Pith. sign in

REVIEW 2 cited by

Detoxifying Large Language Models via Knowledge Editing

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2403.14472 v5 pith:UG2KSMON submitted 2024-03-21 cs.CL cs.AIcs.CVcs.HCcs.LG

classification cs.CLcs.AIcs.CVcs.HCcs.LG
keywords knowledgedetoxifyingeditingllmsapproachesbenchmarkdetoxifydinm
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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 and equips comprehensive metrics for systematic evaluation. 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. Then, we propose a simple yet effective baseline, dubbed Detoxifying with Intraoperative Neural Monitoring (DINM), to diminish the toxicity of LLMs within a few tuning steps via only one instance. We further provide an in-depth analysis of the internal mechanism for various detoxifying approaches, demonstrating that previous methods like SFT and DPO may merely suppress the activations of toxic parameters, while DINM mitigates the toxicity of the toxic parameters to a certain extent, making permanent adjustments. We hope that these insights could shed light on future work of developing detoxifying approaches and the underlying knowledge mechanisms of LLMs. Code and benchmark are available at https://github.com/zjunlp/EasyEdit.

Discussion (0). Sign in to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Isotropy Cliffs: The Geometric Signature of Decision-Making in Large Language Models

    cs.AI 2026-08 reject novelty 5.0 of 10

    Across five LLMs, a sharp decrease in embedding isotropy at a critical layer predicts multiple-choice accuracy, with Spearman correlations up to -0.92.

  2. Detoxification of Large Language Models through Output-layer Fusion with a Calibration Model

    cs.CL 2025-06 conditional novelty 5.0 of 10

    A small calibration model trained on non-toxic text is aligned and fused into the final layer of LLaMA-2-based LLMs, modestly reducing toxicity on RealToxicityPrompts but with mixed perplexity results.

Pith tools