Reindex-Then-Adapt: Improving Large Language Models for Conversational Recommendation
Open Access
- 10 March 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 866-875
Abstract
Large Language Models (LLMs) are revolutionizing conversational recommender systems (CRS) by effectively indexing item content, understanding complex conversational contexts, and generating relevant item titles. However, the autoregressive nature of LLMs, which outputs item titles as a long sequence of subtokens, hinders the ability to efficiently obtain and control recommendations across the entire item set. This challenge in calculating probabilities over all items limits LLMs' potential, such as (1) limiting control over recommendation popularities and (2) preventing the synergy of marrying LLMs and traditional recommender systems (RecSys). To address this challenge, we propose the Reindex-Then-Adapt (RTA) framework. It consists of two steps: (1) Reindex: a lightweight network learns to condense multi-token item titles into single tokens within the LLM and distills LLM-generated recommendations as ranked lists. This bypasses the autoregressive nature of LLMs while trying to preserve their CRS abilities; (2) Adapt: LLMs after reindexing enable efficient adjustment of probability distributions over single-token titles, further enhanced through RecSys integration. RTA bridges the strengths of LLMs and RecSys, enabling understanding of complex queries as LLMs do, while efficiently controlling recommended item distributions as in traditional RecSys. We show the effectiveness of our RTA over base LLMs across three CRS datasets with negligible additional parameters.Keywords
All Related Versions
This publication has 30 references indexed in Scilit:
- Fairness in recommender systems: research landscape and future directionsUser Modeling and User-Adapted Interaction, 2023
- Competition-level code generation with AlphaCodeScience, 2022
- Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusion2020
- Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems2020
- Deep language-based critiquing for recommender systems2019
- Self-Attentive Sequential Recommendation2018
- Towards Conversational Recommender Systems2016
- FISM2013
- Critiquing-based recommenders: survey and emerging trendsUser Modeling and User-Adapted Interaction, 2011
- DBpedia: A Nucleus for a Web of Open Data2007