How Knowledge Popularity Influences and Enhances LLM Knowledge Boundary Perception
This work addresses the problem of LLMs producing confident but incorrect answers by enhancing knowledge boundary perception, offering an incremental improvement through confidence calibration based on popularity signals.
The study investigated how knowledge popularity affects large language models' ability to perceive their knowledge boundaries in entity-centric factual question answering, finding that models perform better and are more confident on popular knowledge, with relation popularity showing the strongest correlation. By leveraging popularity signals for confidence calibration, the method improved answer correctness prediction accuracy by an average of 5.24% across models and datasets.
Large language models (LLMs) often fail to recognize their knowledge boundaries, producing confident yet incorrect answers. In this paper, we investigate how knowledge popularity affects LLMs' ability to perceive their knowledge boundaries. Focusing on entity-centric factual question answering (QA), we quantify knowledge popularity from three perspectives: the popularity of entities in the question, the popularity of entities in the answer, and relation popularity, defined as their co-occurrence frequency. Experiments on three representative datasets containing knowledge with varying popularity show that LLMs exhibit better QA performance, higher confidence, and more accurate perception on more popular knowledge, with relation popularity having the strongest correlation. Cause knowledge popularity shows strong correlation with LLMs' QA performance, we propose to leverage these signals for confidence calibration. This improves the accuracy of answer correctness prediction by an average of 5.24% across all models and datasets. Furthermore, we explore prompting LLMs to estimate popularity without external corpora, which yields a viable alternative.