Retrieve-Plan-Generation: An Iterative Planning and Answering Framework for Knowledge-Intensive LLM Generation

Yuanjie Lyu, Zihan Niu, Zheyong Xie, Chao Zhang, Tong Xu, Yang Wang, Enhong Chen


Abstract
Despite the significant progress of large language models (LLMs) in various tasks, they often produce factual errors due to their limited internal knowledge. Retrieval-Augmented Generation (RAG), which enhances LLMs with external knowledge sources, offers a promising solution. However, these methods can be misled by irrelevant paragraphs in retrieved documents. Due to the inherent uncertainty in LLM generation, inputting the entire document may introduce off-topic information, causing the model to deviate from the central topic and affecting the relevance of the generated content. To address these issues, we propose the Retrieve-Plan-Generation (RPG) framework. RPG generates plan tokens to guide subsequent generation in the plan stage. In the answer stage, the model selects relevant fine-grained paragraphs based on the plan and uses them for further answer generation. This plan-answer process is repeated iteratively until completion, enhancing generation relevance by focusing on specific topics. To implement this framework efficiently, we utilize a simple but effective multi-task prompt-tuning method, enabling the existing LLMs to handle both planning and answering. We comprehensively compare RPG with baselines across 5 knowledge-intensive generation tasks, demonstrating the effectiveness of our approach.
Anthology ID:
2024.emnlp-main.270
Original:
2024.emnlp-main.270v1
Version 2:
2024.emnlp-main.270v2
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4683–4702
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.emnlp-main.270/
DOI:
10.18653/v1/2024.emnlp-main.270
Bibkey:
Cite (ACL):
Yuanjie Lyu, Zihan Niu, Zheyong Xie, Chao Zhang, Tong Xu, Yang Wang, and Enhong Chen. 2024. Retrieve-Plan-Generation: An Iterative Planning and Answering Framework for Knowledge-Intensive LLM Generation. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 4683–4702, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Retrieve-Plan-Generation: An Iterative Planning and Answering Framework for Knowledge-Intensive LLM Generation (Lyu et al., EMNLP 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.emnlp-main.270.pdf