Introduction

We have published several works on generative retrieval as follows.

Multiview Identifiers Enhanced Generative Retrieval. ACL 2023. (MINDER)
Generative Retrieval for Conversational Question Answering. IPM 2023. (GCoQA)
Learning to Rank in Generative Retrieval. AAAI 2024. (LTRGR)
Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond. ACL 2024 (GRACE).
Distillation Enhanced Generative Retrieval. ACL 2024 findings (DGR).

All code, data, and checkpoints of the above works are open-released:

1. MINDER, LTRGR, and DGR, are a series of works on text retrieval. LTRGR and DGR are continuously training based on the MINDER model, so we release MINDER, LTRGR, and DGR together in the same repository https://github.com/liyongqi67/MINDER.
2. GCoQA is the work on conversational retrieval and is released at https://github.com/liyongqi67/GCoQA.
3. GRACE is the work on cross-modal retrieval and is released at https://github.com/liyongqi67/GRACE.

You could also refer to our preprint works on generative retrieval.

A Survey of Generative Search and Recommendation in the Era of Large Language Models.
Revolutionizing Text-to-Image Retrieval as Autoregressive Token-to-Voken Generation.