Abstract
Large language models (LLMs) have achieved satisfactory performance in counterfactual generation. However, confined by the stochastic generation process of LLMs, there often are misalignments between LLMs and humans which hinder LLMs from handling complex tasks like relation extraction. As a result, LLMs may generate commonsense-violated counterfactuals like ‘eggs were produced by a box’. To bridge this gap, we propose to mimick the episodic memory retrieval, the working mechanism of human hippocampus, to align LLMs’ generation process with that of humans. In this way, LLMs can derive experience from their extensive memory, which keeps in line with the way humans gain commonsense. We then implement two central functions in the hippocampus, i.e., pattern separation and pattern completion, to retrieve the episodic memory from LLMs and generate commonsense counterfactuals for relation extraction. Experimental results demonstrate the improvements of our framework over existing methods in terms of the quality of counterfactuals.- Anthology ID:
- 2024.findings-acl.146
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2024
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand
- Editors:
- Lun-Wei Ku, Andre Martins, Vivek Srikumar
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2489–2511
- Language:
- URL:
- https://aclanthology.org/2024.findings-acl.146
- DOI:
- 10.18653/v1/2024.findings-acl.146
- Cite (ACL):
- Xin Miao, Yongqi Li, Shen Zhou, and Tieyun Qian. 2024. Episodic Memory Retrieval from LLMs: A Neuromorphic Mechanism to Generate Commonsense Counterfactuals for Relation Extraction. In Findings of the Association for Computational Linguistics: ACL 2024, pages 2489–2511, Bangkok, Thailand. Association for Computational Linguistics.
- Cite (Informal):
- Episodic Memory Retrieval from LLMs: A Neuromorphic Mechanism to Generate Commonsense Counterfactuals for Relation Extraction (Miao et al., Findings 2024)
- PDF:
- https://preview.aclanthology.org/autopr/2024.findings-acl.146.pdf