On the Robustness of Knowledge Editing for Detoxification

• URL: http://arxiv.org/abs/2602.10504v1
• Date: Wed, 11 Feb 2026 04:05:23 GMT
• Title: On the Robustness of Knowledge Editing for Detoxification
• Abstract summary: We propose a robustness-oriented evaluation framework for Knowledge-based (KE) detoxification.<n>Our results indicate that KE-based detoxification is robust only for certain models, limited numbers of detoxification objectives, and a subset of languages.
• Score: 8.893810228798285
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Knowledge-Editing-based (KE-based) detoxification has emerged as a promising approach for mitigating harmful behaviours in Large Language Models. Existing evaluations, however, largely rely on automatic toxicity classifiers, implicitly assuming that reduced toxicity scores reflect genuine behavioural suppression. In this work, we propose a robustness-oriented evaluation framework for KE-based detoxification that examines its reliability beyond standard classifier-based metrics along three dimensions: optimisation robustness, compositional robustness, and cross-lingual robustness. We identify pseudo-detoxification as a common failure mode, where apparent toxicity reductions arise from degenerate generation behaviours rather than meaningful suppression of unsafe content. We further show that detoxification effectiveness degrades when multiple unsafe behaviours are edited jointly, and that both monolingual and cross-lingual detoxification remain effective only under specific model-method combinations. Overall, our results indicate that KE-based detoxification is robust only for certain models, limited numbers of detoxification objectives, and a subset of languages.

Related papers

• Where Does Toxicity Live? Mechanistic Localization and Targeted Suppression in Language Models [1.2040549525117266]
  Large language models frequently generate toxic, hateful, or harmful content.<n>We introduce Meow2X and TRNE, two complementary retraining-free frameworks that localize toxicity to specific layers and neurons.<n>Our analysis reveals that toxicity is disproportionately encoded in early gradient layers, varies across architectures, and is systematically underestimated by single-evaluator setups.
  arXiv  Detail & Related papers  (2026-05-27T05:41:19Z)
• Detoxification for LLM: From Dataset Itself [69.09071947137926]
  Existing detoxification methods for large language models mainly focus on post-training stage or inference time, while few tackle the source of toxicity, namely, the dataset itself.<n>We attempt to detoxify directly on raw corpora with SoCD (Soft Contrastive Decoding), which guides an LLM to localize and rewrite toxic spans in raw data while preserving semantics.<n>On GPT2-XL, HSPD attains state-of-the-art detoxification, reducing Toxicity Probability (TP) from 0.42 to 0.18 and Maximum Expected Toxicity (EMT) from 0.43 to 0.20.
  arXiv  Detail & Related papers  (2026-04-21T06:12:29Z)
• Unveiling Covert Toxicity in Multimodal Data via Toxicity Association Graphs: A Graph-Based Metric and Interpretable Detection Framework [58.01529356381494]
  We propose a novel detection framework based on Toxicity Association Graphs (TAGs)<n>We introduce the first quantifiable metric for hidden toxicity, the Multimodal Toxicity Covertness (MTC)<n>Our approach enables precise identification of covert toxicity while preserving full interpretability of the decision-making process.
  arXiv  Detail & Related papers  (2026-02-03T08:54:25Z)
• Cleansing the Artificial Mind: A Self-Reflective Detoxification Framework for Large Language Models [14.566005698357747]
  Large Language Models (LLMs) have revealed remarkable generative capabilities and emerging self-regulatory mechanisms.<n>We introduce a fully self-reflective detoxification framework that harnesses the inherent capacities of LLMs to detect, correct toxic content.<n>Our findings underscore the potential for truly self-regulated language models, paving the way for more responsible and ethically guided text generation systems.
  arXiv  Detail & Related papers  (2026-01-16T21:01:26Z)
• Rethinking Toxicity Evaluation in Large Language Models: A Multi-Label Perspective [104.09817371557476]
  Large language models (LLMs) have achieved impressive results across a range of natural language processing tasks.<n>Their potential to generate harmful content has raised serious safety concerns.<n>We introduce three novel multi-label benchmarks for toxicity detection.
  arXiv  Detail & Related papers  (2025-10-16T06:50:33Z)
• Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing [77.75609817898035]
  Large Language Models (LLMs) have demonstrated impressive performance across various tasks, yet they remain vulnerable to generating toxic content.<n>We propose textscAutoregressive textscReward textscGuided textscRe presentation textscEditing (ARGRE)<n>ARGRE explicitly models toxicity transitions within the latent representation space, enabling stable and precise reward-guided editing.
  arXiv  Detail & Related papers  (2025-09-24T03:40:32Z)
• Adaptive Detoxification: Safeguarding General Capabilities of LLMs through Toxicity-Aware Knowledge Editing [49.85884082568318]
  ToxEdit is a toxicity-aware knowledge editing approach.<n>It dynamically detects toxic activation patterns during forward propagation.<n>It then routes computations through adaptive inter-layer pathways to mitigate toxicity effectively.
  arXiv  Detail & Related papers  (2025-05-28T12:37:06Z)
• Breaking mBad! Supervised Fine-tuning for Cross-Lingual Detoxification [39.711527571739666]
  "Cross-lingual Detoxification" is a paradigm that mitigates toxicity in large language models.<n>We analyze toxicity reduction in cross-distribution settings and investigate how mitigation impacts model performance on non-toxic tasks.
  arXiv  Detail & Related papers  (2025-05-22T14:30:14Z)
• Detoxifying Large Language Models via Knowledge Editing [57.0669577257301]
  This paper investigates using knowledge editing techniques to detoxify Large Language Models (LLMs) We construct a benchmark, SafeEdit, which covers nine unsafe categories with various powerful attack prompts. We conduct experiments with several knowledge editing approaches, indicating that knowledge editing has the potential to detoxify LLMs with a limited impact on general performance efficiently.
  arXiv  Detail & Related papers  (2024-03-21T15:18:30Z)
• Contrastive Perplexity for Controlled Generation: An Application in Detoxifying Large Language Models [21.341749351654453]
  The generation of toxic content by large language models (LLMs) remains a critical challenge for the safe deployment of language technology.<n>We propose a novel framework for implicit knowledge editing and controlled text generation by fine-tuning LLMs with a prototype-based contrastive perplexity objective.
  arXiv  Detail & Related papers  (2024-01-16T16:49:39Z)
• Detoxifying Language Models with a Toxic Corpus [16.7345472998388]
  We propose to use toxic corpus as an additional resource to reduce the toxicity. Our result shows that toxic corpus can indeed help to reduce the toxicity of the language generation process substantially.
  arXiv  Detail & Related papers  (2022-04-30T18:25:18Z)
• Reward Modeling for Mitigating Toxicity in Transformer-based Language Models [0.0]
  Transformer-based language models are able to generate fluent text and be efficiently adapted across various natural language generation tasks. Language models that are pretrained on large unlabeled web text corpora have been shown to suffer from degenerating toxic content and social bias behaviors. We propose Reinforce-Detoxify; A reinforcement learning-based method for mitigating toxicity in language models.
  arXiv  Detail & Related papers  (2022-02-19T19:26:22Z)
• Challenges in Automated Debiasing for Toxic Language Detection [81.04406231100323]
  Biased associations have been a challenge in the development of classifiers for detecting toxic language. We investigate recently introduced debiasing methods for text classification datasets and models, as applied to toxic language detection. Our focus is on lexical (e.g., swear words, slurs, identity mentions) and dialectal markers (specifically African American English)
  arXiv  Detail & Related papers  (2021-01-29T22:03:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.