Paul Erdős was one of the most prolific mathematicians to ever live, known for showing up at the door of others in the field and declaring they should host and feed him while they do maths together. I come to you with something a little different for my latest maths column - a plea to Hollywood to make a comedy biopic about one of the greatest mathematicians of all time, Paul Erdős. Why is Erdős (pronounced "air-dish") deserving of such acclaim? With almost 1500 papers to his name, he is probably the most prolific mathematician that ever lived, and possibly that will ever live. Unsurprisingly, with that many papers, he is known for his work across many areas of maths, from probability to number theory to graph theory.

We present a novel statistical framework for analyzing stereotypes in large language models (LLMs) by systematically estimating the bias and variation in their generation. Current evaluation metrics in the alignment literature often overlook the randomness of stereotypes caused by the inconsistent generative behavior of LLMs. For example, this inconsistency can result in LLMs displaying contradictory stereotypes, including those related to gender or race, for identical professions across varied contexts. Neglecting such inconsistency could lead to misleading conclusions in alignment evaluations and hinder the accurate assessment of the risk of LLM applications perpetuating or amplifying social stereotypes and unfairness.This work proposes a Bias-Volatility Framework (BVF) that estimates the probability distribution function of LLM stereotypes. Specifically, since the stereotype distribution fully captures an LLM's generation variation, BVF enables the assessment of both the likelihood and extent to which its outputs are against vulnerable groups, thereby allowing for the quantification of the LLM's aggregated discrimination risk. Furthermore, we introduce a mathematical framework to decompose an LLM's aggregated discrimination risk into two components: bias risk and volatility risk, originating from the mean and variation of LLM's stereotype distribution, respectively. We apply BVF to assess 12 commonly adopted LLMs and compare their risk levels. Our findings reveal that: i) Bias risk is the primary cause of discrimination risk in LLMs; ii) Most LLMs exhibit significant pro-male stereotypes for nearly all careers; iii) Alignment with reinforcement learning from human feedback lowers discrimination by reducing bias, but increases volatility; iv) Discrimination risk in LLMs correlates with key sociol-economic factors like professional salaries. Finally, we emphasize that BVF can also be used to assess other dimensions of generation inconsistency's impact on LLM behavior beyond stereotypes, such as knowledge mastery.

Text-to-Image (T2I) has witnessed significant advancements, demonstrating superior performance for various generative tasks. However, the presence of stereotypes in T2I introduces harmful biases that require urgent attention as the T2I technology becomes more prominent.Previous work for stereotype mitigation mainly concentrated on mitigating stereotypes engendered with individual objects within images, which failed to address stereotypes engendered by the association of multiple objects, referred to as . For example, mentioning ''black people'' and ''houses'' separately in prompts may not exhibit stereotypes. Nevertheless, when these two objects are associated in prompts, the association of ''black people'' with ''poorer houses'' becomes more pronounced. To tackle this issue, we propose a novel framework, MAS, to Mitigate Association-engendered Stereotypes.

With rapid development and deployment of generative language models in global settings, there is an urgent need to also scale our measurements of harm, not just in the number and types of harms covered, but also how well they account for local cultural contexts, including marginalized identities and the social biases experienced by them.Current evaluation paradigms are limited in their abilities to address this, as they are not representative of diverse, locally situated but global, socio-cultural perspectives. It is imperative that our evaluation resources are enhanced and calibrated by including people and experiences from different cultures and societies worldwide, in order to prevent gross underestimations or skews in measurements of harm. In this work, we demonstrate a socio-culturally aware expansion of evaluation resources in the Indian societal context, specifically for the harm of stereotyping. We devise a community engaged effort to build a resource which contains stereotypes for axes of disparity that are uniquely present in India. The resultant resource increases the number of stereotypes known for and in the Indian context by over 1000 stereotypes across many unique identities. We also demonstrate the utility and effectiveness of such expanded resources for evaluations of language models.CONTENT WARNING: This paper contains examples of stereotypes that may be offensive.

With the wide and cross-domain adoption of Large Language Models, it becomes crucial to assess to which extent the statistical correlations in training data, which underlie their impressive performance, hide subtle and potentially troubling biases. Gender bias in LLMs has been widely investigated from the perspectives of works, hobbies, and emotions typically associated with a specific gender. In this study, we introduce a novel perspective. We investigate whether LLMs can predict an individual's gender based solely on online shopping histories and whether these predictions are influenced by gender biases and stereotypes. Using a dataset of historical online purchases from users in the United States, we evaluate the ability of six LLMs to classify gender and we then analyze their reasoning and products-gender co-occurrences. Results indicate that while models can infer gender with moderate accuracy, their decisions are often rooted in stereotypical associations between product categories and gender. Furthermore, explicit instructions to avoid bias reduce the certainty of model predictions, but do not eliminate stereotypical patterns. Our findings highlight the persistent nature of gender biases in LLMs and emphasize the need for robust bias-mitigation strategies.

