LLM-Driven Personalized Answer Generation and Evaluation

TL;DR

This paper investigates the use of Large Language Models to generate personalized answers for online learners, evaluating their effectiveness across language learning and programming domains with various strategies and assessment methods.

Contribution

It introduces a framework and dataset for validating personalized answers generated by LLMs, demonstrating how example-based prompting improves response customization.

Findings

Example-based prompts significantly improve personalization.

LLMs can effectively tailor answers in language learning and programming.

Multiple evaluation methods confirm the quality of generated answers.

Abstract

Online learning has experienced rapid growth due to its flexibility and accessibility. Personalization, adapted to the needs of individual learners, is crucial for enhancing the learning experience, particularly in online settings. A key aspect of personalization is providing learners with answers customized to their specific questions. This paper therefore explores the potential of Large Language Models (LLMs) to generate personalized answers to learners' questions, thereby enhancing engagement and reducing the workload on educators. To evaluate the effectiveness of LLMs in this context, we conducted a comprehensive study using the StackExchange platform in two distinct areas: language learning and programming. We developed a framework and a dataset for validating automatically generated personalized answers. Subsequently, we generated personalized answers using different strategies, including 0-shot, 1-shot, and few-shot scenarios. The generated answers were evaluated using three methods: 1. BERTScore, 2. LLM evaluation, and 3. human evaluation. Our findings indicated that providing LLMs with examples of desired answers (from the learner or similar learners) can significantly enhance the LLMs' ability to tailor responses to individual learners' needs.