''Fifty Shades of Bias'': Normative Ratings of Gender Bias in GPT Generated English Text

Ranked by how close their title and abstract are to this paper’s. Select some to read them together.

Closest papers

1. Very close Cites this paper Not relevant

   A Gender-Diverse Perspective of Bias in Large Language Models

   Aimen Gaba, Emily Wall, Os Keyes et al. · 2026 · Conference on Fairness, Accountability and Transparency · Not summarized yet

   Abstract

   Concerns about bias in large language models (LLMs) often focus on technical metrics, yet limited research examines how marginalized communities perceive and interpret model behavior. Through 25 interviews with participants across gender identities (non-binary, men, and women), we investigate how ChatGPT responds to gendered versus neutral prompts and how users evaluate bias in these responses. Our findings reveal striking differences: non-binary participants identified condescension, stereotyping, and identity erasure in outputs that cisgender participants often found acceptable, demonstrating that bias perception is not universal, but rather shaped by lived experience and social positionin…

2. Very close Cites this paper Not relevant

   “This Model Needs to Chill”: an Experimental Scoring Scale for Participatory Perceptions of Gender Bias and Harm in Large Language Model-Generated Text

   Lara Dal Molin · 2026 · Conference on Fairness, Accountability and Transparency · Not summarized yet

   Abstract

   This contribution explores how 50 participants perceive gender bias in 180 Large Language Model (LLM)-completed text generation tasks through an experimental scoring scale. Drawing on critical literature in Natural Language Processing, Human-Computer Interaction, Science and Technology Studies, and Psychology, this contribution operationalises harmful gender bias in LLM-generated text as gender biased text that causes psychological discomfort as a result of marginalisation, exclusion or stereotyping. Findings illustrate that, while participants apply the scoring system consistently across tasks according to personal perceptions, they disagree on how gender bias manifests in LLM-generated tex…

3. Very close Not relevant

   Quantifying Bias in Text Genrative AI models

   Sai Asrith Devisetti, Radhika Mamidi · 2025 · INTERNATIONAL JOURNAL OF MATHEMATICS AND COMPUTER RESEARCH · Not summarized yet

   Abstract

   Generative artificial intelligence (AI), especially large language models (LLMs), is increasingly deployed in domains such as recruitment, content creation, and education. While these systems accelerate productivity, they also risk reproducing and amplifying societal biases (Ahuchogu et al., 2025). This project addresses the urgent challenge of identifying, quantifying, and mitigating gender bias in text-generative AI outputs, with a focus on job narratives. Building on my independent study of 11,000+ AI-generated job narratives, which we generated using Gemini AI, we introduce a bias quantification framework using mean bias, mean absolute bias, sentiment skew (via TextBlob), and distributio…

4. Very close Not relevant

   Quantifying and Mitigating Bias in GPT-Based Language Models

   Joy Vashisht, Manisha Vashisht · 2025 · 2025 International Conference on Next Generation of Green Information and Emerging Technologies (GIET) · Not summarized yet

   Abstract

   Large Language Models (LLMs) such as OpenAI's GPT -4 have demonstrated remarkable capabilities in generating human-like text across diverse contexts. However, their widespread adoption has raised critical concerns around inherent biases present in the generated content, especially those related to gender, race, and profession. This paper investigates the presence and nature of bias in responses generated by GPT-4 through controlled prompt testing. We introduce a prompt pair generation methodology that varies only on identity-specific variables and assess the outputs of the model on semantic similarity, polarity of sentiment, and embedding-level discrepancy measures. We carry out experiments …

5. Very close Not relevant

   Unveiling Gender Bias in Terms of Profession Across LLMs: Analyzing and Addressing Sociological Implications

   Vishesh Thakur · 2023 · Computation and Language · preprint, not peer reviewed · cited 50 times · AI summary available

   Abstract

   Gender bias in artificial intelligence (AI) and natural language processing has garnered significant attention due to its potential impact on societal perceptions and biases. This research paper aims to analyze gender bias in Large Language Models (LLMs) with a focus on multiple comparisons between GPT-2 and GPT-3.5, some prominent language models, to better understand its implications. Through a comprehensive literature review, the study examines existing research on gender bias in AI language models and identifies gaps in the current knowledge. The methodology involves collecting and preprocessing data from GPT-2 and GPT-3.5, and employing in-depth quantitative analysis techniques to evalu…

6. Very close Not relevant

   A database to support the evaluation of gender biases in GPT-4o output

   Luise Mehner, L. Fiedler, Sabine Ammon et al. · 2025 · arXiv.org · preprint, not peer reviewed · Not summarized yet

   Abstract

   The widespread application of Large Language Models (LLMs) involves ethical risks for users and societies. A prominent ethical risk of LLMs is the generation of unfair language output that reinforces or exacerbates harm for members of disadvantaged social groups through gender biases (Weidinger et al., 2022; Bender et al., 2021; Kotek et al., 2023). Hence, the evaluation of the fairness of LLM outputs with respect to such biases is a topic of rising interest. To advance research in this field, promote discourse on suitable normative bases and evaluation methodologies, and enhance the reproducibility of related studies, we propose a novel approach to database construction. This approach enabl…

