English
Related papers

Related papers: Auditing Stance Asymmetry in Generative Explanatio…

200 papers

While reasoning-based large language models excel at complex tasks through an internal, structured thinking process, a concerning phenomenon has emerged that such a thinking process can aggregate social stereotypes, leading to biased…

Computation and Language · Computer Science 2026-05-13 Guoqing Luo , Iffat Maab , Lili Mou , Junichi Yamagishi

Existing word embedding debiasing methods require social-group-specific word pairs (e.g., "man"-"woman") for each social attribute (e.g., gender), which cannot be used to mitigate bias for other social groups, making these methods…

Computation and Language · Computer Science 2022-10-13 Ali Omrani , Brendan Kennedy , Mohammad Atari , Morteza Dehghani

We typically compute aggregate statistics on held-out test data to assess the generalization of machine learning models. However, statistics on test data often overstate model generalization, and thus, the performance of deployed machine…

Machine Learning · Computer Science 2021-02-12 Dylan Slack , Nathalie Rauschmayr , Krishnaram Kenthapadi

This position paper argues for the use of \emph{structured generative models} (SGMs) for the understanding of static scenes. This requires the reconstruction of a 3D scene from an input image (or a set of multi-view images), whereby the…

Computer Vision and Pattern Recognition · Computer Science 2024-12-16 Christopher K. I. Williams

Contextualized word embeddings have been replacing standard embeddings as the representational knowledge source of choice in NLP systems. Since a variety of biases have previously been found in standard word embeddings, it is crucial to…

Computation and Language · Computer Science 2020-10-29 Marion Bartl , Malvina Nissim , Albert Gatt

Detecting biases in the outputs produced by generative models is essential to reduce the potential risks associated with their application in critical settings. However, the majority of existing methodologies for identifying biases in…

Computation and Language · Computer Science 2025-02-04 Erica Coppolillo , Giuseppe Manco , Luca Maria Aiello

Evaluation of generative models has been an underrepresented field despite the surge of generative architectures. Most recent models are evaluated upon rather obsolete metrics which suffer from robustness issues, while being unable to…

Computer Vision and Pattern Recognition · Computer Science 2024-05-06 Maria Lymperaiou , Giorgos Filandrianos , Konstantinos Thomas , Giorgos Stamou

During training, Large Language Models (LLMs) learn social regularities that can lead to gender bias in downstream applications. Most mitigation efforts focus on reducing bias in generated outputs, typically evaluated on structured…

Computation and Language · Computer Science 2026-05-14 Nour Bouchouchi , Thibault Laugel , Xavier Renard , Christophe Marsala , Marie-Jeanne Lesot , Marcin Detyniecki

This study investigates the dynamics of Score-based Generative Models (SGMs) by treating the score estimation error as a stochastic source driving the Fokker-Planck equation. Departing from particle-centric SDE analyses, we employ an SPDE…

Machine Learning · Computer Science 2026-02-10 Junsu Seo

Large language models (LLMs) often exhibit societal biases in their outputs, prompting ethical concerns regarding fairness and harm. In this work, we propose KLAAD (KL-Attention Alignment Debiasing), an attention-based debiasing framework…

Computation and Language · Computer Science 2025-07-29 Seorin Kim , Dongyoung Lee , Jaejin Lee

Unified multimodal models (UMMs) aim to integrate multimodal understanding and generation within a unified architecture, yet it remains unclear to what extent their representations are truly aligned across modalities. To investigate this…

Computation and Language · Computer Science 2026-04-08 Cheng Yang , Chufan Shi , Bo Shui , Yaokang Wu , Muzi Tao , Huijuan Wang , Ivan Yee Lee , Yong Liu , Xuezhe Ma , Taylor Berg-Kirkpatrick

Stance detection has emerged as a popular task in natural language processing research, enabled largely by the abundance of target-specific social media data. While there has been considerable research on the development of stance detection…

Computation and Language · Computer Science 2025-02-05 Prasanta Bhattacharya , Hong Zhang , Yiming Cao , Wei Gao , Brandon Siyuan Loh , Joseph J. P. Simons , Liang Ze Wong

Responsible deployment of language models requires mechanisms for refusing unsafe prompts while preserving model performance. While most approaches modify model weights through additional training, we explore an alternative: steering model…

Large Language Models (LLMs) can generate biased responses. Yet previous direct probing techniques contain either gender mentions or predefined gender stereotypes, which are challenging to comprehensively collect. Hence, we propose an…

Computation and Language · Computer Science 2024-02-20 Xiangjue Dong , Yibo Wang , Philip S. Yu , James Caverlee

It has been shown that many generative models inherit and amplify societal biases. To date, there is no uniform/systematic agreed standard to control/adjust for these biases. This study examines the presence and manipulation of societal…

Computer Vision and Pattern Recognition · Computer Science 2024-06-11 Philip Wootaek Shin , Jihyun Janice Ahn , Wenpeng Yin , Jack Sampson , Vijaykrishnan Narayanan

This paper proposes a structure-aware decoding method based on large language models to address the difficulty of traditional approaches in maintaining both semantic integrity and structural consistency in nested and overlapping entity…

Computation and Language · Computer Science 2026-01-29 Zhimin Qiu , Di Wu , Feng Liu , Yuxiao Wang

It is well-known that real-world changes constituting distribution shift adversely affect model performance. How to characterize those changes in an interpretable manner is poorly understood. Existing techniques to address this problem take…

Machine Learning · Computer Science 2023-05-26 Adam Stein , Yinjun Wu , Eric Wong , Mayur Naik

Sentiment analysis (SA) systems are used in many products and hundreds of languages. Gender and racial biases are well-studied in English SA systems, but understudied in other languages, with few resources for such studies. To remedy this,…

Computation and Language · Computer Science 2023-05-22 Seraphina Goldfarb-Tarrant , Adam Lopez , Roi Blanco , Diego Marcheggiani

While advances in fairness and alignment have helped mitigate overt biases exhibited by large language models (LLMs) when explicitly prompted, we hypothesize that these models may still exhibit implicit biases when simulating human…

Computation and Language · Computer Science 2025-01-30 Yuxuan Li , Hirokazu Shirado , Sauvik Das

Large Language Models (LLMs) can achieve inflated scores on multiple-choice tasks by exploiting inherent biases in option positions or labels, rather than demonstrating genuine understanding. This study introduces SCOPE, an evaluation…

Computation and Language · Computer Science 2025-08-05 Wonjun Jeong , Dongseok Kim , Taegkeun Whangbo