Learn to Refuse: Making Large Language Models More Controllable and Reliable through Knowledge Scope Limitation and Refusal Mechanism

arXiv:2311.01041v2 Announce Type: replace
Abstract: Large language models (LLMs) have demonstrated impressive language understanding and generation capabilities, enabling them to answer a wide range of questions across various domains. However, these models are not flawless and often produce responses that contain errors or misinformation. These inaccuracies, commonly referred to as hallucinations, render LLMs unreliable and even unusable in many scenarios. In this paper, our focus is on mitigating the issue of hallucination in LLMs, particularly in the context of question-answering. …

abstract arxiv capabilities cs.ai cs.cl domains enabling errors however knowledge language language models language understanding large language large language models learn llms making questions responses them through type understanding