paper-with-me

홈 › Papers

Anti-stereotypical Predictive Text Suggestions Do Not Reliably Yield Anti-stereotypical Writing

2024-09-30 · Connor Baumler, Hal Daumé III

AI-based systems such as language models can replicate and amplify social biases reflected in their training data. Among other questionable behavior, this can lead to LM-generated text--and text suggestions--that contain normatively inappropriate stereotypical associations. In this paper, we consider the question of how "debiasing" a language model impacts stories that people write using that language model in a predictive text scenario. We find that (n=414), in certain scenarios, language model suggestions that align with common social stereotypes are more likely to be accepted by human authors. Conversely, although anti-stereotypical language model suggestions sometimes lead to an increased rate of anti-stereotypical stories, this influence is far from sufficient to lead to "fully debiased" stories.

📄 PDF Abstract BibTeX arXiv:2409.20390

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Do Bias Benchmarks Generalise? Evidence from Voice-based Evaluation of Gender Bias in SpeechLLMs

2025-09-24 · Shree Harsha Bokkahalli Satish, Gustav Eje Henter, Éva Székely arxiv

Recent work in benchmarking bias and fairness in speech large language models (SpeechLLMs) has relied heavily on multiple-choice question answering (MCQA) formats. The model is tasked to choose between stereotypical, ant…

Question Answering

Is She Even Relevant? When BERT Ignores Explicit Gender Cues

2026-05-08 · Jonas Klein, Chiara Manna, Eva Vanmassenhove arxiv

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 in…

Indian-BhED: A Dataset for Measuring India-Centric Biases in Large Language Models

2023-09-15 · Khyati Khandelwal, Manuel Tonneau, Andrew M. Bean, Hannah Rose Kirk 외

Large Language Models (LLMs), now used daily by millions, can encode societal biases, exposing their users to representational harms. A large body of scholarship on LLM bias exists but it predominantly adopts a Western-c…

FairnessLanguage ModellingLarge Language Model

Engagement Undermines Safety: How Stereotypes and Toxicity Shape Humor in Language Models

2025-10-21 · Atharvan Dogra, Soumya Suvra Ghosal, Ameet Deshpande, Ashwin Kalyan 외 arxiv

Large language models are increasingly used for creative writing and engagement content, raising safety concerns about the outputs. Therefore, casting humor generation as a testbed, this work evaluates how funniness opti…

T2IAT: Measuring Valence and Stereotypical Biases in Text-to-Image Generation

2023-06-01 · Jialu Wang, Xinyue Gabby Liu, Zonglin Di, Yang Liu 외

Warning: This paper contains several contents that may be toxic, harmful, or offensive. In the last few years, text-to-image generative models have gained remarkable success in generating images with unprecedented qualit…

Image GenerationText to Image GenerationText-to-Image Generation