by 170
- 2024Language Models with Conformal Factuality Guaranteescited by 131
- 2024Large language model validity via enhanced conformal prediction methodscited by 92
- 2023Conformal PID Control for Time Series Predictioncited by 88
- 2023Improved Online Conformal Prediction via Strongly Adaptive Online Learningcited by 78
- 2022Learning to Defer to Multiple Experts: Consistent Surrogate Losses, Confidence Calibration, and Conformal Ensemblescited by 60
- 2024Mitigating LLM Hallucinations via Conformal Abstentioncited by 59
- 2024Conformal Prediction for Natural Language Processing: A Surveycited by 53
- 2023How to Trust Your Diffusion Model: A Convex Optimization Approach to Conformal Risk Controlcited by 50
- 2023Conformal Decision Theory: Safe Autonomous Decisions from Imperfect Predictionscited by 50
- 2025Decision Theoretic Foundations for Conformal Prediction: Optimal Uncertainty Quantification for Risk-Averse Agentscited by 40
- 2022Calibrated Selective Classificationcited by 33
38 more
- 2023Object Pose Estimation with Statistical Guarantees: Conformal Keypoint Detection and Geometric Uncertainty Propagationcited by 33
- 2023Conformal Prediction Regions for Time Series using Linear Complementarity Programmingcited by 33
- 2024Fast yet Safe: Early-Exiting with Risk Controlcited by 30
- 2022Distribution Free Prediction Sets for Node Classificationcited by 28
- 2023Principal Uncertainty Quantification with Spatial Correlation for Image Restoration Problemscited by 28
- 2024C-RAG: Certified Generation Risks for Retrieval-Augmented Language Modelscited by 27
- 2024Conformal Validity Guarantees Exist for Any Data Distribution (and How to Find Them)cited by 26
- 2024Conformal Prediction: A Data Perspectivecited by 25
- 2024A Survey on the Honesty of Large Language Modelscited by 23
- 2022Efficiently Controlling Multiple Risks with Pareto Testingcited by 22
- 2023Confident Object Detection via Conformal Prediction and Conformal Risk Control: an Application to Railway Signalingcited by 22
- 2023Mitigating Temporal Misalignment by Discarding Outdated Factscited by 21
- 2023Forking Uncertainties: Reliable Prediction and Model Predictive Control with Sequence Models via Conformal Risk Controlcited by 20
- 2024Conformal Semantic Image Segmentation: Post-hoc Quantification of Predictive Uncertaintycited by 20
- 2024Trustworthy Classification through Rank-Based Conformal Prediction Setscited by 20
- 2025Conformal Linguistic Calibration: Trading-off between Factuality and Specificitycited by 20
- 2022Integrative conformal p-values for powerful out-of-distribution testing with labeled outlierscited by 19
- 2024Conformal Prediction for Class-wise Coverage via Augmented Label Rank Calibrationcited by 19
- 2024Conformal Prediction for Causal Effects of Continuous Treatmentscited by 19
- 2024Sample then Identify: A General Framework for Risk Control and Assessment in Multimodal Large Language Modelscited by 19
- 2024Localized Adaptive Risk Controlcited by 17
- 2023Conformal Autoregressive Generation: Beam Search with Coverage Guaranteescited by 16
- 2024Automatically Adaptive Conformal Risk Controlcited by 16
- 2024Robust Yet Efficient Conformal Prediction Setscited by 16
- 2024Adaptive Learn-then-Test: Statistically Valid and Efficient Hyperparameter Selectioncited by 15
- 2024End-to-End Conformal Calibration for Optimization Under Uncertaintycited by 15
- 2025Wasserstein-regularized Conformal Prediction under General Distribution Shiftcited by 15
- 2023Kandinsky Conformal Prediction: Efficient Calibration of Image Segmentation Algorithmscited by 14
- 2025Conformal Prediction for Image Segmentation Using Morphological Prediction Setscited by 14
- 2025Conformal Language Model Reasoning with Coherent Factualitycited by 14
- 2026SCOPE: Selective Conformal Optimized Pairwise LLM Judgingcited by 14
