Enhancing Fault Detection for Large Language Models via Mutation-Based Confidence Smoothing

arXiv:2404.14419v1 Announce Type: cross
Abstract: Large language models (LLMs) achieved great success in multiple application domains and attracted huge attention from different research communities recently. Unfortunately, even for the best LLM, there still exist many faults that LLM cannot correctly predict. Such faults will harm the usability of LLMs. How to quickly reveal them in LLMs is important, but challenging. The reasons are twofold, 1) the heavy labeling effort for preparing the test data, and 2) accessing closed-source LLMs such …

abstract application arxiv attention communities confidence cs.cl cs.lg cs.se detection domains harm language language models large language large language models llm llms multiple mutation research success type usability via will