# Confess What You Know: Forget-Set Misalignment with Model Knowledge in LLM Unlearning

arXiv: https://arxiv.org/abs/2609.00605 · HTML: https://mlsanity.com/paper/2609.00605/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 23 of its 36 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Placed in

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

## Builds on (most cited first, 23 of 23)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [TOFU: A Task of Fictitious Unlearning for LLMs](https://mlsanity.com/paper/2401.06121/) (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)
- [Unlearn What You Want to Forget: Efficient Unlearning for LLMs](https://mlsanity.com/paper/2310.20150/) (2023)
- [What makes unlearning hard and what to do about it](https://mlsanity.com/paper/2406.01257/) (2024)
- [Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench](https://mlsanity.com/paper/2410.22108/) (2024)
- [Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond](https://mlsanity.com/paper/2502.19301/) (2025)
- [Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement](https://mlsanity.com/paper/2409.19732/) (2024)
- [CLEAR: Character Unlearning in Textual and Visual Modalities](https://mlsanity.com/paper/2410.18057/) (2024)
- [Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning](https://mlsanity.com/paper/2505.11953/) (2025)
- [A Duty to Forget, a Right to be Assured? Exposing Vulnerabilities in Machine Unlearning Services](https://mlsanity.com/paper/2309.08230/) (2023)
- [A Comprehensive Survey of Machine Unlearning Techniques for Large Language Models](https://mlsanity.com/paper/2503.01854/) (2025)
- [Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy](https://mlsanity.com/paper/2410.09591/) (2024)

## Abstract (arXiv)

Machine unlearning for large language models (LLMs) often assumes that a pre-defined forget set matches what the model has memorized, but this frequently breaks in realistic privacy settings where the original training data is inaccessible. We term this gap forget-set misalignment and identify two cases. In Under Unlearning, the forget set omits memorized information and leakage persists. In Out-of-Knowledge Unlearning, the algorithm is driven to "forget" knowledge the model never learned, perturbing parameters and degrading utility. Using gradient-level analysis, we show these behaviors arise from misaligned unlearning targets rather than specific optimization choices. We then propose CONfession-to-Forget-Set (CONFS), a data-blind framework that constructs model-aligned forget sets by eliciting and formalizing the model's memorized knowledge. Across synthetic, multimodal, and real-world benchmarks, CONFS approaches Gold-standard performance on several metrics and achieves a competitive forgetting-utility balance, while preserving utility better than other data-blind forget-set constructions.