Enhancing Large Language Model Performance To Answer Questions and Extract Information More Accurately
This addresses accuracy issues in LLMs for question-answering and information extraction, primarily in financial domains, but is incremental as it builds on existing fine-tuning and RAG methods.
The paper tackled the problem of sub-optimal answer quality and inaccuracies in large language models (LLMs) by employing fine-tuning with feedback loops, showing that fine-tuned models surpass zero-shot LLMs in accuracy, particularly when combined with Retrieval Augmented Generation (RAG).
Large Language Models (LLMs) generate responses to questions; however, their effectiveness is often hindered by sub-optimal quality of answers and occasional failures to provide accurate responses to questions. To address these challenges, a fine-tuning process is employed, involving feedback and examples to refine models. The objective is to enhance AI models through continuous feedback loops, utilizing metrics such as cosine similarity, LLM evaluation and Rouge-L scores to evaluate the models. Leveraging LLMs like GPT-3.5, GPT4ALL, and LLaMA2, and Claude, this approach is benchmarked on financial datasets, including the FinanceBench and RAG Instruct Benchmark Tester Dataset, illustrating the necessity of fine-tuning. The results showcase the capability of fine-tuned models to surpass the accuracy of zero-shot LLMs, providing superior question and answering capabilities. Notably, the combination of fine-tuning the LLM with a process known as Retrieval Augmented Generation (RAG) proves to generate responses with improved accuracy.