This is shown by a recent collaborative study between Johannes Gutenberg University Mainz (JGU) and the universities of Hamburg and Washington. The results, presented at this year's Conference on Empirical Methods in Natural Language Processing (EMNLP) - one of the world's leading conferences in computational linguistics - show that all tested AI systems reproduce social stereotypes. "Dialects are an essential part of cultural identity," emphasized Minh Duc Bui, a doctoral researcher in von der Wense's Natural Language Processing (NLP) group at JGU's Institute of Computer Science. "Our analyses suggest that language models associate dialects with negative traits - thereby perpetuating problematic social biases." Using linguistic databases containing orthographic and phonetic variants of German dialects, the team first translated seven regional varieties into Standard German.

Large Language models (LLMs), such as ChatGPT, have gained popularity in recent years with the advancement of Natural Language Processing (NLP), with use cases spanning many disciplines and daily lives as well. LLMs inherit explicit and implicit biases from the datasets they were trained on; these biases can include social, ethical, cultural, religious, and other prejudices and stereotypes. It is important to comprehensively examine such shortcomings by identifying the existence and extent of such biases, recognizing the origin, and attempting to mitigate such biased outputs to ensure fair outputs to reduce harmful stereotypes and misinformation. This study inspects and highlights the need to address biases in LLMs amid growing generative Artificial Intelligence (AI). We utilize bias-specific benchmarks such StereoSet and CrowSPairs to evaluate the existence of various biases in many different generative models such as BERT, GPT 3.5, and ADA. To detect both explicit and implicit biases, we adopt a three-pronged approach for thorough and inclusive analysis. Results indicate fine-tuned models struggle with gender biases but excel at identifying and avoiding racial biases. Our findings also illustrated that despite some cases of success, LLMs often over-rely on keywords in prompts and its outputs. This demonstrates the incapability of LLMs to attempt to truly understand the accuracy and authenticity of its outputs. Finally, in an attempt to bolster model performance, we applied an enhancement learning strategy involving fine-tuning, models using different prompting techniques, and data augmentation of the bias benchmarks. We found fine-tuned models to exhibit promising adaptability during cross-dataset testing and significantly enhanced performance on implicit bias benchmarks, with performance gains of up to 20%.

Existing AI bias evaluation benchmarks largely reflect Western perspectives, leaving African contexts underrepresented and enabling harmful stereotypes in applications across various domains. To address this gap, we introduce AfriStereo, the first open-source African stereotype dataset and evaluation framework grounded in local socio-cultural contexts. Through community engaged efforts across Senegal, Kenya, and Nigeria, we collected 1,163 stereotypes spanning gender, ethnicity, religion, age, and profession. Using few-shot prompting with human-in-the-loop validation, we augmented the dataset to over 5,000 stereotype-antistereotype pairs. Entries were validated through semantic clustering and manual annotation by culturally informed reviewers. Preliminary evaluation of language models reveals that nine of eleven models exhibit statistically significant bias, with Bias Preference Ratios (BPR) ranging from 0.63 to 0.78 (p <= 0.05), indicating systematic preferences for stereotypes over antistereotypes, particularly across age, profession, and gender dimensions. Domain-specific models appeared to show weaker bias in our setup, suggesting task-specific training may mitigate some associations. Looking ahead, AfriStereo opens pathways for future research on culturally grounded bias evaluation and mitigation, offering key methodologies for the AI community on building more equitable, context-aware, and globally inclusive NLP technologies.

Moral alignment has emerged as a widely adopted approach for regulating the behavior of pretrained language models (PLMs), typically through fine-tuning on curated datasets. Gender stereotype mitigation is a representational task within the broader application of moral alignment. However, this process often comes at the cost of degraded downstream task performance. Prior studies commonly aim to achieve a performance trade-off by encouraging PLMs to selectively forget only stereotypical knowledge through carefully designed fairness objective, while preserving their language modeling capability (overall forgetting). In this short paper, we investigate whether the performance trade-off can be achieved through the lens of forgetting and the fairness objective. Our analysis shows that the large datasets needed for satisfactory fairness highlight the limitations of current fairness objectives in achieving an effective trade-off: (1) downstream task performance is strongly correlated with overall forgetting; (2) selective forgetting reduces stereotypes, but overall forgetting increases. and (3) general solutions for alleviating forgetting are ineffective at reducing the overall forgetting and fail to improve downstream task performance.