bias-evaluation

Tag

Cards List
#bias-evaluation

LLM-as-a-Demographic: Whom Sociodemographic Prompting Helps, and Whom It Hurts

arXiv cs.CL · 2026-09-02 Cached

This research paper examines how sociodemographic prompting affects LLMs' judgments in subjective tasks, finding that it often aligns models with majority groups while misrepresenting minority groups, with instruction-tuning identified as a potential cause.

0 favorites 0 likes
#bias-evaluation

ContextBias: Controlled Evaluation of Bias Persistence Under Context Shift in Text-to-Image Models

Hugging Face Daily Papers · 2026-08-30 Cached

This paper introduces ContextBias and ContextBench to evaluate bias persistence in text-to-image models, finding that bias increases in semantically unrelated contexts.

0 favorites 0 likes
#bias-evaluation

Probing Latent Colombian Identity Inferences in Qwen2.5-7B with Natural Language Autoencoders

arXiv cs.CL · 2026-07-27 Cached

This pilot study uses Natural Language Autoencoders to probe whether Qwen2.5-7B internally represents Colombian identity, socioeconomic status, or stereotype-related information when processing Colombian-Spanish and English prompts, finding evidence of latent inferences before they are verbalized.

0 favorites 0 likes
#bias-evaluation

RPAM: A Principled Metric for Evaluating Associations in Language Models with High Predictive Validity in Downstream Outputs

arXiv cs.CL · 2026-07-08 Cached

Introduces RPAM, a principled metric for evaluating associations in language models that demonstrates high predictive validity for downstream outputs, tested on Mistral-7B-Instruct, Mistral-7B, and GPT-2.

0 favorites 0 likes
#bias-evaluation

VIBE: Voice-Induced open-ended Bias Evaluation for Large Audio-Language Models via Real-World Speech

Hugging Face Daily Papers · 2026-07-03 Cached

VIBE is a framework that evaluates generative bias in Large Audio-Language Models using open-ended tasks with human-recorded speech, revealing systematic biases triggered by gender and accent cues.

0 favorites 0 likes
#bias-evaluation

Your Multimodal Speech Model Says I Have a Face for Radio

arXiv cs.CL · 2026-06-01 Cached

This paper presents the first bias evaluation of multimodal speech recognition models, finding significant accuracy differences across gender and ethnicity when pairing faces with audio, with implications for fairness in AI systems.

0 favorites 0 likes
← Back to home

Submit Feedback