Enhancing Retrieval Systems with Inference-Time Logical Reasoning
This addresses a specific limitation in retrieval systems for users dealing with complex queries, though it appears incremental as it builds on existing similarity-based methods.
The paper tackled the problem of traditional retrieval methods failing to handle complex queries with logical constructs like negations and conjunctions, and proposed an inference-time logical reasoning framework that improves retrieval performance for such queries, with results showing consistent outperformance across models and datasets.
Traditional retrieval methods rely on transforming user queries into vector representations and retrieving documents based on cosine similarity within an embedding space. While efficient and scalable, this approach often fails to handle complex queries involving logical constructs such as negations, conjunctions, and disjunctions. In this paper, we propose a novel inference-time logical reasoning framework that explicitly incorporates logical reasoning into the retrieval process. Our method extracts logical reasoning structures from natural language queries and then composes the individual cosine similarity scores to formulate the final document scores. This approach enables the retrieval process to handle complex logical reasoning without compromising computational efficiency. Our results on both synthetic and real-world benchmarks demonstrate that the proposed method consistently outperforms traditional retrieval methods across different models and datasets, significantly improving retrieval performance for complex queries.