7. Very close Not relevant

   Data Bias According to Bipol: Men are Naturally Right and It is the Role of Women to Follow Their Lead

   Irene Pagliai, Goya van Boven, Tosin Adewumi et al. · 2024 · Computation and Language · cited 2 times · AI summary available

   Abstract

   We introduce new large labeled datasets on bias in 3 languages and show in experiments that bias exists in all 10 datasets of 5 languages evaluated, including benchmark datasets on the English GLUE/SuperGLUE leaderboards. The 3 new languages give a total of almost 6 million labeled samples and we benchmark on these datasets using SotA multilingual pretrained models: mT5 and mBERT. The challenge of social bias, based on prejudice, is ubiquitous, as recent events with AI and large language models (LLMs) have shown. Motivated by this challenge, we set out to estimate bias in multiple datasets. We compare some recent bias metrics and use bipol, which has explainability in the metric. We also con…

8. Very close Not relevant

   Gender Bias in Text: Labeled Datasets and Lexicons

   Jad Doughman, Wael Khreich · 2022 · arXiv.org · preprint, not peer reviewed · cited 11 times · Not summarized yet

   Abstract

   Language has a profound impact on our thoughts, perceptions, and conceptions of gender roles. Gender-inclusive language is, therefore, a key tool to promote social inclusion and contribute to achieving gender equality. Consequently, detecting and mitigating gender bias in texts is instrumental in halting its propagation and societal implications. However, there is a lack of gender bias datasets and lexicons for automating the detection of gender bias using supervised and unsupervised machine learning (ML) and natural language processing (NLP) techniques. Therefore, the main contribution of this work is to publicly provide labeled datasets and exhaustive lexicons by collecting, annotating, an…

Prior work it builds on

1. Close A method it uses Not relevant

   Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translation

   Shahar Levy, Koren Lazar, Gabriel Stanovsky · 2021 · Conference on Empirical Methods in Natural Language Processing · cited 96 times · Not summarized yet

   Abstract

   Recent works have found evidence of gender bias in models of machine translation and coreference resolution using mostly synthetic diagnostic datasets. While these quantify bias in a controlled experiment, they often do so on a small scale and consist mostly of artificial, out-of-distribution sentences. In this work, we find grammatical patterns indicating stereotypical and non-stereotypical gender-role assignments (e.g., female nurses versus male dancers) in corpora from three domains, resulting in a first large-scale gender bias dataset of 108K diverse real-world English sentences. We manually verify the quality of our corpus and use it to evaluate gender bias in various coreference resolu…

2. Close Not relevant

   Assessing gender bias in machine translation: a case study with Google Translate

   Marcelo O. R. Prates, Pedro H. C. Avelar, L. Lamb · 2018 · Neural computing & applications (Print) · cited 430 times · Not summarized yet

   Abstract

   Recently there has been a growing concern in academia, industrial research laboratories and the mainstream commercial media about the phenomenon dubbed as machine bias, where trained statistical models—unbeknownst to their creators—grow to reflect controversial societal asymmetries, such as gender or racial bias. A significant number of Artificial Intelligence tools have recently been suggested to be harmfully biased toward some minority, with reports of racist criminal behavior predictors, Apple’s Iphone X failing to differentiate between two distinct Asian people and the now infamous case of Google photos’ mistakenly classifying black people as gorillas. Although a systematic study of such…

3. Close Not relevant

   A Survey on Gender Bias in Natural Language Processing

   Karolina Stańczak, Isabelle Augenstein · 2021 · arXiv.org · preprint, not peer reviewed · cited 177 times · Not summarized yet

   Abstract

   Language can be used as a means of reproducing and enforcing harmful stereotypes and biases and has been analysed as such in numerous research. In this paper, we present a survey of 304 papers on gender bias in natural language processing. We analyse definitions of gender and its categories within social sciences and connect them to formal definitions of gender bias in NLP research. We survey lexica and datasets applied in research on gender bias and then compare and contrast approaches to detecting and mitigating gender bias. We find that research on gender bias suffers from four core limitations. 1) Most research treats gender as a binary variable neglecting its fluidity and continuity. 2)…

4. Close Not relevant

   On Measuring Gender Bias in Translation of Gender-neutral Pronouns

   Won Ik Cho, Jiwon Kim, Seokhwan Kim et al. · 2019 · Proceedings of the First Workshop on Gender Bias in Natural Language Processing · cited 103 times · Not summarized yet

   Abstract

   Ethics regarding social bias has recently thrown striking issues in natural language processing. Especially for gender-related topics, the need for a system that reduces the model bias has grown in areas such as image captioning, content recommendation, and automated employment. However, detection and evaluation of gender bias in the machine translation systems are not yet thoroughly investigated, for the task being cross-lingual and challenging to define. In this paper, we propose a scheme for making up a test set that evaluates the gender bias in a machine translation system, with Korean, a language with gender-neutral pronouns. Three word/phrase sets are primarily constructed, each incorp…

