Enhancing Relation Extraction via Supervised Rationale Verification and Feedback

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Li, Yongqi, Miao, Xin, Zhou, Shen, Xu, Mayi, Ren, Yuyang, Qian, Tieyun
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909424253140992
author Li, Yongqi
Miao, Xin
Zhou, Shen
Xu, Mayi
Ren, Yuyang
Qian, Tieyun
author_facet Li, Yongqi
Miao, Xin
Zhou, Shen
Xu, Mayi
Ren, Yuyang
Qian, Tieyun
contents Despite the rapid progress that existing automated feedback methods have made in correcting the output of large language models (LLMs), these methods cannot be well applied to the relation extraction (RE) task due to their designated feedback objectives and correction manner. To address this problem, we propose a novel automated feedback framework for RE, which presents a rationale supervisor to verify the rationale and provides re-selected demonstrations as feedback to correct the initial prediction. Specifically, we first design a causal intervention and observation method to collect biased/unbiased rationales for contrastive training the rationale supervisor. Then, we present a verification-feedback-correction procedure to iteratively enhance LLMs' capability of handling the RE task. Extensive experiments prove that our proposed framework significantly outperforms existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2412_07289
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enhancing Relation Extraction via Supervised Rationale Verification and Feedback
Li, Yongqi
Miao, Xin
Zhou, Shen
Xu, Mayi
Ren, Yuyang
Qian, Tieyun
Computation and Language
Artificial Intelligence
Despite the rapid progress that existing automated feedback methods have made in correcting the output of large language models (LLMs), these methods cannot be well applied to the relation extraction (RE) task due to their designated feedback objectives and correction manner. To address this problem, we propose a novel automated feedback framework for RE, which presents a rationale supervisor to verify the rationale and provides re-selected demonstrations as feedback to correct the initial prediction. Specifically, we first design a causal intervention and observation method to collect biased/unbiased rationales for contrastive training the rationale supervisor. Then, we present a verification-feedback-correction procedure to iteratively enhance LLMs' capability of handling the RE task. Extensive experiments prove that our proposed framework significantly outperforms existing methods.
title Enhancing Relation Extraction via Supervised Rationale Verification and Feedback
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2412.07289