# Cleansing the Artificial Mind: A Self-Reflective Detoxification Framework for Large Language Models

arXiv: https://arxiv.org/abs/2601.11776 · HTML: https://mlsanity.com/paper/2601.11776/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Self-rewarding alignment and self-training, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 32 of its 43 references that are in the map.
- First posted on arXiv 16 Jan 2026.

## Placed in

- Synthetic data and self-improvement for LLMs / [Self-rewarding alignment and self-training](https://mlsanity.com/synth/self-rewarding-alignment-and-self-training/)

## Builds on (most cited first, 30 of 32)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (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)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [Self-Rewarding Language Models](https://mlsanity.com/paper/2401.10020/) (2024)
- [WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct](https://mlsanity.com/paper/2308.09583/) (2023)
- [Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond](https://mlsanity.com/paper/2304.13712/) (2023)
- [Latent Hatred: A Benchmark for Understanding Implicit Hate Speech](https://mlsanity.com/paper/2109.05322/) (2021)
- [A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity](https://mlsanity.com/paper/2401.01967/) (2024)
- [A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems](https://mlsanity.com/paper/2402.18013/) (2024)
- [Pretrained Language Models for Text Generation: A Survey](https://mlsanity.com/paper/2201.05273/) (2022)
- [Detoxifying Large Language Models via Knowledge Editing](https://mlsanity.com/paper/2403.14472/) (2024)
- [Beyond BLEU: Training Neural Machine Translation with Semantic Similarity](https://mlsanity.com/paper/1909.06694/) (2019)
- [Large Language Model-Aware In-Context Learning for Code Generation](https://mlsanity.com/paper/2310.09748/) (2023)
- [TEaR: Improving LLM-based Machine Translation with Systematic Self-Refinement](https://mlsanity.com/paper/2402.16379/) (2024)
- [Civil Rephrases Of Toxic Texts With Self-Supervised Transformers](https://mlsanity.com/paper/2102.05456/) (2021)
- [NLP for Counterspeech against Hate: A Survey and How-To Guide](https://mlsanity.com/paper/2403.20103/) (2024)
- [MedSyn: LLM-based Synthetic Medical Text Generation Framework](https://mlsanity.com/paper/2408.02056/) (2024)
- [Parameter-Efficient Detoxification with Contrastive Decoding](https://mlsanity.com/paper/2401.06947/) (2024)
- [Self-Evolved Reward Learning for LLMs](https://mlsanity.com/paper/2411.00418/) (2024)
- [Intent-conditioned and Non-toxic Counterspeech Generation using Multi-Task Instruction Tuning with RLAIF](https://mlsanity.com/paper/2403.10088/) (2024)
- [DetoxLLM: A Framework for Detoxification with Explanations](https://mlsanity.com/paper/2402.15951/) (2024)
- [The Dark Side of Human Feedback: Poisoning Large Language Models via User Inputs](https://mlsanity.com/paper/2409.00787/) (2024)
- [DESTEIN: Navigating Detoxification of Language Models via Universal Steering Pairs and Head-wise Activation Fusion](https://mlsanity.com/paper/2404.10464/) (2024)
- [A Survey On Enhancing Reinforcement Learning in Complex Environments: Insights from Human and LLM Feedback](https://mlsanity.com/paper/2411.13410/) (2024)
- [Large Language Models can be Strong Self-Detoxifiers](https://mlsanity.com/paper/2410.03818/) (2024)

## Built on by (most cited first, 1 of 1)

- [A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data](https://mlsanity.com/paper/2601.17717/) (2026)

## Abstract (arXiv)

Recent breakthroughs in Large Language Models (LLMs) have revealed remarkable generative capabilities and emerging self-regulatory mechanisms, including self-correction and self-rewarding. However, current detoxification techniques rarely exploit these built-in abilities; instead, they rely on external modules, labor-intensive data annotation, or human intervention --factors that hinder scalability and consistency. In this paper, we introduce a fully self-reflective detoxification framework that harnesses the inherent capacities of LLMs to detect, correct toxic content, and refine LLMs without external modules and data annotation. Specifically, we propose a Toxic Signal Detector --an internal self-identification mechanism, coupled with a systematic intervention process to transform toxic text into its non-toxic counterpart. This iterative procedure yields a contrastive detoxification dataset used to fine-tune the model, enhancing its ability for safe and coherent text generation. Experiments on benchmark datasets such as DetoxLLM and ParaDetox show that our method achieves better detoxification performance than state-of-the-art methods while preserving semantic fidelity. By obviating the need for human intervention or external components, this paper reveals the intrinsic self-detoxification ability of LLMs, offering a consistent and effective approach for mitigating harmful content generation. Ultimately, our findings underscore the potential for truly self-regulated language models, paving the way for more responsible and ethically guided text generation systems.