Pith. sign in

REVIEW 6 cited by

Gender Bias in Contextualized Word Embeddings

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 1904.03310 v1 pith:H6QVQCUW submitted 2019-04-05 cs.CL

Jieyu Zhao , Tianlu Wang , Mark Yatskar , Ryan Cotterell , Vicente Ordonez , Kai-Wei Chang This is my paper · ORCID
classification cs.CL
keywords biaselmogendercontextualizedembeddingsentitiesfemaleinformation
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this paper, we quantify, analyze and mitigate gender bias exhibited in ELMo's contextualized word vectors. First, we conduct several intrinsic analyses and find that (1) training data for ELMo contains significantly more male than female entities, (2) the trained ELMo embeddings systematically encode gender information and (3) ELMo unequally encodes gender information about male and female entities. Then, we show that a state-of-the-art coreference system that depends on ELMo inherits its bias and demonstrates significant bias on the WinoBias probing corpus. Finally, we explore two methods to mitigate such gender bias and show that the bias demonstrated on WinoBias can be eliminated.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

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

  1. Explaining GAND: A Resource on Gender-Ambiguous Natural Data & Contrastive Attribution

    cs.CL 2026-05 conditional novelty 7.0 of 10

    GAND is a new 5,047-sentence natural benchmark of English sentences with ambiguous referent gender; contrastive saliency analysis of a 1,000-sentence subset shows MT models favor masculine forms and attend to nearby c...

  2. Mitigating Gender Bias in Contextual Word Embeddings

    cs.CL 2024-11 reject novelty 6.0 of 10

    Regularized masked-language modeling and name-masking reduce gender bias in embeddings, but the contextual results rely heavily on evaluation metrics aligned with the training objective.

  3. Good Secretaries, Bad Truck Drivers? Occupational Gender Stereotypes in Sentiment Analysis

    cs.CL 2019-06 unverdicted novelty 6.0 of 10

    Authors release a new 800-sentence gender-balanced profession dataset and use it to test occupational gender stereotypes in three sentiment analysis models.

  4. Surface Fairness, Deep Bias: A Comparative Study of Bias in Language Models

    cs.CL 2025-06 conditional novelty 5.0 of 10

    Language models show negligible persona-based differences on MMLU benchmarks but large, income-relevant differences when asked for salary negotiation advice.

  5. EQUATOR: A Deterministic Framework for Evaluating LLM Reasoning with Open-Ended Questions. # v1.0.0-beta

    cs.CL 2024-12 reject novelty 4.0 of 10

    EQUATOR uses vector search to fetch a human reference answer and a binary LLM grader to score open-ended LLM responses, producing far lower scores than standard benchmarks.

  6. Bias in Large Language Models: Origin, Evaluation, and Mitigation

    cs.CL 2024-11 unverdicted novelty 2.0 of 10

    A literature review that categorizes bias in LLMs, surveys evaluation and mitigation techniques, and discusses ethical implications.

Pith tools