5. Close Not relevant

   Language (Technology) is Power: A Critical Survey of “Bias” in NLP

   Su Lin Blodgett, S. Barocas, Hal Daum'e et al. · 2020 · Annual Meeting of the Association for Computational Linguistics · cited 1,968 times · Not summarized yet

   Abstract

   We survey 146 papers analyzing “bias” in NLP systems, finding that their motivations are often vague, inconsistent, and lacking in normative reasoning, despite the fact that analyzing “bias” is an inherently normative process. We further find that these papers’ proposed quantitative techniques for measuring or mitigating “bias” are poorly matched to their motivations and do not engage with the relevant literature outside of NLP. Based on these findings, we describe the beginnings of a path forward by proposing three recommendations that should guide work analyzing “bias” in NLP systems. These recommendations rest on a greater recognition of the relationships between language and social hiera…

Papers that cite it

1. Close Not relevant

   Algorithmic bias: sexualized violence against women in GPT-3 models

   S. Wyer, Sue Black · 2025 · AI and Ethics · cited 12 times · Not summarized yet

   Abstract

   This study explores the occurrence and implications of sexualized violence against women in text completion tasks performed by GPT-3 models. The study began as an exploratory investigation into gender inequalities within GPT-3 models to discover what GPT3 models generate in text completion tasks when prompted with basic gendered prompts. For example, "Men can…", "Women can…". Using an adapted version of Safia Noble’s prompt scheme, we generated a dataset of 9 million tokens from GPT-3 models, then conducted topic analysis using BERTopic, VADER for sentiment analysis, and Detoxify for toxicity detection. The results were unexpected. Topic analysis revealed sexualized violence ranked as the to…

2. Close Not relevant

   Blind Men and the Elephant: Diverse Perspectives on Gender Stereotypes in Benchmark Datasets

   Mahdi Zakizadeh, Mohammad Taher Pilehvar · 2025 · Conference on Empirical Methods in Natural Language Processing · cited 4 times · Not summarized yet

   Abstract

   Accurately measuring gender stereotypical bias in language models is a complex task with many hidden aspects. Current benchmarks have underestimated this multifaceted challenge and failed to capture the full extent of the problem. This paper examines the inconsistencies between intrinsic stereotype benchmarks. We propose that currently available benchmarks each capture only partial facets of gender stereotypes, and when considered in isolation, they provide just a fragmented view of the broader landscape of bias in language models. Using StereoSet and CrowS-Pairs as case studies, we investigated how data distribution affects benchmark results. By applying a framework from social psychology t…

3. Close Uses this paper in depth Not relevant

   Acmite: Mitigating Gender Bias in LLMs through Concept-Guided Mutual Information

   Tian Lan, Xiao-Qing Cheng, Han Zhang et al. · 2026 · Not summarized yet

   Abstract

   Large language models (LLMs) can reproduce social stereotypes from their training data, motivating extensive research on model debiasing. However, existing methods often rely on explicit biased examples or predefined group-term substitutions, making them sensitive to wording and less effective at capturing stereotype concepts shared across diverse contexts. More importantly, they typically suppress biased outputs without explicitly modeling the statistical dependence between model outputs and the underlying stereotype concepts. We propose Acmite, a lightweight concept-guided framework for targeted and selective debiasing. Acmite represents stereotypes as structured semantic concepts and uses…

4. Close Not relevant

   Investigating Bias in LLM-Based Bias Detection: Disparities between LLMs and Human Perception

   Luyang Lin, Lingzhi Wang, Jinsong Guo et al. · 2024 · Computers and Society · cited 107 times · AI summary available

   Abstract

   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, concerns about inherent biases within these models persist. In this work, we investigate the presence and nature of bias within LLMs and its consequential impact on media bias detection. Departing from conventional approaches that focus solely on bias detection in media content, we delve into biases within the LLM systems themselves. Through meticulous examination, we probe whether LLMs exhibit biases, particularly in political bias prediction and text continuati…

5. Close Not relevant

   Redirected, Not Removed: Task-Dependent Stereotyping Reveals the Limits of LLM Alignments

   Divyanshu Kumar, Ishita Gupta, Nitin Aravind Birur et al. · 2026 · arXiv.org · preprint, not peer reviewed · cited 1 time · Not summarized yet

   Abstract

   How biased is a language model? The answer depends on how you ask. A model that refuses to choose between castes for a leadership role will, in a fill-in-the-blank task, reliably associate upper castes with purity and lower castes with lack of hygiene. Single-task benchmarks miss this because they capture only one slice of a model's bias profile. We introduce a hierarchical taxonomy covering 9 bias types, including under-studied axes like caste, linguistic, and geographic bias, operationalized through 7 evaluation tasks that span explicit decision-making to implicit association. Auditing 7 commercial and open-weight LLMs with \textasciitilde45K prompts, we find three systematic patterns. Fir…