Eugene Agichtein

Jul 8, 2024 | amazon.science | Marcus Collins |Eugene Agichtein |Oleg Rokhlenko |Shervin Malmasi

Continued improvement of conversational assistants in knowledge-rich domains like E-Commerce requires large volumes of realistic high-quality conversation data to power increasingly sophisticated LLM chatbots, dialogue managers, response rankers, and recommenders. The problem is worse for multi-modal interactions in realistic conversational product search and recommendation.

May 17, 2024 | amazon.science | Jason Choi |Marcus Collins |Eugene Agichtein |Oleg Rokhlenko

Conversational AI is a subtype of Human-Computer Interaction that has gained wide adoption. These systems are typically powered by Large Language Models (LLMs) that use Retrieval Augmented Generation (RAG) to infuse external knowledge, which is effective against issues like hallucination. However, automatically evaluating retrieval augmented conversations with minimal human effort remains challenging, particularly in online settings.

May 10, 2024 | amazon.science | Nikhita Vedula |Giuseppe Castellucci |Eugene Agichtein |Oleg Rokhlenko

Conversational Task Assistants (CTAs) guide users in performing a multitude of activities, such as making recipes. However, ensuring that interactions remain engaging, interesting, and enjoyable for CTA users is not trivial, especially for time-consuming or challenging tasks.

Apr 4, 2024 | arxiv.org | Eugene Agichtein

Sep 5, 2023 | amazon.science | Shervin Malmasi |Oleg Rokhlenko |Eugene Agichtein |Tryambak Gangopadhyay

A key application of conversational search is reining a user’s search intent by asking a series of clarification questions, aiming to improve the relevance of search results. Training and evaluating such conversational systems currently requires human participation, making it infeasible to examine a wide range of user behaviors.