@inproceedings{miao-etal-2024-episodic,
title = "Episodic Memory Retrieval from {LLM}s: A Neuromorphic Mechanism to Generate Commonsense Counterfactuals for Relation Extraction",
author = "Miao, Xin and
Li, Yongqi and
Zhou, Shen and
Qian, Tieyun",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.146/",
doi = "10.18653/v1/2024.findings-acl.146",
pages = "2489--2511",
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 {\textquoteleft}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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="miao-etal-2024-episodic">
<titleInfo>
<title>Episodic Memory Retrieval from LLMs: A Neuromorphic Mechanism to Generate Commonsense Counterfactuals for Relation Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Miao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongqi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shen</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tieyun</namePart>
<namePart type="family">Qian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">miao-etal-2024-episodic</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.146</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.146/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>2489</start>
<end>2511</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Episodic Memory Retrieval from LLMs: A Neuromorphic Mechanism to Generate Commonsense Counterfactuals for Relation Extraction
%A Miao, Xin
%A Li, Yongqi
%A Zhou, Shen
%A Qian, Tieyun
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F miao-etal-2024-episodic
%X 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.
%R 10.18653/v1/2024.findings-acl.146
%U https://aclanthology.org/2024.findings-acl.146/
%U https://doi.org/10.18653/v1/2024.findings-acl.146
%P 2489-2511
Markdown (Informal)
[Episodic Memory Retrieval from LLMs: A Neuromorphic Mechanism to Generate Commonsense Counterfactuals for Relation Extraction](https://aclanthology.org/2024.findings-acl.146/) (Miao et al., Findings 2024)
ACL