Pith. sign in

REVIEW 1 cited by

Implicit Bias in LLMs: A Survey

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 2503.02776 v1 pith:DYH4MW72 submitted 2025-03-04 cs.CL cs.AI

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

Due to the implement of guardrails by developers, Large language models (LLMs) have demonstrated exceptional performance in explicit bias tests. However, bias in LLMs may occur not only explicitly, but also implicitly, much like humans who consciously strive for impartiality yet still harbor implicit bias. The unconscious and automatic nature of implicit bias makes it particularly challenging to study. This paper provides a comprehensive review of the existing literature on implicit bias in LLMs. We begin by introducing key concepts, theories and methods related to implicit bias in psychology, extending them from humans to LLMs. Drawing on the Implicit Association Test (IAT) and other psychological frameworks, we categorize detection methods into three primary approaches: word association, task-oriented text generation and decision-making. We divide our taxonomy of evaluation metrics for implicit bias into two categories: single-value-based metrics and comparison-value-based metrics. We classify datasets into two types: sentences with masked tokens and complete sentences, incorporating datasets from various domains to reflect the broad application of LLMs. Although research on mitigating implicit bias in LLMs is still limited, we summarize existing efforts and offer insights on future challenges. We aim for this work to serve as a clear guide for researchers and inspire innovative ideas to advance exploration in this task.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Conversational AI as a Catalyst for Informal Learning: An Empirical Large-Scale Study on LLM Use in Everyday Learning

    cs.HC 2025-06 conditional novelty 6.0 of 10

    Most adults in a German Prolific sample report using large language models for informal learning, with four distinct learner profiles emerging from their usage patterns.

Pith tools