English
Related papers

Related papers: Bias Testing and Mitigation in Black Box LLMs usin…

200 papers

Large language models (LLMs) used in medical applications are known to be prone to exhibiting biased and unfair patterns. Prior to deploying these in clinical decision-making, it is crucial to identify such bias patterns to enable effective…

Artificial Intelligence · Computer Science 2025-12-23 Farzana Islam Adiba , Rahmatollah Beheshti

Large language models (LLMs) have demonstrated impressive capabilities in various tasks using the in-context learning (ICL) paradigm. However, their effectiveness is often compromised by inherent bias, leading to prompt brittleness, i.e.,…

Computation and Language · Computer Science 2024-12-13 Hanzhang Zhou , Zijian Feng , Zixiao Zhu , Junlang Qian , Kezhi Mao

The rapid deployment of artificial intelligence (AI) models demands a thorough investigation of biases and risks inherent in these models to understand their impact on individuals and society. This study extends the focus of bias evaluation…

Computers and Society · Computer Science 2023-06-12 Katelyn X. Mei , Sonia Fereidooni , Aylin Caliskan

Large Language Models (LLMs) have revolutionized natural language processing, yet concerns persist regarding their tendency to reflect or amplify social biases. This study introduces a novel evaluation framework to uncover gender biases in…

Computation and Language · Computer Science 2026-03-10 Evan Chen , Run-Jun Zhan , Yan-Bai Lin , Hung-Hsuan Chen

We explore the internal mechanisms of how bias emerges in large language models (LLMs) when provided with ambiguous comparative prompts: inputs that compare or enforce choosing between two or more entities without providing clear context…

Computation and Language · Computer Science 2024-10-31 Rishabh Adiga , Besmira Nushi , Varun Chandrasekaran

Text classification is a crucial task encountered frequently in practical scenarios, yet it is still under-explored in the era of large language models (LLMs). This study shows that LLMs are vulnerable to changes in the number and…

Computation and Language · Computer Science 2024-06-12 Zhenyi Lu , Jie Tian , Wei Wei , Xiaoye Qu , Yu Cheng , Wenfeng xie , Dangyang Chen

Software bias is an increasingly important operational concern for software engineers. We present a large-scale, comprehensive empirical study of 17 representative bias mitigation methods for Machine Learning (ML) classifiers, evaluated…

Software Engineering · Computer Science 2023-02-13 Zhenpeng Chen , Jie M. Zhang , Federica Sarro , Mark Harman

Large language models (LLMs) are known to inherit and even amplify societal biases present in their pre-training corpora, threatening fairness and social trust. To address this issue, recent work has explored ``editing'' LLM parameters to…

Computation and Language · Computer Science 2025-12-03 Daiki Shirafuji , Tatsuhiko Saito , Yasutomo Kimura

Large Language Models (LLM) have made significant advances in the recent past becoming more mainstream in Artificial Intelligence (AI) enabled human-facing applications. However, LLMs often generate stereotypical output inherited from…

Computation and Language · Computer Science 2023-11-27 Wu Zekun , Sahan Bulathwela , Adriano Soares Koshiyama

Augmented generation techniques such as Retrieval-Augmented Generation (RAG) and Cache-Augmented Generation (CAG) have revolutionized the field by enhancing large language model (LLM) outputs with external knowledge and cached information.…

Software Engineering · Computer Science 2024-02-23 Guanyu Wang , Yuekang Li , Yi Liu , Gelei Deng , Tianlin Li , Guosheng Xu , Yang Liu , Haoyu Wang , Kailong Wang

Biased AI-generated medical advice and misdiagnoses can jeopardize patient safety, making the integrity of AI in healthcare more critical than ever. As Large Language Models (LLMs) take on a growing role in medical decision-making,…

Computation and Language · Computer Science 2024-10-10 Pardis Sadat Zahraei , Zahra Shakeri

Large Reasoning Models (LRMs) like DeepSeek-R1 and OpenAI-o1 have demonstrated remarkable reasoning capabilities, raising important questions about their biases in LLM-as-a-judge settings. We present a comprehensive benchmark comparing…

Computers and Society · Computer Science 2025-04-21 Qian Wang , Zhanzhi Lou , Zhenheng Tang , Nuo Chen , Xuandong Zhao , Wenxuan Zhang , Dawn Song , Bingsheng He

Large language models (LLMs) have convincing performance in a variety of downstream tasks. However, these systems are prone to generating undesirable outputs such as harmful and biased text. In order to remedy such generations, the…

Computation and Language · Computer Science 2025-08-08 Manish Nagireddy , Inkit Padhi , Soumya Ghosh , Prasanna Sattigeri

Large Language Models (LLMs) are known to exhibit social, demographic, and gender biases, often as a consequence of the data on which they are trained. In this work, we adopt a mechanistic interpretability approach to analyze how such…

Computation and Language · Computer Science 2025-06-09 Bhavik Chandna , Zubair Bashir , Procheta Sen

Multiple Choice Question (MCQ) answering is a widely used method for evaluating the performance of Large Language Models (LLMs). However, LLMs often exhibit selection bias in MCQ tasks, where their choices are influenced by factors like…

Computation and Language · Computer Science 2025-12-01 Blessed Guda , Lawrence Francis , Gabrial Zencha Ashungafac , Carlee Joe-Wong , Moise Busogi

We present a novel approach to bias mitigation in large language models (LLMs) by applying steering vectors to modify model activations in forward passes. We compute 8 steering vectors, each corresponding to a different social bias axis,…

Machine Learning · Computer Science 2026-03-31 Zara Siddique , Irtaza Khalid , Liam D. Turner , Luis Espinosa-Anke

Increasing use of large language models (LLMs) demand performant guardrails to ensure the safety of inputs and outputs of LLMs. When these safeguards are trained on imbalanced data, they can learn the societal biases. We present a…

Computation and Language · Computer Science 2024-10-23 Olivia Sturman , Aparna Joshi , Bhaktipriya Radharapu , Piyush Kumar , Renee Shelby

Although large language models (LLMs) demonstrate impressive proficiency in various tasks, they present potential safety risks, such as `jailbreaks', where malicious inputs can coerce LLMs into generating harmful content bypassing safety…

Computation and Language · Computer Science 2025-11-26 Isack Lee , Haebin Seong

The inherent risk of generating harmful and unsafe content by Large Language Models (LLMs), has highlighted the need for their safety alignment. Various techniques like supervised fine-tuning, reinforcement learning from human feedback, and…

Cryptography and Security · Computer Science 2026-03-04 Kalyan Nakka , Nitesh Saxena

The pervasive spread of misinformation and disinformation in social media underscores the critical importance of detecting media bias. While robust Large Language Models (LLMs) have emerged as foundational tools for bias prediction,…

Computers and Society · Computer Science 2024-12-11 Luyang Lin , Lingzhi Wang , Jinsong Guo , Kam-Fai Wong