PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documents
Simeng Sun, Yang Liu, Shuohang Wang, Dan Iter, Chenguang Zhu, Mohit Iyyer
Abstract
Strategies such as chain-of-thought prompting improve the performance of large language models (LLMs) on complex reasoning tasks by decomposing input examples into intermediate steps. However, it remains unclear how to apply such methods to reason over long input documents, in which both the decomposition and the output of each intermediate step are non-trivial to obtain. In this work, we propose PEARL, a prompting framework to improve reasoning over long documents, which consists of three stages: action mining, plan formulation, and plan execution. More specifically, given a question about a long document, PEARL decomposes the question into a sequence of actions (e.g., SUMMARIZE, FIND_EVENT, FIND_RELATION) and then executes them over the document to obtain the answer. Each stage of PEARL is implemented via zero-shot or few-shot prompting of LLMs (in our work, GPT-4) with minimal human input. We evaluate PEARL on a challenging subset of the QuALITY dataset, which contains questions that require complex reasoning over long narrative texts. PEARL outperforms zero-shot and chain-of-thought prompting on this dataset, and ablation experiments show that each stage of PEARL is critical to its performance. Overall, PEARL is a first step towards leveraging LLMs to reason over long documents.- Anthology ID:
- 2024.eacl-long.29
- Volume:
- Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- March
- Year:
- 2024
- Address:
- St. Julian’s, Malta
- Editors:
- Yvette Graham, Matthew Purver
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 469–486
- Language:
- URL:
- https://aclanthology.org/2024.eacl-long.29
- DOI:
- Cite (ACL):
- Simeng Sun, Yang Liu, Shuohang Wang, Dan Iter, Chenguang Zhu, and Mohit Iyyer. 2024. PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documents. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 469–486, St. Julian’s, Malta. Association for Computational Linguistics.
- Cite (Informal):
- PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documents (Sun et al., EACL 2024)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2024.eacl-long.29.pdf