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
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.
Forward citations
Cited by 7 Pith papers
-
How LLM Task-Adaptation Reshapes Alignment: A Multi-dimensional Study of Behavioral and Representational Drift
Task adaptation with SFT drifts LLM alignment substantially more than RLVR, and the drift shows up both in behavior and in internal representations.
-
YouthSafe: A Youth-Centric Safety Benchmark and Safeguard Model for Large Language Models
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.
-
McBE: A Multi-task Chinese Bias Evaluation Benchmark for Large Language Models
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.
-
Adaptive Task Vectors for Large Language Models
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 ...
-
When Tables Go Crazy: Evaluating Multimodal Models on French Financial Documents
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.
-
Investigating Intersectional Bias in Large Language Models using Confidence Disparities in Coreference Resolution
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.
-
Fairness Dynamics During Training
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.
Discussion (0). Sign in to comment.