paper-with-me

Papers

FairDistillation: Mitigating Stereotyping in Language Models

2022-07-10 · Pieter Delobelle, Bettina Berendt

Large pre-trained language models are successfully being used in a variety of tasks, across many languages. With this ever-increasing usage, the risk of harmful side effects also rises, for example by reproducing and reinforcing stereotypes. However, detecting and mitigating these harms is difficult to do in general and becomes computationally expensive when tackling multiple languages or when considering different biases. To address this, we present FairDistillation: a cross-lingual method based on knowledge distillation to construct smaller language models while controlling for specific biases. We found that our distillation method does not negatively affect the downstream performance on most tasks and successfully mitigates stereotyping and representational harms. We demonstrate that FairDistillation can create fairer language models at a considerably lower cost than alternative approaches.

📄 PDF Abstract BibTeX arXiv:2207.04546

Code (1)

ipieter/universal-distillation pytorch

Tasks

Knowledge Distillation

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

How Are LLMs Mitigating Stereotyping Harms? Learning from Search Engine Studies

2024-07-16 · Alina Leidinger, Richard Rogers

With the widespread availability of LLMs since the release of ChatGPT and increased public scrutiny, commercial model development appears to have focused their efforts on 'safety' training concerning legal liabilities at…

Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology

2019-06-11 · ACL 2019 7 · Ran Zmigrod, Sabrina J. Mielke, Hanna Wallach, Ryan Cotterell

Gender stereotypes are manifest in most of the world's languages and are consequently propagated or amplified by NLP systems. Although research has focused on mitigating gender stereotypes in English, the approaches that…

counterfactualData Augmentation

Wait, am I Being Fair? Characterizing Deductive Stereotyping and Mitigating It with Fair-GCG

2026-06-30 · Naihao Deng, Yilun Zhu, Joan Nwatu, Clayton Scott 외 arxiv

Warning: This paper contains several toxic and offensive statements. While reasoning generally improves fairness in recent large language models (LLMs), failures persist. In this work, we identify a failure mode, deducti…

Towards Understanding and Mitigating Social Biases in Language Models

2021-06-24 · Paul Pu Liang, Chiyu Wu, Louis-Philippe Morency, Ruslan Salakhutdinov

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-m…

Decision MakingFairnessText Generation

FairPrism: Evaluating Fairness-Related Harms in Text Generation

2023-07-01 · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics 2023 7 · Eve Fleisig, Aubrie Amstutz, Chad Atalla, Su Lin Blodgett 외

It is critical to measure and mitigate fairness- related harms caused by AI text generation systems, including stereotyping and demeaning harms. To that end, we introduce FairPrism, a dataset of 5,000 examples of AI-gene…

FairnessText Generation