Graph Meets LLM: A Novel Approach to Collaborative Filtering for Robust Conversational Understanding
Zheng Chen, Ziyan Jiang, Fan Yang, Eunah Cho, Xing Fan, Xiaojiang Huang, Yanbin Lu, Aram Galstyan
Abstract
A Personalized Query Rewriting system strives to minimize defective queries to ensure robust conversational functionality by considering individual user behavior and preferences. It’s designed as a search-based system, maintaining a user index of past successful interactions with the conversational AI. However, this method faces challenges with unseen interactions, which refers to novel user interactions not covered by the user’s historical index. This paper introduces our Collaborative Query Rewriting approach, which utilizes underlying topological information to assist in rewriting defective queries arising from unseen user interactions. This approach begins by constructing a “User Feedback Interaction Graph” (FIG) using historical user-entity interactions. Subsequently, we traverse through the graph edges to establish an enhanced user index, referred to as the “collaborative user index”. This paper then further explores the use of Large Language Models (LLMs) in conjunction with graph traversal, leading to a significant increase in index coverage for unseen interactions. The effectiveness of our proposed approach has been proven through experiments on a large-scale real-world dataset and online A/B experiments.- Anthology ID:
- 2023.emnlp-industry.75
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Mingxuan Wang, Imed Zitouni
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 811–819
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-industry.75
- DOI:
- 10.18653/v1/2023.emnlp-industry.75
- Cite (ACL):
- Zheng Chen, Ziyan Jiang, Fan Yang, Eunah Cho, Xing Fan, Xiaojiang Huang, Yanbin Lu, and Aram Galstyan. 2023. Graph Meets LLM: A Novel Approach to Collaborative Filtering for Robust Conversational Understanding. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 811–819, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Graph Meets LLM: A Novel Approach to Collaborative Filtering for Robust Conversational Understanding (Chen et al., EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/naacl-24-ws-corrections/2023.emnlp-industry.75.pdf