Study: Claude, ChatGPT Offer Different Shopping Prices Based on Wealth
A Bloomberg-cited study says Claude and ChatGPT quote different shopping prices based on user wealth.
Stories per day · 30 days
2 RSS
10 stories, newest first · one card per story
Stories tagged #bias
BiasFlow: Geometric Monitoring and Backbone Regularization for Spurious Feature Reliance
BiasFlow regularizes backbone centroids, lifting worst-group accuracy by up to 26 points on UrbanCars.
HackerRank’s AI interviewer offers a glimpse into what job interviews could become
HackerRank made its Chakra AI interviewer generally available after more than 500,000 beta interviews.
2
Collective Bias Mitigation via Model Routing and Collaboration
Collective Bias Mitigation routes multiple LLMs, and a committee cut age bias from 0.25 to 0.10.
Source Preference in the Wild: How LLM Agents Favor Items by Source, and How to Reduce It
Study of 12 LLM agents finds systematic source preference bias that overrides requirement satisfaction; hiding or relabeling source info changes selection rates.
Who Gets a Token, and What Does It Carry? Unequal Name Support and Concept Access in Large Language Models
A study finds unequal name tokenization in LLMs predicts demographic gaps in task-relevant concept access.
Harm Laundering in GPT Models: Evidence That Gender Discrimination Is Transformed Rather Than Reduced Across Safety-Trained Generations
Study of 450,000 GPT-lineage completions finds safety training transforms gender discrimination into subtle 'harm laundering' that toxicity classifiers miss.
Verifiable Social Reasoning for LLM Assistants
Fuse, a multi-agent simulation with hidden motives, evaluates LLM social reasoning, revealing compounding difficulty from user mediation and bias sensitivity.
Before You Poll with LLMs: A Deliberative Diagnostic Framework
Deliberative diagnostic shows all five tested frontier LLMs misrepresent human belief shifts after arguments, with GPT-5.1 reversing on outgroup questions.
The Frontier AEO Tracker: What Astra Chooses (and every other frontier model, and what you can do about it)
Latent Space launches an AEO tracker scoring 7 frontier models' product recommendations across 161 categories, revealing generational bias flips.