English
Related papers

Related papers: Measuring and Reducing Gendered Correlations in Pr…

200 papers

The emergence of reinforcement learning in post-training of large language models has sparked significant interest in reward models. Reward models assess the quality of sampled model outputs to generate training signals. This task is also…

Computation and Language · Computer Science 2025-10-06 Sebastian Gehrmann

Various types of social biases have been reported with pretrained Masked Language Models (MLMs) in prior work. However, multiple underlying factors are associated with an MLM such as its model size, size of the training data, training…

Computation and Language · Computer Science 2023-10-24 Yi Zhou , Jose Camacho-Collados , Danushka Bollegala

While Large Language Models achieve state-of-the-art results across a wide range of NLP tasks, they remain prone to systematic biases. Among these, gender bias is particularly salient in MT, due to systematic differences across languages in…

Computation and Language · Computer Science 2026-03-19 Chiara Manna , Hosein Mohebbi , Afra Alishahi , Frédéric Blain , Eva Vanmassenhove

Vision-language models can encode societal biases and stereotypes, but there are challenges to measuring and mitigating these multimodal harms due to lacking measurement robustness and feature degradation. To address these challenges, we…

Machine Learning · Computer Science 2022-10-27 Hugo Berg , Siobhan Mackenzie Hall , Yash Bhalgat , Wonsuk Yang , Hannah Rose Kirk , Aleksandar Shtedritski , Max Bain

Word embeddings trained on large corpora have shown to encode high levels of unfair discriminatory gender, racial, religious and ethnic biases. In contrast, human-written dictionaries describe the meanings of words in a concise, objective…

Computation and Language · Computer Science 2021-01-26 Masahiro Kaneko , Danushka Bollegala

Model fairness is an essential element for Trustworthy AI. While many techniques for model fairness have been proposed, most of them assume that the training and deployment data distributions are identical, which is often not true in…

Machine Learning · Computer Science 2023-02-07 Yuji Roh , Kangwook Lee , Steven Euijong Whang , Changho Suh

Due to their similarity-based learning objectives, pretrained sentence encoders often internalize stereotypical assumptions that reflect the social biases that exist within their training corpora. In this paper, we describe several kinds of…

Computation and Language · Computer Science 2023-03-13 Hongyin Luo , James Glass

Modern models for common NLP tasks often employ machine learning techniques and train on journalistic, social media, or other culturally-derived text. These have recently been scrutinized for racial and gender biases, rooting from inherent…

Computation and Language · Computer Science 2026-01-27 Scott Friedman , Sonja Schmer-Galunder , Anthony Chen , Jeffrey Rye

Unsupervised cross-lingual pretraining has achieved strong results in neural machine translation (NMT), by drastically reducing the need for large parallel data. Most approaches adapt masked-language modeling (MLM) to sequence-to-sequence…

Computation and Language · Computer Science 2021-06-11 Christos Baziotis , Ivan Titov , Alexandra Birch , Barry Haddow

Predictive algorithms have a powerful potential to offer benefits in areas as varied as medicine or education. However, these algorithms and the data they use are built by humans, consequently, they can inherit the bias and prejudices…

Human-Computer Interaction · Computer Science 2022-03-22 Cristina Manresa-Yee , Silvia Ramis

Multilingual language models were shown to allow for nontrivial transfer across scripts and languages. In this work, we study the structure of the internal representations that enable this transfer. We focus on the representation of gender…

Computation and Language · Computer Science 2022-08-15 Hila Gonen , Shauli Ravfogel , Yoav Goldberg

Language models (LMs) have become pivotal in the realm of technological advancements. While their capabilities are vast and transformative, they often include societal biases encoded in the human-produced datasets used for their training.…

Computation and Language · Computer Science 2024-01-30 Iñigo Parra

Progress in pre-trained language models has led to a surge of impressive results on downstream tasks for natural language understanding. Recent work on probing pre-trained language models uncovered a wide range of linguistic properties…

Computation and Language · Computer Science 2022-03-22 Zeming Chen , Qiyue Gao

Adapting general-purpose language models to new skills is currently an expensive process that must be repeated as new instruction datasets targeting new skills are created, or can cause the models to forget older skills. In this work, we…

Computation and Language · Computer Science 2024-10-18 Jacob Morrison , Noah A. Smith , Hannaneh Hajishirzi , Pang Wei Koh , Jesse Dodge , Pradeep Dasigi

Model merging, particularly through weight averaging, has shown surprising effectiveness in saving computations and improving model performance without any additional training. However, the interpretability of why and how this technique…

Machine Learning · Computer Science 2025-08-20 Hu Wang , Congbo Ma , Ibrahim Almakky , Ian Reid , Gustavo Carneiro , Mohammad Yaqub

In this work, we propose ModelPred, a framework that helps to understand the impact of changes in training data on a trained model. This is critical for building trust in various stages of a machine learning pipeline: from cleaning…

Machine Learning · Computer Science 2022-12-27 Yingyan Zeng , Jiachen T. Wang , Si Chen , Hoang Anh Just , Ran Jin , Ruoxi Jia

We re-evaluate the standard practice of sharing weights between input and output embeddings in state-of-the-art pre-trained language models. We show that decoupled embeddings provide increased modeling flexibility, allowing us to…

Computation and Language · Computer Science 2020-10-27 Hyung Won Chung , Thibault Févry , Henry Tsai , Melvin Johnson , Sebastian Ruder

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.…

Computation and Language · Computer Science 2021-06-25 Paul Pu Liang , Chiyu Wu , Louis-Philippe Morency , Ruslan Salakhutdinov

Real-world datasets often encode stereotypes and societal biases. Such biases can be implicitly captured by trained models, leading to biased predictions and exacerbating existing societal preconceptions. Existing debiasing methods, such as…

Machine Learning · Computer Science 2022-05-06 Aili Shen , Xudong Han , Trevor Cohn , Timothy Baldwin , Lea Frermann

The successful application of neural methods to machine translation has realized huge quality advances for the community. With these improvements, many have noted outstanding challenges, including the modeling and treatment of gendered…

Computation and Language · Computer Science 2020-10-16 Hila Gonen , Kellie Webster