- 2024Bellman Conformal Inference: Calibrating Prediction Intervals For Time Seriescited by 13
- 2024Utility-Directed Conformal Prediction: A Decision-Aware Framework for Actionable Uncertainty Quantificationcited by 13
- 2024Semi-Supervised Risk Control via Prediction-Powered Inferencecited by 13
- 2022Posterior-Variance-Based Error Quantification for Inverse Problems in Imagingcited by 12
- 2024Looks Too Good To Be True: An Information-Theoretic Analysis of Hallucinations in Generative Restoration Modelscited by 12
- 2024Split Conformal Prediction under Data Contaminationcited by 12
- 2025Conformal Arbitrage: Risk-Controlled Balancing of Competing Objectives in Language Modelscited by 12
50 most cited of 299 All 299 (JSON)
- 2026Adaptive Computation with Conformal Certification13 Oct 2026
- 2026CALM-5G: Event-Level Conformal Risk Control for Predictive Service-Assurance Alarms13 Oct 2026
- 2026Conformal Sequential Decision Making With Cost and Sublinear Policy Regret Guarantees10 Oct 2026
- 2026ConformalGuard: False-Positive-Controlled Action Gating for LM Classifiers9 Oct 2026
- 2026CopRoute: Dependence-Aware Conformal Routing for Language Models9 Oct 2026
- 2026Finding Blind Spots in AppWorld and WorkArena Task Verifiers6 Oct 2026
- 2026From Uncertainty to Action: Learning to Steer LLM Agents6 Oct 2026
- 2026Unanimously Wrong: Certified Abstention from How Medical LLM Consensus Forms6 Oct 2026
- 2026MIRTO: a registration-gated, multiverse-tested evaluation protocol for unsupervised anomaly segmentation in brain MRI1 Oct 2026
- 2026Benchmarking System One decision models against trained classifiers and language models for automated decision gates29 Sep 2026
- 2026Cartridges++: KV Cache Compression without Off-Context Derailment28 Sep 2026
- 2026NeuronSifter: An Agent-in-Twin for Prioritizing Central Nervous System Interventions with World Action Models28 Sep 2026
38 more
- 2026Adaptive Safety Filtering for Frozen ACC Policies via Conformal Residual Calibration28 Sep 2026
- 2026RSD-Poker: Structure-Adaptive and Shift-Robust Risk-Utility Certification for Residual Policies in Imperfect-Information Games27 Sep 2026
- 2026Audit-First VAPO: Risk-Certified Selective Updates under Imperfect Verification27 Sep 2026
- 2026RAEGL: Risk-Aware Evidence-Gated Learning for Selective Contextual Routing under Temporal Shift27 Sep 2026
- 2026When Can First-Order Models of Fine-Tuning Bound Forgetting?26 Sep 2026
- 2026Multivariate conformal uncertainty propagation in multitask atomistic simulation: Successes and pitfalls25 Sep 2026
- 2026CRC-Router: Risk-Constrained Routing for Medical Agentic AI Systems25 Sep 2026
- 2026How Many Categories Are Enough? Distribution-Free Certification Limits for Few-Shot Anomaly Thresholds23 Sep 2026
- 2026DRSR: Learning Set-Level Deletion Risk for Efficient Long-Horizon Agents23 Sep 2026
- 2026Meet, Compare, or Abstain: LatWeave for Deterministic Multi-Hop Question Answering on Knowledge Lattices23 Sep 2026
- 2026Certified Against Which Oracle? Execution Labels Set the Reported Risk of Conformal Abstention for Text-to-SQL22 Sep 2026
- 2026SoK: Formal Methods for Fact-Checking and Information Integrity19 Sep 2026
- 2026Available Guardrails: Certifying Selective Prediction across ML Systems18 Sep 2026
- 2026Calibrated RF-Fingerprinting Under Interference With Heterogeneous Transmission Protocols17 Sep 2026
- 2026Should This Case Be Adapted? Prediction Fragmentation Controls Test-Time Adaptation17 Sep 2026
- 2026Symmetry-Aware Likelihood-Orbit Aggregation for Selective Left-Right Claim Verification15 Sep 2026
- 2026Decision-Oriented Uncertainty Quantification for Risk Control in Earth System Spatiotemporal Foundation Models13 Sep 2026
- 2026Certified AI Triage of ICU Alarms11 Sep 2026
- 2026Certified Safety Curation: Distribution-Free Guarantees for Safe Offline Reinforcement Learning10 Sep 2026
