English
Related papers

Related papers: Dissecting Bias in LLMs: A Mechanistic Interpretab…

200 papers

While machine translation (MT) systems have seen significant improvements, it is still common for translations to reflect societal biases, such as gender bias. Decoder-only Large Language Models (LLMs) have demonstrated potential in MT,…

Computation and Language · Computer Science 2024-04-18 Eduardo Sánchez , Pierre Andrews , Pontus Stenetorp , Mikel Artetxe , Marta R. Costa-jussà

Warning: This paper contains examples of stereotypes and biases. Large Language Models (LLMs) exhibit considerable social biases, and various studies have tried to evaluate and mitigate these biases accurately. Previous studies use…

Computation and Language · Computer Science 2024-07-04 Rem Hida , Masahiro Kaneko , Naoaki Okazaki

Large Language Models (LLMs) have transformed text generation through inherently probabilistic context-aware mechanisms, mimicking human natural language. In this paper, we systematically investigate the performance of various LLMs when…

Computation and Language · Computer Science 2025-02-28 Javier Coronado-Blázquez

As large language models (LLMs) become an important way of information access, there have been increasing concerns that LLMs may intensify the spread of unethical content, including implicit bias that hurts certain populations without…

Computation and Language · Computer Science 2025-07-14 Yuchen Wen , Keping Bi , Wei Chen , Jiafeng Guo , Xueqi Cheng

Large language models (LLMs) show promise for supporting clinicians in diagnostic communication by generating explanations and guidance for patients. Yet their ability to produce outputs that are both understandable and empathetic remains…

Computation and Language · Computer Science 2025-11-04 Jianzhou Yao , Shunchang Liu , Guillaume Drui , Rikard Pettersson , Alessandro Blasimme , Sara Kijewski

Large Language Models (LLMs) have shown a high capability in answering questions on a diverse range of topics. However, these models sometimes produce biased, ideologized or incorrect responses, limiting their applications if there is no…

Artificial Intelligence · Computer Science 2026-04-08 Xiaotian Zhou , Di Tang , Xiaofeng Wang , Xiaozhong Liu

Large Language Models (LLMs) have emerged as dominant foundational models in modern NLP. However, the understanding of their prediction processes and internal mechanisms, such as feed-forward networks (FFN) and multi-head self-attention…

Computation and Language · Computer Science 2024-04-16 Xintong Wang , Xiaoyu Li , Xingshan Li , Chris Biemann

This paper investigates biases of Large Language Models (LLMs) through the lens of grammatical gender. Drawing inspiration from seminal works in psycholinguistics, particularly the study of gender's influence on language perception, we…

Computation and Language · Computer Science 2024-07-16 Viktor Mihaylov , Aleksandar Shtedritski

While large language models (LLMs) play increasingly significant roles in society, research shows they continue to generate content that reflects social bias against sensitive groups. Existing benchmarks effectively identify these biases,…

Computation and Language · Computer Science 2026-03-12 Tian Xie , Tongxin Yin , Vaishakh Keshava , Xueru Zhang , Siddhartha Reddy Jonnalagadda

Large language models (LLMs) have demonstrated impressive capabilities across a wide range of natural language processing tasks. However, their outputs often exhibit social biases, raising fairness concerns. Existing debiasing methods, such…

Computation and Language · Computer Science 2026-02-05 Yujie Lin , Kunquan Li , Yixuan Liao , Xiaoxin Chen , Jinsong Su

Mechanistic interpretability identifies internal circuits responsible for model behaviors, yet translating these findings into human-understandable explanations remains an open problem. We present a pipeline that bridges circuit-level…

Computation and Language · Computer Science 2026-03-12 Ajay Pravin Mahale

This position paper's primary goal is to provoke thoughtful discussion about the relationship between bias and fundamental properties of large language models. I do this by seeking to convince the reader that harmful biases are an…

Computation and Language · Computer Science 2025-03-17 Philip Resnik

Since the advent of Large Language Models (LLMs), a significant area of research has focused on their intrinsic biases, particularly in political discourse. This study investigates a different but related concept, "political plasticity",…

Artificial Intelligence · Computer Science 2026-05-12 Bruno Bianchi , Diego Tiscornia , Matias Travizano , Ariel Futoransky

This paper presents a systematic analysis of biases in open-source Large Language Models (LLMs), across gender, religion, and race. Our study evaluates bias in smaller-scale Llama and Gemma models using the SALT ($\textbf{S}$ocial…

Computation and Language · Computer Science 2025-02-19 Samee Arif , Zohaib Khan , Maaidah Kaleem , Suhaib Rashid , Agha Ali Raza , Awais Athar

Large language models (LLMs) offer significant potential as tools to support an expanding range of decision-making tasks. Given their training on human (created) data, LLMs have been shown to inherit societal biases against protected…

Artificial Intelligence · Computer Science 2024-10-07 Jessica Echterhoff , Yao Liu , Abeer Alessa , Julian McAuley , Zexue He

We have only limited understanding of how and why large language models (LLMs) respond in the ways that they do. Their neural networks have proven challenging to interpret, and we are only beginning to tease out the function of individual…

Computation and Language · Computer Science 2025-11-12 Dillon Plunkett , Adam Morris , Keerthi Reddy , Jorge Morales

Pre-trained large language models (LLMs) have been reliably integrated with visual input for multimodal tasks. The widespread adoption of instruction-tuned image-to-text vision-language assistants (VLAs) like LLaVA and InternVL necessitates…

Computers and Society · Computer Science 2025-03-14 Leander Girrbach , Stephan Alaniz , Yiran Huang , Trevor Darrell , Zeynep Akata

The Large Language Model Bias Index (LLMBI) is a pioneering approach designed to quantify and address biases inherent in large language models (LLMs), such as GPT-4. We recognise the increasing prevalence and impact of LLMs across diverse…

Computation and Language · Computer Science 2024-01-01 Abiodun Finbarrs Oketunji , Muhammad Anas , Deepthi Saina

Are large language models (LLMs) sensitive to the distinction between humanly possible and impossible languages? This question was recently used in a broader debate on whether LLMs and humans share the same innate learning biases. Previous…

Computation and Language · Computer Science 2026-04-01 Imry Ziv , Nur Lan , Emmanuel Chemla

Large language models (LLMs) are increasingly deployed in high-stakes hiring applications, making decisions that directly impact people's careers and livelihoods. While prior studies suggest simple anti-bias prompts can eliminate…

Machine Learning · Computer Science 2025-06-13 Adam Karvonen , Samuel Marks