SumRec: A Framework for Recommendation using Open-Domain Dialogue

TL;DR

Open-domain chat dialogues encode user interests but extracting actionable signals for recommendations is challenging. SumRec addresses this by using a large language model to produce compact speaker summaries from a dialogue and to generate item-specific guidance based on user type, then feeding both into a score-estimation component to produce a recommendation score. The framework is evaluated on the newly constructed ChatRec dataset, and results show improved recommendation quality over baselines that operate on raw dialogues and item descriptions. The work provides a publicly available dataset and code, enabling reproducibility and easier integration into dialogue-aware personalization systems.

Abstract

Chat dialogues contain considerable useful information about a speaker's interests, preferences, and experiences.Thus, knowledge from open-domain chat dialogue can be used to personalize various systems and offer recommendations for advanced information.This study proposed a novel framework SumRec for recommending information from open-domain chat dialogue.The study also examined the framework using ChatRec, a newly constructed dataset for training and evaluation. To extract the speaker and item characteristics, the SumRec framework employs a large language model (LLM) to generate a summary of the speaker information from a dialogue and to recommend information about an item according to the type of user.The speaker and item information are then input into a score estimation model, generating a recommendation score.Experimental results show that the SumRec framework provides better recommendations than the baseline method of using dialogues and item descriptions in their original form. Our dataset and code is publicly available at https://github.com/Ryutaro-A/SumRec