The Challenges of Evaluating LLM Applications: An Analysis of Automated, Human, and LLM-Based Approaches
This work addresses the challenge of effectively evaluating domain-specific chatbots, such as in medicine and psychology, which is critical for ensuring reliability in non-retrieval applications.
The paper tackles the problem of evaluating LLM applications by analyzing automated, human, and LLM-based approaches, and introduces a factored evaluation mechanism that provides better insights into aspects needing improvement, as shown in an experimental evaluation with a chatbot consuming educational reports.
Chatbots have been an interesting application of natural language generation since its inception. With novel transformer based Generative AI methods, building chatbots have become trivial. Chatbots which are targeted at specific domains for example medicine and psychology are implemented rapidly. This however, should not distract from the need to evaluate the chatbot responses. Especially because the natural language generation community does not entirely agree upon how to effectively evaluate such applications. With this work we discuss the issue further with the increasingly popular LLM based evaluations and how they correlate with human evaluations. Additionally, we introduce a comprehensive factored evaluation mechanism that can be utilized in conjunction with both human and LLM-based evaluations. We present the results of an experimental evaluation conducted using this scheme in one of our chatbot implementations which consumed educational reports, and subsequently compare automated, traditional human evaluation, factored human evaluation, and factored LLM evaluation. Results show that factor based evaluation produces better insights on which aspects need to be improved in LLM applications and further strengthens the argument to use human evaluation in critical spaces where main functionality is not direct retrieval.