Large language models develop novel social biases through adaptive exploration
Summary
This research explores how large language models develop new social biases through adaptive exploration, highlighting implications for AI fairness and ethical considerations.
View Cached Full Text
Cached at: 09/09/26, 12:42 AM
Similar Articles
Confirming Our Biases? Evaluating the Capabilities, Risks, and Societal Impact of Large Language Models
This preprint evaluates how six large language models respond to prompt framing and biased prompts across 160 prompts, finding that LLMs systematically adapt their responses to align with prompt framing even in factual contexts, potentially reinforcing user biases.
Cultural Adaptation in Large Language Models for Political Discourse
This paper explores methods for adapting large language models to cultural contexts in political discourse, aiming to improve cross-cultural understanding and reduce bias.
Mimicry without understanding: the origins of decision bias in large language models
This paper investigates how LLMs like ChatGPT-4o and Qwen develop decision biases through faulty mimicry of human behavior, even when preferences are not biased, and shows that scientific descriptions of biases can become self-fulfilling prophecies for LLM responses.
Lessons learned on language model safety and misuse
OpenAI shares lessons learned on language model safety and misuse, discussing challenges in measuring risks, the limitations of existing benchmarks, and their development of new evaluation metrics for toxicity and policy violations. The post also highlights concerns about labor market impacts and the need for continued research on measuring social effects of AI deployment at scale.
Large Language Models Should Learn Personalized Rather Than Aggregated Human Preferences
This position paper argues that large language models should learn from personalized rather than aggregated human preferences, highlighting theoretical limitations from social choice theory and practical issues from demographic diversity. It proposes bounded personalization frameworks that respect individual autonomy while maintaining universal safety constraints.