Hugging Face Trending Papers
Aug 5
The Effect of Perceived Race and Gender on Police Language Use: Experimental Evidence from VR Simulations
Against the backdrop of violence in police interactions with the U. S.
The Effect of Perceived Race and Gender on Police Language Use: Experimental Evidence from VR Simulations
arXiv:2608. 05050v1 Announce Type: cross Abstract: Against the backdrop of violence in police interactions with the U.
Related stories
arXiv Computation and Language
Oct 27
Veracity labels flip the emotional tone of language models but leave racial disparities intact
arXiv:2610.33021v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly deliver information through personas, but it is unclear whether correcting the facts also makes their frami...
Hugging Face Trending Papers
Oct 26
When Pointing Becomes Profiling: Social Bias and Refusal in Text-Steerable Visual Encoders
Text-steerable visual encoders condition a frozen Vision Transformer on a natural-language prompt and point at the matching image region, producing prompt-conditioned heatmaps and features. We audit t...
arXiv Computation and Language
Sep 17
Do Social Patterns Hold in Synthetic Data? Analyzing Cyberbullying Dynamics in LLM-Generated and Authentic Dialogues
The paper investigates whether large language models (LLMs) can generate synthetic cyberbullying conversations that replicate the social dynamics of real interactions. Using a comprehensive framework, the authors compare authentic dialogues with synthetic ones from GPT, Grok, and LLaMA across structural, linguistic, affective, and temporal dimensions, and conduct human evaluations of realism. Results show that while LLMs preserve high‑level interaction patterns, they systematically distort finer‑grained social phenomena, with model‑specific biases such as GPT’s suppression of harmful content and Grok’s amplification of aggression.
arXiv Computer Vision
Oct 27
When Pointing Becomes Profiling: Social Bias and Refusal in Text-Steerable Visual Encoders
arXiv:2610.35017v1 Announce Type: new Abstract: Text-steerable visual encoders condition a frozen Vision Transformer on a natural-language prompt and point at the matching image region, producing pro...
arXiv AI
Sep 17
Linguistic Triggers of Gender and Racial Bias in Open-Weight LLMs Applied to Recruitment
The paper reports the first systematic audit of open‑weight large language models (LLMs) in hiring contexts, examining how job‑posting language influences recruiter and job‑seeker simulations across six models. It finds that agentic language lowers recruiter scores for female candidates while communal language mitigates this effect, and that coded‑exclusion language sharply reduces recruiter scores for non‑White candidates and discourages non‑White personas from applying. The study also identifies the explicit demographic label as the main causal factor and proposes a concrete pre‑deployment audit protocol aligned with EU and U.S. regulatory requirements.
arXiv AI
Sep 1
Multimodal Large Language Models Predict Urban Safety Perception but Encode Non-Neutral Demographic Priors
arXiv:2503.00610v2 Announce Type: replace-cross Abstract: Understanding how people perceive urban environments is essential for inclusive planning, yet conventional surveys are costly and difficult t...
arXiv AI
Aug 12
ConVAWG: A Retrieval-Grounded Framework for Controlled Synthetic Dialogue Generation in Violence Against Women and Girls
arXiv:2608. 11200v1 Announce Type: cross Abstract: Synthetic dialogue generation offers a way to study conversational dynamics in sensitive domains where real data are difficult to access, release, or annotate.
arXiv Machine Learning
Sep 3
FairLens: Benchmarking Fairness in Vision-Language Models for High-Stakes Decision-Making
FairLens is a benchmark and evaluation framework that measures fairness and validity of vision‑language models (VLMs) in high‑stakes domains such as hiring, legal, and healthcare. It uses over 100,000 face‑image and question pairs covering gender, race, and age, and assesses responses through demographic parity, soundness, demographic association, and bias in free‑text generation. The study finds that VLMs often make unwarranted inferences from faces rather than abstaining, especially in legal and healthcare contexts, and that small parity gaps can still hide unsafe treatment across groups.
arXiv Computation and Language
Sep 23
Do Synthetic Personas Predict Real Audience Response? A Sim-to-Real Study Where a No-Persona Baseline Beats Persona-Based Copy Simulation
The study evaluates whether large language models (LLMs) used as synthetic personas can predict real audience responses to marketing copy. Using thousands of headline A/B tests from the Upworthy Research Archive, the authors compare a ten-persona panel grounded in real audience demographics to a no-persona zero‑shot baseline that asks the model for a typical reader’s click likelihood. Results show that the no‑persona baseline outperforms the persona‑based approach, with higher predictive validity and top‑1 accuracy, indicating that forcing the model to role‑play specific personas introduces bias and noise.
arXiv Computation and Language
Oct 19
Analyzing Occupational Gender Bias across the LLM Training Lifecycle
arXiv:2610.23587v1 Announce Type: new Abstract: Post-training is widely assumed to reduce the social biases language models inherit from pretraining, yet direct evidence for this assumption remains m...
arXiv Computation and Language
Oct 23
Invisibilization as a Source of Probability Bias in Language Models
The paper investigates how large language models (LLMs) from OpenAI and Anthropic exhibit probability bias when deciding whether to trust information from reporters of different racial descriptions. Using a two‑urn Bayesian game and 6,600 sessions, the authors find that models often refuse to assess a reporter’s credibility—especially for Black‑described reporters—yet when they do assess, Black reporters receive slightly higher trust. The bias is subtle, growing with reasoning effort, and is not detected by standard audits that compare average trust or only assessed cases.