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
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.
Forward citations
Cited by 3 Pith papers
-
STEREODISCO: Discovering Stereotypicality in LLMs
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.
-
The Alignment Veto: How Safety Training Suppresses Cultural Knowledge in LLMs
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—...
-
More is Less? A Simulation-Based Approach to Dynamic Interactions between Biases in Multimodal Models
A heuristic, simulation-based framework classifies multimodal bias interactions as amplification, mitigation, or neutrality, applied to the MMBias dataset.
Discussion (0). Continue with ORCID to comment.