# Re3val: Reinforced and Reranked Generative Retrieval

arXiv: https://arxiv.org/abs/2401.16979 · HTML: https://mlsanity.com/paper/2401.16979/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jan 2024.

## Built on by (most cited first, 9 of 9)

- [From Matching to Generation: A Survey on Generative Information Retrieval](https://mlsanity.com/paper/2404.14851/) (2024)
- [Stochastic RAG: End-to-End Retrieval-Augmented Generation through Expected Utility Maximization](https://mlsanity.com/paper/2405.02816/) (2024)
- [Question-Based Retrieval using Atomic Units for Enterprise RAG](https://mlsanity.com/paper/2405.12363/) (2024)
- [DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation](https://mlsanity.com/paper/2505.07233/) (2025)
- [Efficient Dynamic Clustering-Based Document Compression for Retrieval-Augmented-Generation](https://mlsanity.com/paper/2504.03165/) (2025)
- [From Relevance to Authority: Authority-aware Generative Retrieval in Web Search Engines](https://mlsanity.com/paper/2604.13468/) (2026)
- [eXplainable Bayesian Multi-Perspective Generative Retrieval](https://mlsanity.com/paper/2402.02418/) (2024)
- [A Method for Detecting Legal Article Competition for Korean Criminal Law Using a Case-augmented Mention Graph](https://mlsanity.com/paper/2412.11787/) (2024)
- [WIDE: Wildcard Inference with Dynamic Expansion for Cross-Modal Generative Retrieval](https://mlsanity.com/paper/2609.03554/) (2026)

## Abstract (arXiv)

Generative retrieval models encode pointers to information in a corpus as an index within the model's parameters. These models serve as part of a larger pipeline, where retrieved information conditions generation for knowledge-intensive NLP tasks. However, we identify two limitations: the generative retrieval does not account for contextual information. Secondly, the retrieval can't be tuned for the downstream readers as decoding the page title is a non-differentiable operation. This paper introduces Re3val, trained with generative reranking and reinforcement learning using limited data. Re3val leverages context acquired via Dense Passage Retrieval to rerank the retrieved page titles and utilizes REINFORCE to maximize rewards generated by constrained decoding. Additionally, we generate questions from our pre-training dataset to mitigate epistemic uncertainty and bridge the domain gap between the pre-training and fine-tuning datasets. Subsequently, we extract and rerank contexts from the KILT database using the rerank page titles. Upon grounding the top five reranked contexts, Re3val demonstrates the Top 1 KILT scores compared to all other generative retrieval models across five KILT datasets.