paper-with-me

홈 › Papers

Bridging the Fairness Gap: Enhancing Pre-trained Models with LLM-Generated Sentences

2025-01-12 · Liu Yu, Ludie Guo, Ping Kuang, Fan Zhou

Pre-trained language models (PLMs) are trained on data that inherently contains gender biases, leading to undesirable impacts. Traditional debiasing methods often rely on external corpora, which may lack quality, diversity, or demographic balance, affecting the effectiveness of debiasing. With the rise of large language models and their extensive knowledge, we propose enhancing fairness (Fair-Gender) in PLMs by absorbing coherent, attribute-balanced, and semantically rich sentences. However, these sentences cannot be directly used for debiasing due to alignment issues and the risk of negative transfer. We address this by applying causal analysis to estimate causal effects, filtering out unaligned sentences, and identifying aligned ones for incorporation into PLMs, thereby ensuring positive transfer. Experiments show that our approach significantly reduces gender biases in PLMs while preserving their language expressiveness.

📄 PDF Abstract BibTeX arXiv:2501.06795

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeDiversityFairness

Similar Papers 제목 키워드 기반

Human-Guided Fair Classification for Natural Language Processing

2022-12-20 · Florian E. Dorner, Momchil Peychev, Nikola Konstantinov, Naman Goel 외

Text classifiers have promising applications in high-stake tasks such as resume screening and content moderation. These classifiers must be fair and avoid discriminatory decisions by being invariant to perturbations of s…

ClassificationFairnessStyle Transfer

Toward Fairness in Text Generation via Mutual Information Minimization based on Importance Sampling

2023-02-25 · Rui Wang, Pengyu Cheng, Ricardo Henao

Pretrained language models (PLMs), such as GPT2, have achieved remarkable empirical performance in text generation tasks. However, pretrained on large-scale natural language corpora, the generated text from PLMs may exhi…

FairnessLanguage ModelingLanguage ModellingSentence+1

Widespread Gender and Pronoun Bias in Moral Judgments Across LLMs

2026-03-13 · Gustavo Lúcius Fernandes, Jeiverson C. V. M. Santos, Pedro O. S. Vaz-de-Melo arxiv

Large language models (LLMs) are increasingly used to assess moral or ethical statements, yet their judgments may reflect social and linguistic biases. This work presents a controlled, sentence-level study of how grammat…

SAFES: Sequential Privacy and Fairness Enhancing Data Synthesis for Responsible AI

2024-11-14 · Spencer Giddens, Fang Liu

As data-driven and AI-based decision making gains widespread adoption in most disciplines, it is crucial that both data privacy and decision fairness are appropriately addressed. While differential privacy (DP) provides …

Decision MakingFairness

Bridging Dictionary: AI-Generated Dictionary of Partisan Language Use

2024-07-12 · Hang Jiang, Doug Beeferman, William Brannon, Andrew Heyward 외

Words often carry different meanings for people from diverse backgrounds. Today's era of social polarization demands that we choose words carefully to prevent miscommunication, especially in political communication and j…

Language ModelingLanguage ModellingLarge Language Model