Authors: Ryutaro Asahara, Masaki Takahashi, Chiho Iwahashi, Michimasa Inaba

Published on: February 07, 2024

Impact Score: 8.22

Arxiv code: Arxiv:2402.04523

Summary

• What is new: Introduction of the SumRec framework for information recommendation from open-domain chat dialogue.
• Why this is important: Existing methods struggle to effectively utilize the vast amount of user-related information within open-domain chat dialogues for personalized information recommendation.
• What the research proposes: The SumRec framework uses a large language model to summarize dialogues for extracting relevant speaker and item information, which is then used for personalized recommendations.
• Results: SumRec outperforms baseline methods in providing better information recommendations by effectively summarizing and utilizing chat dialogues.

Technical Details

Technological frameworks used: SumRec

Models used: Large Language Model (LLM) for summarization

Data used: ChatRec dataset

Potential Impact

Personalized recommendation services, chat-based support systems, and conversational AI platforms.

Want to implement this idea in a business?

We have generated a startup concept here: PersoRec.