Explore a cutting-edge approach to personalized multi-session conversational search in this 14-minute conference talk from SIGIR 2024. Delve into the innovative LAPS (LLM-Augmented Dialogue Construction for Personalized Multi-Session Conversational Search) method presented by authors Hideaki Joko, Shubham Chatterjee, Andrew Ramsay, Arjen de Vries, Jeff Dalton, and Faegheh Hasibi. Gain insights into how Large Language Models (LLMs) are leveraged to enhance dialogue construction in conversational information retrieval and recommendation systems. Learn about the potential implications of this research for improving personalized search experiences across multiple user sessions.
LLM-Augmented Dialogue Construction for Personalized Multi-Session Conversational Search - Session M3.2
Association for Computing Machinery (ACM) via YouTube
Overview
Syllabus
SIGIR 2024 M3.2 [fp] LAPS: LLM-Augmented Dialogue Construction for Personalized Multi-Session CS
Taught by
Association for Computing Machinery (ACM)
Related Courses
-
An Empirical Analysis on Multi-turn Conversational Recommender Systems - Lecture 3.2
-
Broadening the View: Demonstration-augmented Prompt Learning for Conversational Recommendation - Session M3.2
-
Towards Human-centered Proactive Conversational Agents - Conversational IR and Recommendation
-
Explainability for Transparent Conversational Information-Seeking
-
Rethinking the Evaluation of Dialogue Systems: Effects of User Feedback on Crowdworkers and LLMs
-
Large Language Models for Intent-Driven Session Recommendations - Session M1.6