- 2026Engineering Reliable Commit Gates for Agentic AI: Cost-Aware Verification Portfolios under Common-Mode Data Failures10 Sep 2026
- 2026Conformal Calibration Transfer9 Sep 2026
- 2026Learning to Adapt and Calibrate: Score Distribution Alignment for Few-Shot Uncertainty Prediction in Medical VLMs9 Sep 2026
- 2026View-Structured Conformal Prediction for 3D Gaussian Splatting9 Sep 2026
- 2026Safe to Stop? Risk-Constrained Stopping for Sequential Clinical Diagnosis Agents9 Sep 2026
- 2026Stochastic Semantic Evidence Graphs: Uncertainty Propagation and Governance for Agentic AI3 Sep 2026
- 2026Conformity Breaks Conformal Prediction3 Sep 2026
- 2026More Criticism Does Not Make a Better Review: EquiReview-R3 Sep 2026
- 2026SafeRestore: Detector-Relative Risk Certificates for Selective Industrial Image Restoration3 Sep 2026
- 2026RACE-AIMC: Selective Inference for Heterogeneous Analog In-Memory Accelerators at the Edge2 Sep 2026
- 2026Occupancy-based Quantile Risk Control2 Sep 2026
- 2026Probabilistic Model Checking of Autoregressive Neural Sequence Models1 Sep 2026
- 2026TRUST: Threshold-Recalibrated Uncertainty-Safe Training for Certified Dismissal in Breast Cancer Screening31 Aug 2026
- 2026FaultLens: Learning Compact Behavioral Test Suites for Generated Operational Programs27 Aug 2026
- 2026CVE-SAI: Counterfactual Visual Evidence-Guided Selective Attribute Indexing for Risk-Controlled E-commerce Search25 Aug 2026
- 2026Revelation Control24 Aug 2026
- 2026Replicable Conformal Prediction23 Aug 2026
- 2026Bound-Aware Per-Organ Recall Risk Control for Multi-Organ CT Segmentation under Clinical Domain Shift18 Aug 2026
- 2026Judge, Retrieve, or Abstain: Uncertainty-Guarded LLM Judging with Provable Risk Guarantees18 Aug 2026
50 newest of 299 All 299 (JSON)
- 2025Conformal Language Model Reasoning with Coherent Factualitycited by 14
- 2026Conformal Thinking: Risk Control for Reasoning on a Compute Budgetcited by 10
- 2025On the Provable Performance Guarantee of Efficient Reasoning Modelscited by 6
- 2026CoT2-Meta: Budgeted Metacognitive Control for Test-Time Reasoningcited by 4
- 2026Process Supervision of Confidence Margin for Calibrated LLM Reasoningcited by 2
- 2026Conformal Certification of Reasoning Trace Prefixescited by 2
- 2026When Does Learning to Stop Help? A Cost-Aware Study of Early Exits in Reasoning Modelscited by 2
- 2026What Predicts Correctness in Text-to-SQL? A Selective-Prediction Studycited by 2
- 2026HyPAC: Cost-Efficient LLMs-Human Hybrid Annotation with PAC Error Guaranteescited by 1
- 2026Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoningcited by 1
- 2026Prefix-Safe Bayesian Belief Tracking for LLM Reasoning Reliability:Separating Calibration from Rankingcited by 1
- 2026Budgeted Act-or-Defer Multi-Agent LLM Deliberation with Local Reliability Boundscited by 1
12 most cited of 15 All 15 (JSON)
- 2026DRSR: Learning Set-Level Deletion Risk for Efficient Long-Horizon Agents23 Sep 2026
- 2026What Predicts Correctness in Text-to-SQL? A Selective-Prediction Study7 Jul 2026
- 2026When Does Learning to Stop Help? A Cost-Aware Study of Early Exits in Reasoning Models29 Jun 2026
- 2026Budgeted Act-or-Defer Multi-Agent LLM Deliberation with Local Reliability Bounds28 Jun 2026
- 2026Conformal Certification of Reasoning Trace Prefixes28 May 2026
- 2026Prefix-Safe Bayesian Belief Tracking for LLM Reasoning Reliability:Separating Calibration from Ranking26 May 2026
- 2026Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning13 May 2026
- 2026Process Supervision of Confidence Margin for Calibrated LLM Reasoning25 Apr 2026
- 2026CoT2-Meta: Budgeted Metacognitive Control for Test-Time Reasoning30 Mar 2026
- 2026I Know What I Don't Know: Latent Posterior Factor Models for Multi-Evidence Probabilistic Reasoning13 Mar 2026
