Do Large Language Models Know How Much They Know?

Gabriele Prato, Jerry Huang, Prasanna Parthasarathi, Shagun Sodhani, Sarath Chandar


Abstract
Large Language Models (LLMs) have emerged as highly capable systems and are increasingly being integrated into various uses. Nevertheless, the rapid advancement in their deployment trails a comprehensive understanding of their internal mechanisms, as well as a delineation of their capabilities and limitations. A desired characteristic of an intelligent system is its ability to recognize the scope of its own knowledge. To investigate whether LLMs embody this attribute, we develop a benchmark that challenges these models to enumerate all information they possess on specific topics. This benchmark assesses whether the models recall excessive, insufficient, or the precise amount of required information, thereby indicating their awareness of how much they know about the given topic. Our findings reveal that the emergence of this property varies across different architectures and manifests at diverse rates. However, with sufficient scaling, all tested models are ultimately capable of performing this task. The insights gained from this research advance our understanding of LLMs, shedding light on their operational capabilities and contributing to the ongoing exploration of their intricate dynamics.
Anthology ID:
2024.emnlp-main.348
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6054–6070
Language:
URL:
https://aclanthology.org/2024.emnlp-main.348/
DOI:
10.18653/v1/2024.emnlp-main.348
Bibkey:
Cite (ACL):
Gabriele Prato, Jerry Huang, Prasanna Parthasarathi, Shagun Sodhani, and Sarath Chandar. 2024. Do Large Language Models Know How Much They Know?. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 6054–6070, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Do Large Language Models Know How Much They Know? (Prato et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.348.pdf