# Gumbel Reranking: Differentiable End-to-End Reranker Optimization

arXiv: https://arxiv.org/abs/2502.11116 · HTML: https://mlsanity.com/paper/2502.11116/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation.
- Builds on 37 of its 47 references that are in the map.
- First posted on arXiv 16 Feb 2025.

## Placed in

- Retrieval-augmented generation / [Generation and context integration](https://mlsanity.com/rag/generation-and-context-integration/)

## Builds on (most cited first, 30 of 37)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [Atlas: Few-shot Learning with Retrieval Augmented Language Models](https://mlsanity.com/paper/2208.03299/) (2022)
- [REPLUG: Retrieval-Augmented Black-Box Language Models](https://mlsanity.com/paper/2301.12652/) (2023)
- [Latent Retrieval for Weakly Supervised Open Domain Question Answering](https://mlsanity.com/paper/1906.00300/) (2019)
- [Learning to Explain: An Information-Theoretic Perspective on Model Interpretation](https://mlsanity.com/paper/1802.07814/) (2018)
- [Distilling Knowledge from Reader to Retriever for Question Answering](https://mlsanity.com/paper/2012.04584/) (2020)
- [RA-DIT: Retrieval-Augmented Dual Instruction Tuning](https://mlsanity.com/paper/2310.01352/) (2023)
- [Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering](https://mlsanity.com/paper/2101.00774/) (2021)
- [Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval](https://mlsanity.com/paper/2009.12756/) (2020)
- [Modeling Point Clouds with Self-Attention and Gumbel Subset Sampling](https://mlsanity.com/paper/1904.03375/) (2019)
- [End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering](https://mlsanity.com/paper/2106.05346/) (2021)
- [RankT5: Fine-Tuning T5 for Text Ranking with Ranking Losses](https://mlsanity.com/paper/2210.10634/) (2022)
- [Long-Context Language Modeling with Parallel Context Encoding](https://mlsanity.com/paper/2402.16617/) (2024)
- [Reparameterizable Subset Sampling via Continuous Relaxations](https://mlsanity.com/paper/1901.10517/) (2019)
- [Bridging the Preference Gap between Retrievers and LLMs](https://mlsanity.com/paper/2401.06954/) (2024)
- [FiD-Light: Efficient and Effective Retrieval-Augmented Text Generation](https://mlsanity.com/paper/2209.14290/) (2022)
- [Select, Answer and Explain: Interpretable Multi-hop Reading Comprehension over Multiple Documents](https://mlsanity.com/paper/1911.00484/) (2019)
- [Don't Forget to Connect! Improving RAG with Graph-based Reranking](https://mlsanity.com/paper/2405.18414/) (2024)
- [Questions Are All You Need to Train a Dense Passage Retriever](https://mlsanity.com/paper/2206.10658/) (2022)
- [Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2112.08688/) (2021)
- [End-to-End Beam Retrieval for Multi-Hop Question Answering](https://mlsanity.com/paper/2308.08973/) (2023)

## Built on by (most cited first, 2 of 2)

- [CLaRa: Bridging Retrieval and Generation with Continuous Latent Reasoning](https://mlsanity.com/paper/2511.18659/) (2025)
- [MiRAGE: Misconception Detection with Retrieval-Guided Multi-Stage Reasoning and Ensemble Fusion](https://mlsanity.com/paper/2511.01182/) (2025)

## Abstract (arXiv)

RAG systems rely on rerankers to identify relevant documents. However, fine-tuning these models remains challenging due to the scarcity of annotated query-document pairs. Existing distillation-based approaches suffer from training-inference misalignment and fail to capture interdependencies among candidate documents. To overcome these limitations, we reframe the reranking process as an attention-mask problem and propose Gumbel Reranking, an end-to-end training framework for rerankers aimed at minimizing the training-inference gap. In our approach, reranker optimization is reformulated as learning a stochastic, document-wise Top-k attention mask using the Gumbel Trick and Relaxed Top-k Sampling. This formulation enables end-to-end optimization by minimizing the overall language loss. Experiments across various settings consistently demonstrate performance gains, including a 10.4% improvement in recall on HotpotQA for distinguishing indirectly relevant documents.