# Reindex-Then-Adapt: Improving Large Language Models for Conversational Recommendation

arXiv: https://arxiv.org/abs/2405.12119 · HTML: https://mlsanity.com/paper/2405.12119/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 69 references that are in the map.
- First posted on arXiv 20 May 2024.

## Builds on (most cited first, 30 of 51)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)](https://mlsanity.com/paper/2203.13366/) (2022)
- [TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation](https://mlsanity.com/paper/2305.00447/) (2023)
- [One Embedder, Any Task: Instruction-Finetuned Text Embeddings](https://mlsanity.com/paper/2212.09741/) (2022)
- [Large Language Models are Zero-Shot Rankers for Recommender Systems](https://mlsanity.com/paper/2305.08845/) (2023)
- [CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X](https://mlsanity.com/paper/2303.17568/) (2023)
- [Transformer Memory as a Differentiable Search Index](https://mlsanity.com/paper/2202.06991/) (2022)
- [Bias and Debias in Recommender System: A Survey and Future Directions](https://mlsanity.com/paper/2010.03240/) (2020)
- [Is ChatGPT a Good Recommender? A Preliminary Study](https://mlsanity.com/paper/2304.10149/) (2023)
- [Towards Deep Conversational Recommendations](https://mlsanity.com/paper/1812.07617/) (2018)
- [Uncovering ChatGPT's Capabilities in Recommender Systems](https://mlsanity.com/paper/2305.02182/) (2023)
- [M6-Rec: Generative Pretrained Language Models are Open-Ended Recommender Systems](https://mlsanity.com/paper/2205.08084/) (2022)
- [Large Language Models as Zero-Shot Conversational Recommenders](https://mlsanity.com/paper/2308.10053/) (2023)
- [Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusion](https://mlsanity.com/paper/2007.04032/) (2020)
- [Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Prediction](https://mlsanity.com/paper/2305.06474/) (2023)
- [Towards Knowledge-Based Recommender Dialog System](https://mlsanity.com/paper/1908.05391/) (2019)
- [GPT4Rec: A Generative Framework for Personalized Recommendation and User Interests Interpretation](https://mlsanity.com/paper/2304.03879/) (2023)

## Built on by (most cited first, 10 of 10)

- [Towards Next-Generation LLM-based Recommender Systems: A Survey and Beyond](https://mlsanity.com/paper/2410.19744/) (2024)
- [Bridging Conversational and Collaborative Signals for Conversational Recommendation](https://mlsanity.com/paper/2412.06949/) (2024)
- [Search-Based Interaction For Conversation Recommendation via Generative Reward Model Based Simulated User](https://mlsanity.com/paper/2504.20458/) (2025)
- [Beyond Single Labels: Improving Conversational Recommendation through LLM-Powered Data Augmentation](https://mlsanity.com/paper/2508.05657/) (2025)
- [LaViC: Adapting Large Vision-Language Models to Visually-Aware Conversational Recommendation](https://mlsanity.com/paper/2503.23312/) (2025)
- [RecRM-Bench: Benchmarking Multidimensional Reward Modeling for Agentic Recommender Systems](https://mlsanity.com/paper/2605.11874/) (2026)
- [Retrieval Augmented Conversational Recommendation with Reinforcement Learning](https://mlsanity.com/paper/2604.04457/) (2026)
- [RecToM: A Benchmark for Evaluating Machine Theory of Mind in LLM-based Conversational Recommender Systems](https://mlsanity.com/paper/2511.22275/) (2025)
- [LatentCRS: A Variational EM Framework for Bridging Semantics and Behavior in LLM-based Conversational Recommendation](https://mlsanity.com/paper/2503.10703/) (2025)
- [Give Users the Wheel: Towards Promptable Recommendation Paradigm](https://mlsanity.com/paper/2602.18929/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are revolutionizing conversational recommender systems by adeptly indexing item content, understanding complex conversational contexts, and generating relevant item titles. However, controlling the distribution of recommended items remains a challenge. This leads to suboptimal performance due to the failure to capture rapidly changing data distributions, such as item popularity, on targeted conversational recommendation platforms. In conversational recommendation, LLMs recommend items by generating the titles (as multiple tokens) autoregressively, making it difficult to obtain and control the recommendations over all items. Thus, we propose a Reindex-Then-Adapt (RTA) framework, which converts multi-token item titles into single tokens within LLMs, and then adjusts the probability distributions over these single-token item titles accordingly. The RTA framework marries the benefits of both LLMs and traditional recommender systems (RecSys): understanding complex queries as LLMs do; while efficiently controlling the recommended item distributions in conversational recommendations as traditional RecSys do. Our framework demonstrates improved accuracy metrics across three different conversational recommendation datasets and two adaptation settings