5 papers
Pseudo-Deliberation in Language Models: When Reasoning Fails to Align Values and Actions
Sushrita Rakshit, Hanwen Zhang, Hua Shen
Large language models (LLMs) are often evaluated based on their stated values, yet these do not reliably translate into their actions, a discrepancy termed "value-action gap." In t…
Position: Towards Bidirectional Human-AI Alignment
Hua Shen, Tiffany Knearem, Reshmi Ghosh +21
Recent advances in general-purpose AI underscore the urgent need to align AI systems with human goals and values. Yet, the lack of a clear, shared understanding of what constitutes…
Emotionally-Aware Agents for Dispute Resolution
Sushrita Rakshit, James Hale, Kushal Chawla +2
In conflict, people use emotional expressions to shape their counterparts' thoughts, feelings, and actions. This paper explores whether automatic text emotion recognition offers in…
KODIS: A Multicultural Dispute Resolution Dialogue Corpus
James Hale, Sushrita Rakshit, Kushal Chawla +2
We present KODIS, a dyadic dispute resolution corpus containing thousands of dialogues from over 75 countries. Motivated by a theoretical model of culture and conflict, participant…
Real or Robotic? Assessing Whether LLMs Accurately Simulate Qualities of Human Responses in Dialogue
Jonathan Ivey, Shivani Kumar, Jiayu Liu +12
Studying and building datasets for dialogue tasks is both expensive and time-consuming due to the need to recruit, train, and collect data from study participants. In response, muc…