Multi-Step Semantic Reasoning in Generative Retrieval

TL;DR

ReasonGR is a novel framework that enhances multi-step semantic reasoning in generative retrieval models, significantly improving accuracy on complex financial queries by combining structured prompting and reasoning-focused adaptation.

Contribution

It introduces ReasonGR, a new approach that combines structured prompting and adaptation modules to improve reasoning capabilities in generative retrieval models.

Findings

ReasonGR outperforms baseline models on the FinQA dataset.

Enhanced reasoning leads to higher retrieval accuracy and consistency.

Framework demonstrates potential for reasoning-intensive retrieval tasks.

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.