Structures Facilitate Retrieve, Rerank, and Generate

arXiv cs.CL Papers

Summary

The paper proposes SF-Re2G, a method that improves document-grounded dialogue systems by leveraging document structure to enhance retrieval, reranking, and generation. It validates on Chinese and English datasets.

arXiv:2606.03247v1 Announce Type: new Abstract: 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.
Original Article
View Cached Full Text

Cached at: 06/03/26, 09:38 AM

# Structures Facilitate Retrieve, Rerank, and Generate
Source: [https://arxiv.org/abs/2606.03247](https://arxiv.org/abs/2606.03247)
[View PDF](https://arxiv.org/pdf/2606.03247)

> Abstract: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\.

## Submission history

From: Xujie Zhang \[[view email](https://arxiv.org/show-email/1a0e14e6/2606.03247)\] **\[v1\]**Tue, 2 Jun 2026 07:09:41 UTC \(8,382 KB\)

Similar Articles

Fine-grained Fragment Retrieval in Multi-modal Long-form Dialogues

arXiv cs.CL

This paper introduces Fine-grained Fragment Retrieval (FFR), a new task for locating semantically coherent multi-modal fragments (text and images) within long-form dialogues. The authors propose F2RVLM, a generation-based retrieval model trained with reinforcement learning, and FFRS, a two-stage retrieval system, along with a new dataset MLDR for evaluation.

Disco-RAG: Discourse-Aware Retrieval-Augmented Generation

arXiv cs.CL

Disco-RAG proposes a discourse-aware retrieval-augmented generation framework that integrates discourse signals through intra-chunk discourse trees and inter-chunk rhetorical graphs to improve knowledge synthesis in LLMs. The method achieves state-of-the-art results on QA and summarization benchmarks without fine-tuning.