Answering Questions by Meta-Reasoning over Multiple Chains of Thought
This addresses the need for better reasoning and explainability in multi-hop QA systems, though it is an incremental improvement over existing chain-of-thought methods.
The paper tackles the problem of multi-hop question answering by introducing Multi-Chain Reasoning (MCR), which meta-reasons over multiple chains of thought instead of aggregating answers, outperforming baselines on 7 datasets and producing high-quality explanations for human verification.
Modern systems for multi-hop question answering (QA) typically break questions into a sequence of reasoning steps, termed chain-of-thought (CoT), before arriving at a final answer. Often, multiple chains are sampled and aggregated through a voting mechanism over the final answers, but the intermediate steps themselves are discarded. While such approaches improve performance, they do not consider the relations between intermediate steps across chains and do not provide a unified explanation for the predicted answer. We introduce Multi-Chain Reasoning (MCR), an approach which prompts large language models to meta-reason over multiple chains of thought, rather than aggregating their answers. MCR examines different reasoning chains, mixes information between them and selects the most relevant facts in generating an explanation and predicting the answer. MCR outperforms strong baselines on 7 multi-hop QA datasets. Moreover, our analysis reveals that MCR explanations exhibit high quality, enabling humans to verify its answers.