Pith. sign in

REVIEW 7 cited by

CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked 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 2010.00133 v1 pith:45L3V6JU submitted 2020-09-30 cs.CL cs.AI

classification cs.CLcs.AI
keywords crows-pairsmodelslanguagegroupsstereotypesbenchmarkbiasbiased
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Pretrained language models, especially masked language models (MLMs) have seen success across many NLP tasks. However, there is ample evidence that they use the cultural biases that are undoubtedly present in the corpora they are trained on, implicitly creating harm with biased representations. To measure some forms of social bias in language models against protected demographic groups in the US, we introduce the Crowdsourced Stereotype Pairs benchmark (CrowS-Pairs). CrowS-Pairs has 1508 examples that cover stereotypes dealing with nine types of bias, like race, religion, and age. In CrowS-Pairs a model is presented with two sentences: one that is more stereotyping and another that is less stereotyping. The data focuses on stereotypes about historically disadvantaged groups and contrasts them with advantaged groups. We find that all three of the widely-used MLMs we evaluate substantially favor sentences that express stereotypes in every category in CrowS-Pairs. As work on building less biased models advances, this dataset can be used as a benchmark to evaluate progress.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

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

  1. How LLM Task-Adaptation Reshapes Alignment: A Multi-dimensional Study of Behavioral and Representational Drift

    cs.AI 2026-07 conditional novelty 6.0 of 10

    Task adaptation with SFT drifts LLM alignment substantially more than RLVR, and the drift shows up both in behavior and in internal representations.

  2. YouthSafe: A Youth-Centric Safety Benchmark and Safeguard Model for Large Language Models

    cs.HC 2025-09 conditional novelty 6.0 of 10

    Introduces YAIR, a youth-GenAI risk benchmark, and YouthSafe, a fine-tuned classifier with AUPRC 0.94 on it, though it compares a trained model to untrained baselines.

  3. McBE: A Multi-task Chinese Bias Evaluation Benchmark for Large Language Models

    cs.CL 2025-07 conditional novelty 6.0 of 10

    A new Chinese bias benchmark with 4,077 instances and five tasks indicates larger language models are less biased than smaller ones when bias is measured through understanding tasks.

  4. Adaptive Task Vectors for Large Language Models

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Adaptive Task Vectors use a small model to generate query-specific steering vectors for frozen LLMs, reporting strong accuracy and generalization, though the theoretical equivalences to LoRA and Prefix-Tuning are not ...

  5. When Tables Go Crazy: Evaluating Multimodal Models on French Financial Documents

    cs.CL 2026-02 conditional novelty 5.0 of 10

    A new French financial document benchmark shows vision-language models are strong at text/table extraction but brittle on charts and multi-turn dialogue, with accuracy converging near 50% in conversational settings.

  6. Investigating Intersectional Bias in Large Language Models using Confidence Disparities in Coreference Resolution

    cs.CL 2025-08 unverdicted novelty 5.0 of 10

    The abstract claims LLMs show up to 40% coreference confidence disparities across intersectional identities, but the article body is an unrelated paper on robotic fruit handling.

  7. Fairness Dynamics During Training

    cs.CL 2025-06 conditional novelty 5.0 of 10

    Gender bias in Pythia-6.9b grows sharply after about 80k training steps even as general performance improves, and stopping earlier could trade 1.7% LAMBADA accuracy for a large fairness gain.

Pith tools