My research focuses on mitigating hallucinations in interactive dialogue systems through efficient, data-driven methods. I specialize in developing scalable solutions that improve the factual accuracy and reliability of dialogue agents, particularly in real-time, resource-constrained applications such as virtual assistants, educational tools, and knowledge-based question answering (KBQA) systems. A central theme of my work is exploring the use of smaller, domain-specific models—trained via techniques like knowledge distillation and self-training—as viable, cost-effective alternatives to large, generalist LLMs.

My work also emphasizes the value of synthetic data, showing that high-quality LLM-generated data can match or exceed the effectiveness of human annotations in hallucination reduction. Complementing these modeling efforts, I am developing more robust evaluation frameworks to better assess and detect hallucinations in dialogue settings, proposing dynamic, context-aware metrics that go beyond the limitations of existing tools like FactScore.

Overall, my goal is to improve the reliability, accessibility, and usability of interactive AI systems while promoting efficient and responsible development practices.

Projects:

Virtual Museum Tour Guide

I'm working on creating a virtual, interactive avatar that can act as a tour guide for the Language Pod at COSI. This project began as an offshoot of the Virtual Patient Project, but has since been revamped to be a document-grounded conversational agent that can respond to user questions dynamically and with contextual awareness. I work primarily on the response generation model and have been focusing on leveraging the benefits of LLMs (like ChatGPT) but mitigating the risks of confabulations/hallucinations and toxic outputs, particularly through knowledge distillation. The initial stages of this work are described in this paper, which I presented at the Taming LLMs Workshop in Prague, Czech Republic.

Interactive Semantic Parsing

My work in interactive semantic parsing focuses on bridging the gap between natural language and query languages like SPARQL. I've applied RSA-based NLG techniques to improve the generation of clarification questions in human-in-the-loop correction systems, minimizing both hallucinations and omissions. This work, which I presented at ACL 2022 in Dublin, can be found here. A follow-up work, presented by my co-author at InterNLP, can be found here. We also conducted a usability study, which I presented at HumEval at LREC-COLING 2024 in Turin, Italy.

AlexaPrize Taskbot Challenge

I was also part of a team that participated in the AlexaPrize Taskbot Challenge, in which we achieved 3rd place. I presented a demo of this work at SIGDIAL 2023.