6 papers
A Roadmap to Impactful Pluralistic Alignment Research
Elinor Poole-Dayan, Jillian Fisher, Atoosa Kasirzadeh +3
Pluralistic value alignment---the goal of building AI systems that represent and serve diverse human values and perspectives---has emerged as an active research agenda. Yet, there'…
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…
Applying Large Language Models to Characterize Public Narratives
Elinor Poole-Dayan, Daniel T Kessler, Hannah Chiou +4
Public Narratives (PNs) are key tools for leadership development and civic mobilization, yet their systematic analysis remains challenging due to their subjective interpretation an…
LLM Targeted Underperformance Disproportionately Impacts Vulnerable Users
Elinor Poole-Dayan, Deb Roy, Jad Kabbara
While state-of-the-art large language models (LLMs) have shown impressive performance on many tasks, there has been extensive research on undesirable model behavior such as halluci…
Computational Analysis of Conversation Dynamics through Participant Responsivity
Margaret Hughes, Brandon Roy, Elinor Poole-Dayan +2
Growing literature explores toxicity and polarization in discourse, with comparatively less work on characterizing what makes dialogue prosocial and constructive. We explore conver…
An AI-Powered Framework for Analyzing Collective Idea Evolution in Deliberative Assemblies
Elinor Poole-Dayan, Deb Roy, Jad Kabbara
In an era of increasing societal fragmentation, political polarization, and erosion of public trust in institutions, representative deliberative assemblies are emerging as a promis…