# Aligning Language Models for Versatile Text-based Item Retrieval

arXiv: https://arxiv.org/abs/2402.18899 · HTML: https://mlsanity.com/paper/2402.18899/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Feb 2024.

## Built on by (most cited first, 4 of 4)

- [Explaining Length Bias in LLM-Based Preference Evaluations](https://mlsanity.com/paper/2407.01085/) (2024)
- [RecAI: Leveraging Large Language Models for Next-Generation Recommender Systems](https://mlsanity.com/paper/2403.06465/) (2024)
- [Uncertainty Quantification and Decomposition for LLM-based Recommendation](https://mlsanity.com/paper/2501.17630/) (2025)
- [Unveiling the Learning Mind of Language Models: A Cognitive Framework and Empirical Study](https://mlsanity.com/paper/2506.13464/) (2025)

## Abstract (arXiv)

This paper addresses the gap between general-purpose text embeddings and the specific demands of item retrieval tasks. We demonstrate the shortcomings of existing models in capturing the nuances necessary for zero-shot performance on item retrieval tasks. To overcome these limitations, we propose generate in-domain dataset from ten tasks tailored to unlocking models' representation ability for item retrieval. Our empirical studies demonstrate that fine-tuning embedding models on the dataset leads to remarkable improvements in a variety of retrieval tasks. We also illustrate the practical application of our refined model in a conversational setting, where it enhances the capabilities of LLM-based Recommender Agents like Chat-Rec. Our code is available at https://github.com/microsoft/RecAI.