Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs

Jiefeng Chen, Jinsung Yoon, Sayna Ebrahimi, Sercan Arik, Tomas Pfister, Somesh Jha


Abstract
Large language models (LLMs) have recently shown great advances in a variety of tasks, including natural language understanding and generation. However, their use in high-stakes decision-making scenarios is still limited due to the potential for errors. *Selective prediction* is a technique that can be used to improve the reliability of the LLMs by allowing them to abstain from making predictions when they are unsure of the answer. In this work, we propose a novel framework for adaptation with self-evaluation to improve the selective prediction performance of LLMs. Our framework is based on the idea of using parameter-efficient tuning to adapt the LLM to the specific task at hand while improving its ability to perform self-evaluation. We evaluate our method on a variety of question-answering (QA) datasets and show that it outperforms state-of-the-art selective prediction methods. For example, on the CoQA benchmark, our method improves the AUACC from 91.23% to 92.63% and improves the AUROC from 74.61% to 80.25%.
Anthology ID:
2023.findings-emnlp.345
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5190–5213
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.345
DOI:
10.18653/v1/2023.findings-emnlp.345
Bibkey:
Cite (ACL):
Jiefeng Chen, Jinsung Yoon, Sayna Ebrahimi, Sercan Arik, Tomas Pfister, and Somesh Jha. 2023. Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 5190–5213, Singapore. Association for Computational Linguistics.
Cite (Informal):
Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs (Chen et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.345.pdf
Video:
 https://aclanthology.org/2023.findings-emnlp.345.mp4