- 2026Conformal Thinking: Risk Control for Reasoning on a Compute Budget3 Feb 2026
- 2026HyPAC: Cost-Efficient LLMs-Human Hybrid Annotation with PAC Error Guarantees30 Jan 2026
12 newest of 15 All 15 (JSON)
- 2026ToolChain-CRC: Conformal Risk Control for Agentic AI Under Retrieval and Tool-Use Driftcited by 6
- 2026Responsible Agentic AI Requires Explicit Provenancecited by 3
- 2026CodeRescue: Budget-Calibrated Recovery Routing for Coding Agentscited by 3
- 2026ParEvalLayer: When Partial LLM-Agent Evaluations Support a Decisioncited by 1
- 2026Post-Hoc Trajectory-Risk Certification for Modular LLM-Based Security Agentscited by 1
- 2026Engineering Reliable Commit Gates for Agentic AI: Cost-Aware Verification Portfolios under Common-Mode Data Failurescited by 1
- 2026Calibrating Conservatism for Scalable Oversightcited by 0
- 2026Stochastic Semantic Evidence Graphs: Uncertainty Propagation and Governance for Agentic AIcited by 0
- 2026Unanimously Wrong: Certified Abstention from How Medical LLM Consensus Formscited by 0
- 2026From Uncertainty to Action: Learning to Steer LLM Agentscited by 0
- 2026From Uncertainty to Action: Learning to Steer LLM Agents6 Oct 2026
- 2026Unanimously Wrong: Certified Abstention from How Medical LLM Consensus Forms6 Oct 2026
- 2026Engineering Reliable Commit Gates for Agentic AI: Cost-Aware Verification Portfolios under Common-Mode Data Failures10 Sep 2026
- 2026Stochastic Semantic Evidence Graphs: Uncertainty Propagation and Governance for Agentic AI3 Sep 2026
- 2026Post-Hoc Trajectory-Risk Certification for Modular LLM-Based Security Agents4 Aug 2026
- 2026ParEvalLayer: When Partial LLM-Agent Evaluations Support a Decision3 Aug 2026
- 2026CodeRescue: Budget-Calibrated Recovery Routing for Coding Agents21 Jul 2026
- 2026ToolChain-CRC: Conformal Risk Control for Agentic AI Under Retrieval and Tool-Use Drift16 Jun 2026
- 2026Calibrating Conservatism for Scalable Oversight27 May 2026
- 2026Responsible Agentic AI Requires Explicit Provenance16 May 2026
- 2024Sample then Identify: A General Framework for Risk Control and Assessment in Multimodal Large Language Modelscited by 19
- 2025Data-Driven Calibration of Prediction Sets in Large Vision-Language Models Based on Inductive Conformal Predictioncited by 3
- 2025Explicit Abstention Knobs for Predictable Reliability in Video Question Answeringcited by 3
- 2026Uncertainty Quantification for Computer-Use Agents: A Benchmark across Vision-Language Models and GUI Grounding Datasetscited by 2
- 2026Geometric Risk Control for Vision-Language Model OCRcited by 1
- 2026When Does Visual Token Pruning Improve Calibration? The Role of Evidence Coverage in MLLMscited by 1
- 2026Auditing Medical Vision-Language Models on Chest Radiographs: Estimating Reference Agreement Across Institutionscited by 0
- 2026Symmetry-Aware Likelihood-Orbit Aggregation for Selective Left-Right Claim Verificationcited by 0
- 2026Symmetry-Aware Likelihood-Orbit Aggregation for Selective Left-Right Claim Verification15 Sep 2026
- 2026Auditing Medical Vision-Language Models on Chest Radiographs: Estimating Reference Agreement Across Institutions1 Aug 2026
- 2026Uncertainty Quantification for Computer-Use Agents: A Benchmark across Vision-Language Models and GUI Grounding Datasets24 Jun 2026
- 2026When Does Visual Token Pruning Improve Calibration? The Role of Evidence Coverage in MLLMs13 Apr 2026
- 2026Geometric Risk Control for Vision-Language Model OCR20 Mar 2026
- 2025Explicit Abstention Knobs for Predictable Reliability in Video Question Answering31 Dec 2025
- 2025Data-Driven Calibration of Prediction Sets in Large Vision-Language Models Based on Inductive Conformal Prediction24 Apr 2025
- 2024Sample then Identify: A General Framework for Risk Control and Assessment in Multimodal Large Language Models10 Oct 2024
