6 papers
Benchmarking Overton Pluralism in LLMs
Elinor Poole-Dayan, Jiayi Wu, Taylor Sorensen +2
We introduce OVERTONBENCH, a novel framework for measuring Overton pluralism in LLMs--the extent to which diverse viewpoints are represented in model outputs. We (i) formalize Over…
EVALUESTEER: Measuring Reward Model Steerability Towards Values and Preferences
Kshitish Ghate, Andy Liu, Devansh Jain +5
As large language models (LLMs) are deployed globally, creating pluralistic systems that can accommodate the diverse preferences and values of users worldwide becomes essential. We…
Value Profiles for Encoding Human Variation
Taylor Sorensen, Pushkar Mishra, Roma Patel +6
Modelling human variation in rating tasks is crucial for personalization, pluralistic model alignment, and computational social science. We propose representing individuals using n…
Political Neutrality in AI Is Impossible- But Here Is How to Approximate It
Jillian Fisher, Ruth E. Appel, Chan Young Park +9
AI systems often exhibit political bias, influencing users' opinions and decisions. While political neutrality-defined as the absence of bias-is often seen as an ideal solution for…
Can Language Models Reason about Individualistic Human Values and Preferences?
Liwei Jiang, Taylor Sorensen, Sydney Levine +1
Recent calls for pluralistic alignment emphasize that AI systems should address the diverse needs of all people. Yet, efforts in this space often require sorting people into fixed…
Information-Guided Identification of Training Data Imprint in (Proprietary) Large Language Models
Abhilasha Ravichander, Jillian Fisher, Taylor Sorensen +6
High-quality training data has proven crucial for developing performant large language models (LLMs). However, commercial LLM providers disclose few, if any, details about the data…