Towards Understanding Factual Knowledge of Large Language Models

Authors: Xuming Hu, Junzhe Chen, Xiaochuan Li, Yufei Guo, Lijie Wen, Philip S. Yu, Zhijiang Guo

ICLR 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on different sizes and types of LLMs show that existing LLMs still lack factual knowledge and suffer from various spurious correlations.
Researcher Affiliation Academia 1 Tsinghua University 2 The Hong Kong University of Science and Technology (Guangzhou) 3 University of Illinois at Chicago 4 University of Cambridge
Pseudocode No The paper describes methods in text but does not include any clearly labeled 'Pseudocode' or 'Algorithm' blocks.
Open Source Code Yes The dataset Pinocchio and our codes are publicly available at: https://github.com/THU-BPM/Pinocchio.
Open Datasets Yes The dataset Pinocchio and our codes are publicly available at: https://github.com/THU-BPM/Pinocchio.
Dataset Splits No The paper describes the Pinocchio dataset and its subsets but does not explicitly state specific training/validation/test dataset splits (e.g., percentages or counts) within the main text.
Hardware Specification No The paper does not explicitly describe the specific hardware used for running its experiments, such as GPU or CPU models.
Software Dependencies No The paper does not provide specific software dependencies, such as library names with version numbers, used to replicate the experiments.
Experiment Setup No While the paper describes various prompt strategies used in experiments, it does not provide specific experimental setup details such as hyperparameter values (e.g., learning rate, batch size) or detailed system-level training settings.