Fairness in large language models: A taxonomic survey
Large Language Models (LLMs) have demonstrated remarkable success across various
domains. However, despite their promising performance in numerous real-world …
domains. However, despite their promising performance in numerous real-world …
On learning fairness and accuracy on multiple subgroups
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 …
prediction disparities under the criteria of group sufficiency. We focus on the scenario where …
Item-side Fairness of Large Language Model-based Recommendation System
Recommendation systems for Web content distribution intricately connect to the information
access and exposure opportunities for vulnerable populations. The emergence of Large …
access and exposure opportunities for vulnerable populations. The emergence of Large …
Bias and fairness in large language models: A survey
Rapid advancements of large language models (LLMs) have enabled the processing,
understanding, and generation of human-like text, with increasing integration into systems …
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
Gender inequality is embedded in our communication practices and perpetuated in
translation technologies. This becomes particularly apparent when translating into …
translation technologies. This becomes particularly apparent when translating into …
Exploiting biased models to de-bias text: A gender-fair rewriting model
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 …
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
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 …
study, we explore gender-neutral translation (GNT) as a form of gender inclusivity and a goal …
Debiasing large language models: research opportunities
Large language models (LLMs) are powerful decision-making tools widely adopted in
healthcare, finance, and transportation. Embracing the opportunities and innovations of …
healthcare, finance, and transportation. Embracing the opportunities and innovations of …
Test suites task: Evaluation of gender fairness in MT with MuST-SHE and INES
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 …
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 …
markers in the source language are expected to be resolved in the output. Conversely, this …