# Structures Facilitate Retrieve, Rerank, and Generate

arXiv: https://arxiv.org/abs/2606.03247 · HTML: https://mlsanity.com/paper/2606.03247/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 30 references that are in the map.
- First posted on arXiv 2 Jun 2026.

## Builds on (most cited first, 20 of 20)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [Passage Re-ranking with BERT](https://mlsanity.com/paper/1901.04085/) (2019)
- [A Knowledge-Grounded Neural Conversation Model](https://mlsanity.com/paper/1702.01932/) (2017)
- [Re2G: Retrieve, Rerank, Generate](https://mlsanity.com/paper/2207.06300/) (2022)
- [doc2dial: A Goal-Oriented Document-Grounded Dialogue Dataset](https://mlsanity.com/paper/2011.06623/) (2020)
- [Low-Resource Knowledge-Grounded Dialogue Generation](https://mlsanity.com/paper/2002.10348/) (2020)
- [MultiDoc2Dial: Modeling Dialogues Grounded in Multiple Documents](https://mlsanity.com/paper/2109.12595/) (2021)
- [Incremental Transformer with Deliberation Decoder for Document Grounded Conversations](https://mlsanity.com/paper/1907.08854/) (2019)
- [RefNet: A Reference-aware Network for Background Based Conversation](https://mlsanity.com/paper/1908.06449/) (2019)
- [RetGen: A Joint framework for Retrieval and Grounded Text Generation Modeling](https://mlsanity.com/paper/2105.06597/) (2021)
- [FiD-Ex: Improving Sequence-to-Sequence Models for Extractive Rationale Generation](https://mlsanity.com/paper/2012.15482/) (2020)
- [Incorporating Explicit Knowledge in Pre-trained Language Models for Passage Re-ranking](https://mlsanity.com/paper/2204.11673/) (2022)
- [UniGDD: A Unified Generative Framework for Goal-Oriented Document-Grounded Dialogue](https://mlsanity.com/paper/2204.07770/) (2022)
- [Towards Unification of Discourse Annotation Frameworks](https://mlsanity.com/paper/2204.07781/) (2022)
- [Improving Conditioning in Context-Aware Sequence to Sequence Models](https://mlsanity.com/paper/1911.09728/) (2019)
- [Unstructured Text Enhanced Open-domain Dialogue System: A Systematic Survey](https://mlsanity.com/paper/2411.09166/) (2024)

## Abstract (arXiv)

Document-grounded dialogue systems (DGDS) utilize knowledge from external documents to answer domain-specific user questions. Existing solutions typically divide documents into independent passages for retrieval and response generation. This approach, however, neither makes good use of structural information within documents nor provides enough (document) context for knowledge selection and responses. This paper proposes SF-Re2G to address such issues systematically. Firstly, we seek to improve a passage representation by contrasting it with others of the same section, thus improving the retrieval performance. Secondly, a structure-enhanced reranker is built, leveraging the fact that multiple grounding passages of one dialog turn tend to be in the same neighborhood. Specifically, candidates from the retrieval are grouped into subgraphs according to the document structure. The reranker will rescore the candidate integrating its group information. Finally, the chosen passages are used for responses, taking into account the subgraph context for better generation. Experimental results on two DGDS datasets validate our method for both Chinese and English.