English
Related papers

Related papers: The Binding Effect: Analyzing How Multi-Dimensiona…

200 papers

A dangerous assumption that can be made from prior work on the bias transfer hypothesis (BTH) is that biases do not transfer from pre-trained large language models (LLMs) to adapted models. We invalidate this assumption by studying the BTH…

Computation and Language · Computer Science 2025-11-20 Nivedha Sivakumar , Natalie Mackraz , Samira Khorshidi , Krishna Patel , Barry-John Theobald , Luca Zappella , Nicholas Apostoloff

Large Language Models (LLMs) can generate biased and toxic responses. Yet most prior work on LLM gender bias evaluation requires predefined gender-related phrases or gender stereotypes, which are challenging to be comprehensively collected…

Computation and Language · Computer Science 2023-11-02 Xiangjue Dong , Yibo Wang , Philip S. Yu , James Caverlee

Text-to-Image (T2I) generative models have revolutionized content creation, yet they inherently risk amplifying societal biases. While sociological research provides systematic classifications of bias, existing T2I benchmarks largely…

Computers and Society · Computer Science 2026-04-15 Hanjun Luo , Zhimu Huang , Haoyu Huang , Ziye Deng , Ruizhe Chen , Xinfeng Li , Zuozhu Liu , Hanan Salam

Using observed language to understand interpersonal interactions is important in high-stakes decision making. We propose a causal research design for observational (non-experimental) data to estimate the natural direct and indirect effects…

Computation and Language · Computer Science 2021-09-17 Katherine A. Keith , Douglas Rice , Brendan O'Connor

Note: This paper includes examples of potentially offensive content related to religious bias, presented solely for academic purposes. The widespread adoption of language models highlights the need for critical examinations of their…

Computation and Language · Computer Science 2025-11-06 Ajwad Abrar , Nafisa Tabassum Oeshy , Mohsinul Kabir , Sophia Ananiadou

Despite their prevalence in society, social biases are difficult to identify, primarily because human judgements in this domain can be unreliable. We take an unsupervised approach to identifying gender bias against women at a comment level…

Computation and Language · Computer Science 2020-10-07 Anjalie Field , Yulia Tsvetkov

As LLMs are increasingly integrated into user-facing applications, addressing biases that perpetuate societal inequalities is crucial. While much work has gone into measuring or mitigating biases in these models, fewer studies have…

Computation and Language · Computer Science 2026-05-13 Marion Thaler , Abdullatif Köksal , Alina Leidinger , Anna Korhonen , Hinrich Schütze

While vision-language models (VLMs) have achieved remarkable performance improvements recently, there is growing evidence that these models also posses harmful biases with respect to social attributes such as gender and race. Prior studies…

Computer Vision and Pattern Recognition · Computer Science 2023-10-05 Phillip Howard , Avinash Madasu , Tiep Le , Gustavo Lujan Moreno , Vasudev Lal

With the growing adoption of Text-to-Image (TTI) systems, the social biases of these models have come under increased scrutiny. Herein we conduct a systematic investigation of one such source of bias for diffusion models: embedding spaces.…

Machine Learning · Computer Science 2024-09-17 Sahil Kuchlous , Marvin Li , Jeffrey G. Wang

Language models are trained mostly on Web data, which often contains social stereotypes and biases that the models can inherit. This has potentially negative consequences, as models can amplify these biases in downstream tasks or…

Computation and Language · Computer Science 2025-10-02 Orhun Mersin Caglidil , Malte Ostendorff , Georg Rehm

LLMs are increasingly embedded in programming workflows, from code generation to automated code review. Yet, how gendered communication styles interact with LLM-assisted programming and code review remains underexplored. We present a…

Software Engineering · Computer Science 2026-03-26 Lynn Janzen , Üveys Eroglu , Dorothea Kolossa , Pia Knöferle , Sebastian Möller , Vera Schmitt , Veronika Solopova

Large Language Models (LLMs) inherit explicit and implicit biases from their training datasets. Identifying and mitigating biases in LLMs is crucial to ensure fair outputs, as they can perpetuate harmful stereotypes and misinformation. This…

Machine Learning · Computer Science 2025-11-19 Fatima Kazi , Alex Young , Yash Inani , Setareh Rafatirad

Machine learning models that convert user-written text descriptions into images are now widely available online and used by millions of users to generate millions of images a day. We investigate the potential for these models to amplify…

Bias amplification is a phenomenon in which models exacerbate biases or stereotypes present in the training data. In this paper, we study bias amplification in the text-to-image domain using Stable Diffusion by comparing gender ratios in…

Machine Learning · Computer Science 2023-11-16 Preethi Seshadri , Sameer Singh , Yanai Elazar

Objectives: Compare qualitative coding of instruction tuned large language models (IT-LLMs) against human coders in classifying the presence or absence of vulnerability in routinely collected unstructured text that describes police-public…

Computation and Language · Computer Science 2024-12-17 Sam Relins , Daniel Birks , Charlie Lloyd

With the advent of Large Language Models (LLMs) possessing increasingly impressive capabilities, a number of Large Vision-Language Models (LVLMs) have been proposed to augment LLMs with visual inputs. Such models condition generated text on…

Computer Vision and Pattern Recognition · Computer Science 2024-06-11 Phillip Howard , Anahita Bhiwandiwalla , Kathleen C. Fraser , Svetlana Kiritchenko

AI-based systems such as language models have been shown to replicate and even amplify social biases reflected in their training data. Among other questionable behaviors, this can lead to AI-generated text--and text suggestions--that…

Computation and Language · Computer Science 2026-02-19 Connor Baumler , Hal Daumé

Multilingual representations embed words from many languages into a single semantic space such that words with similar meanings are close to each other regardless of the language. These embeddings have been widely used in various settings,…

Computation and Language · Computer Science 2020-05-05 Jieyu Zhao , Subhabrata Mukherjee , Saghar Hosseini , Kai-Wei Chang , Ahmed Hassan Awadallah

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

Gender bias in large language models has primarily been investigated for English, while languages with grammatical or morphological gender remain comparatively understudied. This paper investigates how and when gender information emerges in…

Computation and Language · Computer Science 2026-05-11 Jonas Klein , Chiara Manna , Eva Vanmassenhove