RISE: Reasoning Enhancement via Iterative Self-Exploration in Multi-hop Question Answering

TL;DR

RISE is a novel framework that enhances multi-hop question answering by iterative self-exploration, improving reasoning accuracy through question decomposition, evidence retrieval, and self-critique.

Contribution

It introduces a new iterative self-exploration approach that significantly boosts reasoning capabilities in multi-hop question answering models.

Findings

Substantial improvement in reasoning accuracy on multiple benchmarks

Effective evidence integration and logical consistency maintenance

Enhanced model performance through iterative self-improvement

Abstract

Large Language Models (LLMs) excel in many areas but continue to face challenges with complex reasoning tasks, such as Multi-Hop Question Answering (MHQA). MHQA requires integrating evidence from diverse sources while managing intricate logical dependencies, often leads to errors in reasoning. Retrieval-Augmented Generation (RAG), widely employed in MHQA tasks, faces challenges in effectively filtering noisy data and retrieving all necessary evidence, thereby limiting its effectiveness in addressing MHQA challenges. To address these challenges, we propose RISE:Reasoning Enhancement via Iterative Self-Exploration, a novel framework designed to enhance models' reasoning capability through iterative self-exploration. Specifically, RISE involves three key steps in addressing MHQA tasks: question decomposition, retrieve-then-read, and self-critique. By leveraging continuous self-exploration, RISE identifies accurate reasoning paths, iteratively self-improving the model's capability to integrate evidence, maintain logical consistency, and enhance performance in MHQA tasks. Extensive experiments on multiple MHQA benchmarks demonstrate that RISE significantly improves reasoning accuracy and task performance.