# DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning

arXiv: https://arxiv.org/abs/2511.05784 · HTML: https://mlsanity.com/paper/2511.05784/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 60 of its 71 references that are in the map.
- First posted on arXiv 8 Nov 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 30 of 60)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [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)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [Yi: Open Foundation Models by 01.AI](https://mlsanity.com/paper/2403.04652/) (2024)
- [Automatic Chain of Thought Prompting in Large Language Models](https://mlsanity.com/paper/2210.03493/) (2022)
- [Textbooks Are All You Need II: phi-1.5 technical report](https://mlsanity.com/paper/2309.05463/) (2023)
- [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)
- [Zephyr: Direct Distillation of LM Alignment](https://mlsanity.com/paper/2310.16944/) (2023)
- [Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning](https://mlsanity.com/paper/2404.05868/) (2024)
- [Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey](https://mlsanity.com/paper/2111.01243/) (2021)
- [Who's Harry Potter? Approximate Unlearning in LLMs](https://mlsanity.com/paper/2310.02238/) (2023)
- [Measuring short-form factuality in large language models](https://mlsanity.com/paper/2411.04368/) (2024)
- [Deliberative Alignment: Reasoning Enables Safer Language Models](https://mlsanity.com/paper/2412.16339/) (2024)

## Built on by (most cited first, 7 of 7)

- [CAP: Controllable Alignment Prompting for Unlearning in LLMs](https://mlsanity.com/paper/2604.21251/) (2026)
- [Observations and Remedies for Large Language Model Bias in Self-Consuming Performative Loop](https://mlsanity.com/paper/2601.05184/) (2026)
- [Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning](https://mlsanity.com/paper/2605.16776/) (2026)
- [SoK: Unlearnability and Unlearning for Model Dememorization](https://mlsanity.com/paper/2605.11592/) (2026)
- [DualOptim+: Bridging Shared and Decoupled Optimizer States for Better Machine Unlearning in Large Language Models](https://mlsanity.com/paper/2605.21539/) (2026)
- [ICCU: In-Context Continual Unlearning via Pattern-Induced Refusal Rules](https://mlsanity.com/paper/2605.27138/) (2026)
- [UnlearningSoup: Is Repeated Tuning Necessary for Large Language Model Unlearning?](https://mlsanity.com/paper/2609.37076/) (2026)

## Abstract (arXiv)

Unlearning in Large Language Models (LLMs) is crucial for protecting private data and removing harmful knowledge. Most existing approaches rely on fine-tuning to balance unlearning efficiency with general language capabilities. However, these methods typically require training or access to retain data, which is often unavailable in real world scenarios. Although these methods can perform well when both forget and retain data are available, few works have demonstrated equivalent capability in more practical, data-limited scenarios. To overcome these limitations, we propose Detect-Reasoning Augmented GeneratiON (DRAGON), a systematic, reasoning-based framework that utilizes in-context chain-of-thought (CoT) instructions to guard deployed LLMs before inference. Instead of modifying the base model, DRAGON leverages the inherent instruction-following ability of LLMs and introduces a lightweight detection module to identify forget-worthy prompts without any retain data. These are then routed through a dedicated CoT guard model to enforce safe and accurate in-context intervention. To robustly evaluate unlearning performance, we introduce novel metrics for unlearning performance and the continual unlearning setting. Extensive experiments across three representative unlearning tasks validate the effectiveness of DRAGON, demonstrating its strong unlearning capability, scalability, and applicability in practical scenarios.