Recognizing Limits: Investigating Infeasibility in Large Language Models
This addresses the issue of LLM hallucinations and reliability for users, but it is incremental as it builds on prior work on infeasibility and fine-tuning.
The paper tackles the problem of large language models (LLMs) incorrectly handling queries beyond their capabilities by developing a dataset to evaluate and improve their ability to refuse infeasible tasks, with experiments showing validated effectiveness.
Large language models (LLMs) have shown remarkable performance in various tasks but often fail to handle queries that exceed their knowledge and capabilities, leading to incorrect or fabricated responses. This paper addresses the need for LLMs to recognize and refuse infeasible tasks due to the requests surpassing their capabilities. We conceptualize four main categories of infeasible tasks for LLMs, which cover a broad spectrum of hallucination-related challenges identified in prior literature. We develop and benchmark a new dataset comprising diverse infeasible and feasible tasks to evaluate multiple LLMs' abilities to decline infeasible tasks. Furthermore, we explore the potential of increasing LLMs' refusal capabilities with fine-tuning. Our experiments validate the effectiveness of the trained models, suggesting promising directions for improving the performance of LLMs in real-world applications.