REVIEW 4 cited by
Intrinsic Bias Metrics Do Not Correlate with Application Bias
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
Signed reviews
read the original abstract
Natural Language Processing (NLP) systems learn harmful societal biases that cause them to amplify inequality as they are deployed in more and more situations. To guide efforts at debiasing these systems, the NLP community relies on a variety of metrics that quantify bias in models. Some of these metrics are intrinsic, measuring bias in word embedding spaces, and some are extrinsic, measuring bias in downstream tasks that the word embeddings enable. Do these intrinsic and extrinsic metrics correlate with each other? We compare intrinsic and extrinsic metrics across hundreds of trained models covering different tasks and experimental conditions. Our results show no reliable correlation between these metrics that holds in all scenarios across tasks and languages. We urge researchers working on debiasing to focus on extrinsic measures of bias, and to make using these measures more feasible via creation of new challenge sets and annotated test data. To aid this effort, we release code, a new intrinsic metric, and an annotated test set focused on gender bias in hate speech.
Forward citations
Cited by 4 Pith papers
-
Evaluating Gender Bias Transfer between Pre-trained and Prompt-Adapted Language Models
Intrinsic and prompt-adapted gender biases in causal LLMs are highly correlated (Pearson rho >= 0.94) on WinoBias, contrary to earlier fine-tuning results.
-
Exploring Gender Bias Beyond Occupational Titles
The paper presents GenderLexicon and a ClozeGender score, reporting that action verbs and object nouns carry gender bias beyond occupational stereotypes in English and Japanese language models.
-
Deontological Keyword Bias: The Impact of Modal Expressions on Normative Judgments of Language Models
LLMs systematically treat modal words like 'must' as evidence of obligation even in non-obligatory contexts, more strongly than humans, and a few-shot plus reasoning prompt can lower the rate of such judgments.
-
LangFair: A Python Package for Assessing Bias and Fairness in Large Language Model Use Cases
LangFair is an open-source Python package that computes bias and fairness metrics for LLM use cases from user-provided prompts and responses, guided by a decision framework.
Discussion (0). Continue with ORCID to comment.