TY - GEN
T1 - ZARA
T2 - 2023 Findings of the Association for Computational Linguistics: EMNLP 2023
AU - Chen, Wei Lin
AU - Yen, An Zi
AU - Wu, Cheng Kuang
AU - Huang, Hen Hsen
AU - Chen, Hsin Hsi
N1 - Publisher Copyright:
© 2023 Association for Computational Linguistics.
PY - 2023
Y1 - 2023
N2 - Language models (LMs) that jointly generate end-task answers as well as free-text rationales are known as self-rationalization models. Recent works demonstrate great performance gain for self-rationalization by few-shot prompting LMs with rationale-augmented exemplars. However, the ability to benefit from explanations only emerges with large-scale LMs, which have poor accessibility. In this work, we explore the less-studied setting of leveraging explanations for small LMs to improve few-shot self-rationalization. We first revisit the relationship between rationales and answers. Inspired by the implicit mental process of how human beings assess explanations, we present a novel approach, Zero-shot Augmentation of Rationale-Answer pairs (ZARA), to automatically construct pseudo-parallel data for self-training by reducing the problem of plausibility judgement to natural language inference. Experimental results show ZARA achieves SOTA performance on the FEB benchmark, for both the task accuracy and the explanation metric. In addition, we conduct human and quantitative evaluation validating ZARA's ability to automatically identify plausible and accurate rationale-answer pairs.
AB - Language models (LMs) that jointly generate end-task answers as well as free-text rationales are known as self-rationalization models. Recent works demonstrate great performance gain for self-rationalization by few-shot prompting LMs with rationale-augmented exemplars. However, the ability to benefit from explanations only emerges with large-scale LMs, which have poor accessibility. In this work, we explore the less-studied setting of leveraging explanations for small LMs to improve few-shot self-rationalization. We first revisit the relationship between rationales and answers. Inspired by the implicit mental process of how human beings assess explanations, we present a novel approach, Zero-shot Augmentation of Rationale-Answer pairs (ZARA), to automatically construct pseudo-parallel data for self-training by reducing the problem of plausibility judgement to natural language inference. Experimental results show ZARA achieves SOTA performance on the FEB benchmark, for both the task accuracy and the explanation metric. In addition, we conduct human and quantitative evaluation validating ZARA's ability to automatically identify plausible and accurate rationale-answer pairs.
UR - http://www.scopus.com/inward/record.url?scp=85183310366&partnerID=8YFLogxK
U2 - 10.18653/v1/2023.findings-emnlp.310
DO - 10.18653/v1/2023.findings-emnlp.310
M3 - Conference contribution
AN - SCOPUS:85183310366
T3 - Findings of the Association for Computational Linguistics: EMNLP 2023
SP - 4682
EP - 4693
BT - Findings of the Association for Computational Linguistics
PB - Association for Computational Linguistics (ACL)
Y2 - 6 December 2023 through 10 December 2023
ER -