HalluciBot: Is There No Such Thing as a Bad Question?

arXiv:2404.12535v1 Announce Type: new
Abstract: Hallucination continues to be one of the most critical challenges in the institutional adoption journey of Large Language Models (LLMs). In this context, an overwhelming number of studies have focused on analyzing the post-generation phase - refining outputs via feedback, analyzing logit output values, or deriving clues via the outputs' artifacts. We propose HalluciBot, a model that predicts the probability of hallucination $\textbf{before generation}$, for any query imposed to an LLM. In essence, HalluciBot does …

abstract adoption arxiv challenges context cs.ai cs.cl cs.lg feedback hallucination journey language language models large language large language models llms question studies type values via