# A Step Closer to Comprehensive Answers: Constrained Multi-Stage Question Decomposition with Large Language Models

Source: [A Step Closer to Comprehensive Answers: Constrained Multi-Stage Question Decomposition with Large Language Models](<https://www.sota2.com/research/paper/68fa712e1e209131cea4fc41>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T02:00:40.638Z

Authors: Hejing Cao, Zhenwei An, Jiazhan Feng, Kun Xu, Liwei Chen, Dongyan Zhao

Published: 2023-11-13T17:28:03.000Z

## Abstract

While large language models exhibit remarkable performance in the Question Answering task, they are susceptible to hallucinations. Challenges arise when these models grapple with understanding multi-hop relations in complex questions or lack the necessary knowledge for a comprehensive response. To address this issue, we introduce the "Decompose-and-Query" framework (D&Q). This framework guides the model to think and utilize external knowledge similar to ReAct, while also restricting its thinking to reliable information, effectively mitigating the risk of hallucinations. Experiments confirm the effectiveness of D&Q: On our ChitChatQA dataset, D&Q does not lose to ChatGPT in 67% of cases; on the HotPotQA question-only setting, D&Q achieved an F1 score of 59.6%. Our code is available at https://github.com/alkaidpku/DQ-ToolQA.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2311.07491>)

[PDF](<https://arxiv.org/pdf/2311.07491.pdf>)
