Pith. sign in

REVIEW 5 cited by

Detoxifying Language Models Risks Marginalizing Minority Voices

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2104.06390 v1 pith:7DKKB7LW submitted 2021-04-13 cs.CL cs.LG

Albert Xu , Eshaan Pathak , Eric Wallace , Suchin Gururangan , Maarten Sap , Dan Klein This is my paper
classification cs.CLcs.LG
keywords detoxificationlanguagegroupsmarginalizedminoritymodelstechniquesused
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Language models (LMs) must be both safe and equitable to be responsibly deployed in practice. With safety in mind, numerous detoxification techniques (e.g., Dathathri et al. 2020; Krause et al. 2020) have been proposed to mitigate toxic LM generations. In this work, we show that current detoxification techniques hurt equity: they decrease the utility of LMs on language used by marginalized groups (e.g., African-American English and minority identity mentions). In particular, we perform automatic and human evaluations of text generation quality when LMs are conditioned on inputs with different dialects and group identifiers. We find that detoxification makes LMs more brittle to distribution shift, especially on language used by marginalized groups. We identify that these failures stem from detoxification methods exploiting spurious correlations in toxicity datasets. Overall, our results highlight the tension between the controllability and distributional robustness of LMs.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

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

  1. Red Teaming Language Models with Language Models

    cs.CL 2022-02 conditional novelty 7.0 of 10

    One language model can generate diverse test cases to automatically uncover tens of thousands of harmful behaviors, including offensive replies and privacy leaks, in a large target language model.

  2. Test-Time Scaling via Error Localization

    cs.LG 2026-07 conditional novelty 6.0 of 10

    TTEL uses feedback-induced token probability drops to localize the first error in a failed reasoning trace and branch a new generation from that prefix, improving pass@k per token on coding and math benchmarks.

  3. On The Effectiveness-Fluency Trade-Off In LLM Conditioning: A Systematic Study

    cs.CL 2026-06 unverdicted novelty 6.0 of 10

    Systematic experiments reveal that activation steering trades fluency for concept control, is less effective on instruction-tuned models, and that prompting/SFT excel at injection but not removal, with textual metrics...

  4. Ethical and social risks of harm from Language Models

    cs.CL 2021-12 accept novelty 6.0 of 10

    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...

  5. PaLM 2 Technical Report

    cs.CL 2023-05 unverdicted novelty 5.0 of 10

    PaLM 2 reports state-of-the-art results on language, reasoning, and multilingual tasks with improved efficiency over PaLM.

Pith tools