Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs
This work addresses the need for more reliable LLMs in high-stakes decision-making by improving selective prediction, though it is incremental as it builds on existing selective prediction methods.
The paper tackles the problem of improving selective prediction in large language models (LLMs) to enhance reliability in high-stakes scenarios, proposing a framework that uses parameter-efficient tuning for adaptation and self-evaluation, resulting in performance gains such as increasing AUACC from 91.23% to 92.63% and AUROC from 74.61% to 80.25% on the CoQA benchmark.
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%.