English
Related papers

Related papers: A Robust Bias Mitigation Procedure Based on the St…

200 papers

Mitigating biases in machine learning models has become an increasing concern in Natural Language Processing (NLP), particularly in developing fair text embeddings, which are crucial yet challenging for real-world applications like search…

Computation and Language · Computer Science 2024-06-25 Wenlong Deng , Blair Chen , Beidi Zhao , Chiyu Zhang , Xiaoxiao Li , Christos Thrampoulidis

Recently, sentiment-aware pre-trained language models (PLMs) demonstrate impressive results in downstream sentiment analysis tasks. However, they neglect to evaluate the quality of their constructed sentiment representations; they just…

Computation and Language · Computer Science 2024-04-02 Jaemin Kim , Yohan Na , Kangmin Kim , Sang Rak Lee , Dong-Kyu Chae

Shortcut learning undermines model generalization to out-of-distribution data. While the literature attributes shortcuts to biases in superficial features, we show that imbalances in the semantic distribution of sample embeddings induce…

Machine Learning · Computer Science 2025-06-24 Shuo Yang , Bardh Prenkaj , Gjergji Kasneci

Concept Bottleneck Models (CBMs) assume that training examples (e.g., x-ray images) are annotated with high-level concepts (e.g., types of abnormalities), and perform classification by first predicting the concepts, followed by predicting…

Computation and Language · Computer Science 2023-12-19 Danis Alukaev , Semen Kiselev , Ilya Pershin , Bulat Ibragimov , Vladimir Ivanov , Alexey Kornaev , Ivan Titov

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

Concept Bottleneck Models (CBMs) aim to enhance interpretability by predicting human-understandable concepts as intermediates for decision-making. However, these models often face challenges in ensuring reliable concept representations,…

Computer Vision and Pattern Recognition · Computer Science 2025-02-04 Yuxuan Cai , Xiyu Wang , Satoshi Tsutsui , Winnie Pang , Bihan Wen

Large language models(LLM) are pre-trained on extensive corpora to learn facts and human cognition which contain human preferences. However, this process can inadvertently lead to these models acquiring biases and stereotypes prevalent in…

Computation and Language · Computer Science 2024-03-22 Yuchen Cai , Ding Cao , Rongxi Guo , Yaqin Wen , Guiquan Liu , Enhong Chen

Large language models~(LLMs) exhibit exceptional performance in language tasks, yet their auto-regressive inference is limited due to high computational requirements and is sub-optimal due to the exposure bias. Inspired by speculative…

Computation and Language · Computer Science 2024-03-14 Hongyi Yuan , Keming Lu , Fei Huang , Zheng Yuan , Chang Zhou

Automatic content moderation is crucial to ensuring safety in social media. Language Model-based classifiers are being increasingly adopted for this task, but it has been shown that they perpetuate racial and social biases. Even if several…

Computation and Language · Computer Science 2026-03-12 Alessandra Urbinati , Mirko Lai , Simona Frenda , Marco Antonio Stranisci

Many studies have shown various biases targeting different demographic groups in language models, amplifying discrimination and harming fairness. Recent parameter modification debiasing approaches significantly degrade core capabilities…

Computation and Language · Computer Science 2025-10-01 Dianqing Liu , Yi Liu , Guoqing Jin , Zhendong Mao

Image captioning models are known to perpetuate and amplify harmful societal bias in the training set. In this work, we aim to mitigate such gender bias in image captioning models. While prior work has addressed this problem by forcing…

Computer Vision and Pattern Recognition · Computer Science 2023-12-22 Yusuke Hirota , Yuta Nakashima , Noa Garcia

Models that bridge vision and language, such as CLIP, are key components of multimodal AI, yet their large-scale, uncurated training data introduce severe social and spurious biases. Existing post-hoc debiasing methods often operate…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Quentin Guimard , Federico Bartsch , Simone Caldarella , Rahaf Aljundi , Elisa Ricci , Massimiliano Mancini

Entity bias widely affects pretrained (large) language models, causing them to rely on (biased) parametric knowledge to make unfaithful predictions. Although causality-inspired methods have shown great potential to mitigate entity bias, it…

Computation and Language · Computer Science 2023-10-30 Fei Wang , Wenjie Mo , Yiwei Wang , Wenxuan Zhou , Muhao Chen

Detecting and mitigating harmful biases in modern language models are widely recognized as crucial, open problems. In this paper, we take a step back and investigate how language models come to be biased in the first place. We use a…

Computation and Language · Computer Science 2022-07-22 Oskar van der Wal , Jaap Jumelet , Katrin Schulz , Willem Zuidema

With surge in online platforms, there has been an upsurge in the user engagement on these platforms via comments and reactions. A large portion of such textual comments are abusive, rude and offensive to the audience. With machine learning…

Computation and Language · Computer Science 2021-08-17 Ayush Kumar , Pratik Kumar

Speech models may be affected by performance imbalance in different population subgroups, raising concerns about fair treatment across these groups. Prior attempts to mitigate unfairness either focus on user-defined subgroups, potentially…

Computation and Language · Computer Science 2024-09-17 Alkis Koudounas , Flavio Giobergia , Eliana Pastor , Elena Baralis

Dataset bias has attracted increasing attention recently for its detrimental effect on the generalization ability of fine-tuned models. The current mainstream solution is designing an additional shallow model to pre-identify biased…

Computation and Language · Computer Science 2022-10-17 Songyang Gao , Shihan Dou , Qi Zhang , Xuanjing Huang

Advances in language modeling architectures and the availability of large text corpora have driven progress in automatic text generation. While this results in models capable of generating coherent texts, it also prompts models to…

Computation and Language · Computer Science 2020-10-09 Po-Sen Huang , Huan Zhang , Ray Jiang , Robert Stanforth , Johannes Welbl , Jack Rae , Vishal Maini , Dani Yogatama , Pushmeet Kohli

In this paper, we focus on the problem of unsupervised image-sentence matching. Existing research explores to utilize document-level structural information to sample positive and negative instances for model training. Although the approach…

Computer Vision and Pattern Recognition · Computer Science 2021-04-07 Zejun Li , Zhongyu Wei , Zhihao Fan , Haijun Shan , Xuanjing Huang

Vision-language model (VLM) embeddings have been shown to encode biases present in their training data, such as societal biases that prescribe negative characteristics to members of various racial and gender identities. VLMs are being…

Computer Vision and Pattern Recognition · Computer Science 2024-11-08 Walter Gerych , Haoran Zhang , Kimia Hamidieh , Eileen Pan , Maanas Sharma , Thomas Hartvigsen , Marzyeh Ghassemi