Knowledge Boundary Discovery for Large Language Models

Ziquan Wang; Zhongqi Lu

AAAI 2026technical0 citations

Knowledge Boundary Discovery for Large Language Models

Abstract

We propose Knowledge Boundary Discovery (KBD), a reinforcement learning based framework to explore the knowledge boundaries of the Large Language Models (LLMs). We define the knowledge boundary by automatically generating two types of questions: (i) those the LLM can confidently answer within-knowledge boundary and (ii) those it cannot beyond-knowledge boundary. Iteratively exploring and exploiting the LLM

BibTeX

@inproceedings{aaai2026_knowledgeboundar,
  title = {Knowledge Boundary Discovery for Large Language Models},
  author = {Ziquan Wang and Zhongqi Lu},
  booktitle = {AAAI 2026},
  year = {2026}
}