Fairness in large language models: A taxonomic survey

Z Chu, Z Wang, W Zhang - ACM SIGKDD explorations newsletter, 2024 - dl.acm.org
Large Language Models (LLMs) have demonstrated remarkable success across various
domains. However, despite their promising performance in numerous real-world …

On learning fairness and accuracy on multiple subgroups

C Shui, G Xu, Q Chen, J Li, CX Ling… - Advances in …, 2022 - proceedings.neurips.cc
We propose an analysis in fair learning that preserves the utility of the data while reducing
prediction disparities under the criteria of group sufficiency. We focus on the scenario where …

Item-side Fairness of Large Language Model-based Recommendation System

M Jiang, K Bao, J Zhang, W Wang, Z Yang… - Proceedings of the …, 2024 - dl.acm.org
Recommendation systems for Web content distribution intricately connect to the information
access and exposure opportunities for vulnerable populations. The emergence of Large …

Bias and fairness in large language models: A survey

IO Gallegos, RA Rossi, J Barrow, MM Tanjim… - Computational …, 2024 - direct.mit.edu
Rapid advancements of large language models (LLMs) have enabled the processing,
understanding, and generation of human-like text, with increasing integration into systems …

Hi guys or hi folks? benchmarking gender-neutral machine translation with the gente corpus

A Piergentili, B Savoldi, D Fucci, M Negri… - arxiv preprint arxiv …, 2023 - arxiv.org
Gender inequality is embedded in our communication practices and perpetuated in
translation technologies. This becomes particularly apparent when translating into …

Exploiting biased models to de-bias text: A gender-fair rewriting model

C Amrhein, F Schottmann, R Sennrich… - arxiv preprint arxiv …, 2023 - arxiv.org
Natural language generation models reproduce and often amplify the biases present in their
training data. Previous research explored using sequence-to-sequence rewriting models to …

Gender neutralization for an inclusive machine translation: from theoretical foundations to open challenges

A Piergentili, D Fucci, B Savoldi, L Bentivogli… - arxiv preprint arxiv …, 2023 - arxiv.org
Gender inclusivity in language technologies has become a prominent research topic. In this
study, we explore gender-neutral translation (GNT) as a form of gender inclusivity and a goal …

Debiasing large language models: research opportunities

V Yogarajan, G Dobbie, TT Keegan - … of the Royal Society of New …, 2025 - Taylor & Francis
Large language models (LLMs) are powerful decision-making tools widely adopted in
healthcare, finance, and transportation. Embracing the opportunities and innovations of …

Test suites task: Evaluation of gender fairness in MT with MuST-SHE and INES

B Savoldi, M Gaido, M Negri, L Bentivogli - arxiv preprint arxiv …, 2023 - arxiv.org
As part of the WMT-2023" Test suites" shared task, in this paper we summarize the results of
two test suites evaluations: MuST-SHE-WMT23 and INES. By focusing on the en-de and de …

Gender, names and other mysteries: Towards the ambiguous for gender-inclusive translation

D Saunders, K Olsen - arxiv preprint arxiv:2306.04573, 2023 - arxiv.org
The vast majority of work on gender in MT focuses on'unambiguous' inputs, where gender
markers in the source language are expected to be resolved in the output. Conversely, this …