Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Multi-Step Semantic Reasoning in Generative Retrieval

Steven Dong, Yubao Tang, Maarten de Rijke

Abstract

Generative retrieval (GR) models encode a corpus within model parameters and generate relevant document identifiers directly for a given query. While this paradigm shows promise in retrieval tasks, existing GR models struggle with complex queries in numerical contexts, such as those involving semantic reasoning over financial reports, due to limited reasoning capabilities. This limitation leads to suboptimal retrieval accuracy and hinders practical applicability. We propose ReasonGR, a framework designed to enhance multi-step semantic reasoning in numerical contexts within GR. ReasonGR employs a structured prompting strategy combining task-specific instructions with stepwise reasoning guidance to better address complex retrieval queries. Additionally, it integrates a reasoning-focused adaptation module to improve the learning of reasoning-related parameters. Experiments on the FinQA dataset, which contains financial queries over complex documents, demonstrate that ReasonGR improves retrieval accuracy and consistency, indicating its potential for advancing GR models in reasoning-intensive retrieval scenarios.

Multi-Step Semantic Reasoning in Generative Retrieval

Abstract

Generative retrieval (GR) models encode a corpus within model parameters and generate relevant document identifiers directly for a given query. While this paradigm shows promise in retrieval tasks, existing GR models struggle with complex queries in numerical contexts, such as those involving semantic reasoning over financial reports, due to limited reasoning capabilities. This limitation leads to suboptimal retrieval accuracy and hinders practical applicability. We propose ReasonGR, a framework designed to enhance multi-step semantic reasoning in numerical contexts within GR. ReasonGR employs a structured prompting strategy combining task-specific instructions with stepwise reasoning guidance to better address complex retrieval queries. Additionally, it integrates a reasoning-focused adaptation module to improve the learning of reasoning-related parameters. Experiments on the FinQA dataset, which contains financial queries over complex documents, demonstrate that ReasonGR improves retrieval accuracy and consistency, indicating its potential for advancing GR models in reasoning-intensive retrieval scenarios.
Paper Structure (22 sections, 1 figure, 2 tables)

This paper contains 22 sections, 1 figure, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methodology
  4. Task definition
  5. Model architecture
  6. Reasoning-guided training framework
  7. Reasoning-enhanced prompting
  8. Training tasks
  9. Adaptive penalty scaling loss
  10. Experimental Setup
  11. Dataset and metrics
  12. Model variants
  13. Implementation details
  14. Experimental Results
  15. Main results
  16. ...and 7 more sections

Figures (1)

  • Figure 1: ReasonGR performing multi-step semantic reasoning on a FinQA query. The model extracts key info and locates relevant report sections to generate the docid, formed by the company name and report year.