Pith. sign in

REVIEW 3 cited by

Towards Understanding and Mitigating Social Biases in 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 2106.13219 v1 pith:PO3FNARI submitted 2021-06-24 cs.CL cs.AIcs.CYcs.LG

classification cs.CLcs.AIcs.CYcs.LG
keywords biasessocialmitigatingtowardscrucialgenerationlanguagemodels
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

As machine learning methods are deployed in real-world settings such as healthcare, legal systems, and social science, it is crucial to recognize how they shape social biases and stereotypes in these sensitive decision-making processes. Among such real-world deployments are large-scale pretrained language models (LMs) that can be potentially dangerous in manifesting undesirable representational biases - harmful biases resulting from stereotyping that propagate negative generalizations involving gender, race, religion, and other social constructs. As a step towards improving the fairness of LMs, we carefully define several sources of representational biases before proposing new benchmarks and metrics to measure them. With these tools, we propose steps towards mitigating social biases during text generation. Our empirical results and human evaluation demonstrate effectiveness in mitigating bias while retaining crucial contextual information for high-fidelity text generation, thereby pushing forward the performance-fairness Pareto frontier.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. STEREODISCO: Discovering Stereotypicality in LLMs

    cs.AI 2026-07 conditional novelty 7.0 of 10

    LLMs encode stereotypes along recoverable geometric axes in attention heads, and two tested LLMs share more stereotype content with each other than with documented human stereotypes.

  2. The Alignment Veto: How Safety Training Suppresses Cultural Knowledge in LLMs

    cs.CL 2025-10 reject novelty 6.0 of 10

    The full text builds the MENA Values benchmark (864 questions, 7 models) and reports that LLM cultural answers shift with language, decline with reasoning prompts, and hide strong internal preferences behind refusals—...

  3. More is Less? A Simulation-Based Approach to Dynamic Interactions between Biases in Multimodal Models

    stat.ML 2024-12 reject novelty 3.0 of 10

    A heuristic, simulation-based framework classifies multimodal bias interactions as amplification, mitigation, or neutrality, applied to the MMBias dataset.

Pith tools