# Inference-time Unlearning Using Conformal Prediction

arXiv: https://arxiv.org/abs/2602.03787 · HTML: https://mlsanity.com/paper/2602.03787/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 51 of its 63 references that are in the map.
- First posted on arXiv 3 Feb 2026.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 30 of 51)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Adafactor: Adaptive Learning Rates with Sublinear Memory Cost](https://mlsanity.com/paper/1804.04235/) (2018)
- [A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification](https://mlsanity.com/paper/2107.07511/) (2021)
- [Certified Data Removal from Machine Learning Models](https://mlsanity.com/paper/1911.03030/) (2019)
- [TOFU: A Task of Fictitious Unlearning for LLMs](https://mlsanity.com/paper/2401.06121/) (2024)
- [The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning](https://mlsanity.com/paper/2403.03218/) (2024)
- [Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning](https://mlsanity.com/paper/2404.05868/) (2024)
- [Knowledge Unlearning for Mitigating Privacy Risks in Language Models](https://mlsanity.com/paper/2210.01504/) (2022)
- [Remember What You Want to Forget: Algorithms for Machine Unlearning](https://mlsanity.com/paper/2103.03279/) (2021)
- [Large Language Model Unlearning](https://mlsanity.com/paper/2310.10683/) (2023)
- [Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Control](https://mlsanity.com/paper/2110.01052/) (2021)
- [Towards Unbounded Machine Unlearning](https://mlsanity.com/paper/2302.09880/) (2023)
- [MUSE: Machine Unlearning Six-Way Evaluation for Language Models](https://mlsanity.com/paper/2407.06460/) (2024)
- [Rethinking Machine Unlearning for Large Language Models](https://mlsanity.com/paper/2402.08787/) (2024)
- [Approximate Data Deletion from Machine Learning Models](https://mlsanity.com/paper/2002.10077/) (2020)
- [Unlearn What You Want to Forget: Efficient Unlearning for LLMs](https://mlsanity.com/paper/2310.20150/) (2023)
- [Adaptive Machine Unlearning](https://mlsanity.com/paper/2106.04378/) (2021)
- [On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning](https://mlsanity.com/paper/2110.11891/) (2021)
- [Conformal Language Modeling](https://mlsanity.com/paper/2306.10193/) (2023)
- [Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks](https://mlsanity.com/paper/2309.17410/) (2023)
- [Language Models with Conformal Factuality Guarantees](https://mlsanity.com/paper/2402.10978/) (2024)
- [BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Sampling](https://mlsanity.com/paper/2406.00832/) (2024)
- [Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment](https://mlsanity.com/paper/2503.21878/) (2025)
- [A Conformal Prediction Approach to Explore Functional Data](https://mlsanity.com/paper/1302.6452/) (2013)
- [RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models](https://mlsanity.com/paper/2406.10890/) (2024)
- [Right to be Forgotten in the Era of Large Language Models: Implications, Challenges, and Solutions](https://mlsanity.com/paper/2307.03941/) (2023)
- [Evaluation of Best-of-N Sampling Strategies for Language Model Alignment](https://mlsanity.com/paper/2502.12668/) (2025)

## Built on by (most cited first, 2 of 2)

- [Published Unlearning Numbers Move Per Checkpoint, and Not Because the Removed Data Survives: An Audit of 263 Released Batch-Normalized Checkpoints](https://mlsanity.com/paper/2609.11490/) (2026)
- [UNBIND: UNlearning By INference-time Directional Steering for Code LLMs](https://mlsanity.com/paper/2609.35913/) (2026)

## Abstract (arXiv)

Machine unlearning is the process of efficiently removing specific information from a trained machine learning model without retraining from scratch. Existing unlearning methods, which often provide provable guarantees, typically involve retraining a subset of model parameters based on a forget set. While these approaches show promise in certain scenarios, their underlying assumptions are often challenged in real-world applications -- particularly when applied to generative models. Furthermore, updating parameters using these unlearning procedures often degrades the general-purpose capabilities the model acquired during pre-training. Motivated by these shortcomings, this paper considers the paradigm of inference time unlearning -- wherein, the generative model is equipped with an (approximately correct) verifier that judges whether the model's response satisfies appropriate unlearning guarantees. This paper introduces a framework that iteratively refines the quality of the generated responses using feedback from the verifier without updating the model parameters. The proposed framework leverages conformal prediction to reduce computational overhead and provide distribution-free unlearning guarantees. This paper's approach significantly outperforms existing state-of-the-art methods, reducing unlearning error by up to 93% across challenging unlearning benchmarks.