English
Related papers

Related papers: Towards Universal Debiasing for Language Models-ba…

200 papers

Diffusion Models (DMs) have emerged as powerful generative models with unprecedented image generation capability. These models are widely used for data augmentation and creative applications. However, DMs reflect the biases present in the…

Computer Vision and Pattern Recognition · Computer Science 2025-04-11 Rishubh Parihar , Abhijnya Bhat , Abhipsa Basu , Saswat Mallick , Jogendra Nath Kundu , R. Venkatesh Babu

The specification of prior distributions is fundamental in Bayesian inference, yet it remains a significant bottleneck. The prior elicitation process is often a manual, subjective, and unscalable task. We propose a novel framework which…

Machine Learning · Computer Science 2025-08-07 Yongchao Huang

Large Language Models (LLMs) often exhibit gender bias, resulting in unequal treatment of male and female subjects across different contexts. To address this issue, we propose a novel data generation framework that fosters exploratory…

Computation and Language · Computer Science 2026-01-15 Kangda Wei , Hasnat Md Abdullah , Ruihong Huang

Modern alignment pipelines are increasingly replacing expensive human preference labels with evaluations from large language models (LLM-as-Judge). However, AI labels can be systematically biased compared to high-quality human feedback…

Machine Learning · Statistics 2026-02-10 Xintao Xia , Zhiqiu Xia , Linjun Zhang , Zhanrui Cai

Data processing is one of the fundamental steps in machine learning pipelines to ensure data quality. Majority of the applications consider the user-defined function (UDF) design pattern for data processing in databases. Although the UDF…

Databases · Computer Science 2023-12-29 Luyi Ma , Nikhil Thakurdesai , Jiao Chen , Jianpeng Xu , Evren Korpeoglu , Sushant Kumar , Kannan Achan

Large language models (LLMs), despite their remarkable capabilities, are susceptible to generating biased and discriminatory responses. As LLMs increasingly influence high-stakes decision-making (e.g., hiring and healthcare), mitigating…

Computation and Language · Computer Science 2025-03-04 Jingling Li , Zeyu Tang , Xiaoyu Liu , Peter Spirtes , Kun Zhang , Liu Leqi , Yang Liu

Pre-trained language models (PLMs) are trained on data that inherently contains gender biases, leading to undesirable impacts. Traditional debiasing methods often rely on external corpora, which may lack quality, diversity, or demographic…

Computation and Language · Computer Science 2025-03-13 Liu Yu , Ludie Guo , Ping Kuang , Fan Zhou

As Large Language Models (LLMs) have risen in prominence over the past few years, there has been concern over the potential biases in LLMs inherited from the training data. Previous studies have examined how LLMs exhibit implicit bias, such…

Computation and Language · Computer Science 2025-12-30 Lake Yin , Fan Huang

Pairwise debiasing is one of the most effective strategies in reducing position bias in learning-to-rank (LTR) models. However, limiting the scope of this strategy, are the underlying assumptions required by many pairwise debiasing…

Information Retrieval · Computer Science 2022-07-19 Alexey Kurennoy , John Coleman , Ian Harris , Alice Lynch , Oisin Mac Fhearai , Daphne Tsatsoulis

Fine-tuning pre-trained Large Language Models (LLMs) is essential to align them with human values and intentions. This process often utilizes methods like pairwise comparisons and KL divergence against a reference LLM, focusing on the…

Computation and Language · Computer Science 2024-09-02 Yongcheng Zeng , Guoqing Liu , Weiyu Ma , Ning Yang , Haifeng Zhang , Jun Wang

Synthesizing high-quality tabular data is an important topic in many data science tasks, ranging from dataset augmentation to privacy protection. However, developing expressive generative models for tabular data is challenging due to its…

Machine Learning · Computer Science 2025-02-18 Juntong Shi , Minkai Xu , Harper Hua , Hengrui Zhang , Stefano Ermon , Jure Leskovec

Social biases embedded in Large Language Models (LLMs) raise critical concerns, resulting in representational harms -- unfair or distorted portrayals of demographic groups -- that may be expressed in subtle ways through generated language.…

Computation and Language · Computer Science 2026-01-21 Jinhao Pan , Chahat Raj , Ziwei Zhu

AI fairness seeks to improve the transparency and explainability of AI systems by ensuring that their outcomes genuinely reflect the best interests of users. Data augmentation, which involves generating synthetic data from existing…

Machine Learning · Computer Science 2024-10-22 Christina Hastings Blow , Lijun Qian , Camille Gibson , Pamela Obiomon , Xishuang Dong

Biases and errors in human-labeled data present significant challenges for machine learning, especially in supervised learning reliant on potentially flawed ground truth data. These flaws, including diagnostic errors and societal biases,…

Artificial Intelligence · Computer Science 2024-10-25 Edward Y. Chang

The increasing capabilities of large language models (LLMs) raise opportunities for artificial general intelligence but concurrently amplify safety concerns, such as potential misuse of AI systems, necessitating effective AI alignment.…

Machine Learning · Computer Science 2023-09-29 Chaoqi Wang , Yibo Jiang , Chenghao Yang , Han Liu , Yuxin Chen

Large language models (LLMs) have shown promise in synthetic tabular data generation, yet existing methods struggle to preserve complex feature dependencies, particularly among categorical variables. This work introduces a…

Machine Learning · Computer Science 2025-05-07 Andrey Sidorenko

Preferences within a group of people are not uniform but follow a distribution. While existing alignment methods like Direct Preference Optimization (DPO) attempt to steer models to reflect human preferences, they struggle to capture the…

Computation and Language · Computer Science 2025-05-14 Binwei Yao , Zefan Cai , Yun-Shiuan Chuang , Shanglin Yang , Ming Jiang , Diyi Yang , Junjie Hu

Large Language Models (LLMs) often exhibit implicit biases and discriminatory tendencies that reflect underlying social stereotypes. While recent alignment techniques such as RLHF and DPO have mitigated some of these issues, they remain…

Computation and Language · Computer Science 2025-11-11 Deng Yixuan , Ji Xiaoqiang

Large language models are becoming the go-to solution for the ever-growing number of tasks. However, with growing capacity, models are prone to rely on spurious correlations stemming from biases and stereotypes present in the training data.…

Computation and Language · Computer Science 2024-05-30 Tomasz Limisiewicz , David Mareček , Tomáš Musil

Diffusion language models (DLMs) enable parallel, order-agnostic generation with iterative refinement, offering a flexible alternative to autoregressive large language models (LLMs). However, adapting reinforcement learning (RL) fine-tuning…

Machine Learning · Computer Science 2026-02-12 Kevin Rojas , Jiahe Lin , Kashif Rasul , Anderson Schneider , Yuriy Nevmyvaka , Molei Tao , Wei Deng