Multi-Step Semantic Reasoning in Generative Retrieval
This addresses a domain-specific limitation for users of generative retrieval in financial or numerical data, but it is incremental as it builds on existing generative retrieval methods.
The paper tackled the problem of generative retrieval models struggling with complex queries in numerical contexts, such as financial reports, by proposing ReasonGR, a framework that improves retrieval accuracy and consistency on the FinQA dataset.
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.