14 papers
The Effect of Perceived Race and Gender on Police Language Use: Experimental Evidence from VR Simulations
Sandra C. Sandoval, Navita Goyal, Rashawn Ray +3
Against the backdrop of violence in police interactions with the U.S. public, we explore how deferentially police officers speak to virtual characters depicted as Black adult males…
On the Role of Citations in Preference Data
Yu Hou, Hal Daumé, Rachel Rudinger +1
Many NLP tasks require systems to provide attribution in their outputs--i.e. citations to grounding sources. Attribution serves as a bulwark against model hallucination and as a me…
SMARTER: A Data-efficient Framework to Improve Toxicity Detection with Explanation via Self-augmenting Large Language Models
Huy Nghiem, Advik Sachdeva, Hal Daumé
WARNING: This paper contains examples of offensive materials. To address the proliferation of toxic content on social media, we introduce SMARTER, we introduce SMARTER, a data-effi…
Balancing Safety and Helpfulness in Healthcare AI Assistants through Iterative Preference Alignment
Huy Nghiem, Swetasudha Panda, Devashish Khatwani +3
Large Language Models (LLMs) are increasingly used in healthcare, yet ensuring their safety and trustworthiness remains a barrier to deployment. Conversational medical assistants m…
Which Demographic Features Are Relevant for Individual Fairness Evaluation of U.S. Recidivism Risk Assessment Tools?
Tin Trung Nguyen, Jiannan Xu, Phuong-Anh Nguyen-Le +4
Despite its constitutional relevance, the technical ``individual fairness'' criterion has not been operationalized in U.S. state or federal statutes/regulations. We conduct a human…
A Necessary Step toward Faithfulness: Measuring and Improving Consistency in Free-Text Explanations
Lingjun Zhao, Hal Daumé
Faithful free-text explanations are important to ensure transparency in high-stakes AI decision-making contexts, but they are challenging to generate by language models and assess…