Pith. sign in

REVIEW 7 cited by

Challenges in Detoxifying Language Models

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 2109.07445 v1 pith:OJSQ77L6 submitted 2021-09-15 cs.CL cs.AIcs.CYcs.LG

Challenges in Detoxifying Language Models

classification cs.CL cs.AIcs.CYcs.LG
keywords toxicityautomaticevaluationhumanlanguagemitigationmodelsoften
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Large language models (LM) generate remarkably fluent text and can be efficiently adapted across NLP tasks. Measuring and guaranteeing the quality of generated text in terms of safety is imperative for deploying LMs in the real world; to this end, prior work often relies on automatic evaluation of LM toxicity. We critically discuss this approach, evaluate several toxicity mitigation strategies with respect to both automatic and human evaluation, and analyze consequences of toxicity mitigation in terms of model bias and LM quality. We demonstrate that while basic intervention strategies can effectively optimize previously established automatic metrics on the RealToxicityPrompts dataset, this comes at the cost of reduced LM coverage for both texts about, and dialects of, marginalized groups. Additionally, we find that human raters often disagree with high automatic toxicity scores after strong toxicity reduction interventions -- highlighting further the nuances involved in careful evaluation of LM toxicity.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

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

  1. Ethics Testing: Proactive Identification of Generative AI System Harms

    cs.SE 2026-04 unverdicted novelty 6.0

    Ethics testing is introduced as a systematic approach to generate tests that identify software harms induced by unethical behavior in generative AI outputs.

  2. GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

    cs.AI 2023-09 unverdicted novelty 6.0

    GPTFuzz is a black-box fuzzing framework that mutates seed jailbreak templates to automatically generate effective attacks, achieving over 90% success rates on models including ChatGPT and Llama-2.

  3. Ethical and social risks of harm from Language Models

    cs.CL 2021-12 accept novelty 6.0

    The authors provide a detailed taxonomy of 21 risks associated with language models, covering discrimination, information leaks, misinformation, malicious applications, interaction harms, and societal impacts like job...

  4. A General Language Assistant as a Laboratory for Alignment

    cs.CL 2021-12 conditional novelty 6.0

    Ranked preference modeling outperforms imitation learning for language model alignment and scales more favorably with model size.

  5. Where Does Toxicity Live? Mechanistic Localization and Targeted Suppression in Language Models

    cs.CL 2026-05 unverdicted novelty 5.0

    Toxicity in language models is disproportionately encoded in early MLP layers and can be localized via activation differentials then suppressed at inference time without gradient descent.

  6. TrustLLM: Trustworthiness in Large Language Models

    cs.CL 2024-01 unverdicted novelty 5.0

    TrustLLM defines eight trustworthiness principles, creates a six-dimension benchmark, and evaluates 16 LLMs showing proprietary models generally lead but some open-source ones are close while over-calibration can hurt...

  7. Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model

    cs.CL 2022-01 unverdicted novelty 5.0

    Trained the largest monolithic 530B-parameter transformer language model to date and reported new state-of-the-art zero- and few-shot results on multiple NLP benchmarks.