- 2024Fast yet Safe: Early-Exiting with Risk Controlcited by 30
- 2025Controlling the Risk of Corrupted Contexts for Language Models via Early-Exitingcited by 3
- 2026Cartridges++: KV Cache Compression without Off-Context Derailmentcited by 2
- 2026SAFE-KD: Risk-Controlled Early-Exit Distillation for Vision Backbonescited by 0
- 2026Cartridges++: KV Cache Compression without Off-Context Derailment28 Sep 2026
- 2026SAFE-KD: Risk-Controlled Early-Exit Distillation for Vision Backbones3 Feb 2026
- 2025Controlling the Risk of Corrupted Contexts for Language Models via Early-Exiting2 Oct 2025
- 2024Fast yet Safe: Early-Exiting with Risk Control31 May 2024
- 2024C-RAG: Certified Generation Risks for Retrieval-Augmented Language Modelscited by 27
- 2026PASC: Pipeline-Aware Conformal Prediction with Joint Coverage Guarantees for Multi-Stage NLP and LLM Pipelinescited by 7
- 2024CONFLARE: CONFormal LArge language model REtrievalcited by 6
- 2026Meet, Compare, or Abstain: LatWeave for Deterministic Multi-Hop Question Answering on Knowledge Latticescited by 0
- 2026Meet, Compare, or Abstain: LatWeave for Deterministic Multi-Hop Question Answering on Knowledge Lattices23 Sep 2026
- 2026PASC: Pipeline-Aware Conformal Prediction with Joint Coverage Guarantees for Multi-Stage NLP and LLM Pipelines12 May 2026
- 2024CONFLARE: CONFormal LArge language model REtrieval4 Apr 2024
- 2024C-RAG: Certified Generation Risks for Retrieval-Augmented Language Models5 Feb 2024
- 2023Conformal Language Modelingcited by 170
- 2024Language Models with Conformal Factuality Guaranteescited by 131
- 2024Large language model validity via enhanced conformal prediction methodscited by 92
- 2023Conformal PID Control for Time Series Predictioncited by 88
- 2023Improved Online Conformal Prediction via Strongly Adaptive Online Learningcited by 78
- 2022Learning to Defer to Multiple Experts: Consistent Surrogate Losses, Confidence Calibration, and Conformal Ensemblescited by 60
- 2024Mitigating LLM Hallucinations via Conformal Abstentioncited by 59
- 2024Conformal Prediction for Natural Language Processing: A Surveycited by 53
- 2023Conformal Decision Theory: Safe Autonomous Decisions from Imperfect Predictionscited by 50
- 2025Decision Theoretic Foundations for Conformal Prediction: Optimal Uncertainty Quantification for Risk-Averse Agentscited by 40
- 2022Calibrated Selective Classificationcited by 33
- 2023Object Pose Estimation with Statistical Guarantees: Conformal Keypoint Detection and Geometric Uncertainty Propagationcited by 33
12 most cited of 248 All 248 (JSON)
- 2026Adaptive Computation with Conformal Certification13 Oct 2026
- 2026CALM-5G: Event-Level Conformal Risk Control for Predictive Service-Assurance Alarms13 Oct 2026
- 2026Conformal Sequential Decision Making With Cost and Sublinear Policy Regret Guarantees10 Oct 2026
- 2026ConformalGuard: False-Positive-Controlled Action Gating for LM Classifiers9 Oct 2026
- 2026CopRoute: Dependence-Aware Conformal Routing for Language Models9 Oct 2026
- 2026Finding Blind Spots in AppWorld and WorkArena Task Verifiers6 Oct 2026
- 2026MIRTO: a registration-gated, multiverse-tested evaluation protocol for unsupervised anomaly segmentation in brain MRI1 Oct 2026
- 2026Benchmarking System One decision models against trained classifiers and language models for automated decision gates29 Sep 2026
- 2026Adaptive Safety Filtering for Frozen ACC Policies via Conformal Residual Calibration28 Sep 2026
- 2026RSD-Poker: Structure-Adaptive and Shift-Robust Risk-Utility Certification for Residual Policies in Imperfect-Information Games27 Sep 2026
- 2026Audit-First VAPO: Risk-Certified Selective Updates under Imperfect Verification27 Sep 2026
- 2026RAEGL: Risk-Aware Evidence-Gated Learning for Selective Contextual Routing under Temporal Shift27 Sep 2026
12 newest of 248 All 248 (JSON)