6 papers
Knowing When Not to Answer: Lightweight KB-Aligned OOD Detection for Safe RAG
Ilias Triantafyllopoulos, Renyi Qu, Salvatore Giorgi +3
Retrieval-Augmented Generation (RAG) systems are increasingly deployed in high-stakes domains, where safety depends not only on how a system answers, but also on whether a query sh…
The Illusion of Empathy: How AI Chatbots Shape Conversation Perception
Tingting Liu, Salvatore Giorgi, Ankit Aich +4
As AI chatbots increasingly incorporate empathy, understanding user-centered perceptions of chatbot empathy and its impact on conversation quality remains essential yet under-explo…
Modeling Human Subjectivity in LLMs Using Explicit and Implicit Human Factors in Personas
Salvatore Giorgi, Tingting Liu, Ankit Aich +6
Large language models (LLMs) are increasingly being used in human-centered social scientific tasks, such as data annotation, synthetic data creation, and engaging in dialog. Howeve…
Building Knowledge-Guided Lexica to Model Cultural Variation
Shreya Havaldar, Salvatore Giorgi, Sunny Rai +4
Cultural variation exists between nations (e.g., the United States vs. China), but also within regions (e.g., California vs. Texas, Los Angeles vs. San Francisco). Measuring this r…
DiverseDialogue: A Methodology for Designing Chatbots with Human-Like Diversity
Xiaoyu Lin, Xinkai Yu, Ankit Aich +2
Large Language Models (LLMs), which simulate human users, are frequently employed to evaluate chatbots in applications such as tutoring and customer service. Effective evaluation n…
Vernacular? I Barely Know Her: Challenges with Style Control and Stereotyping
Ankit Aich, Tingting Liu, Salvatore Giorgi +3
Large Language Models (LLMs) are increasingly being used in educational and learning applications. Research has demonstrated that controlling for style, to fit the needs of the lea…