Enhancing Human-AI Collaboration Through Logic-Guided Reasoning

Authors: Chengzhi Cao, Yinghao Fu, Sheng Xu, Ruimao Zhang, Shuang Li

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

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments validate each component of our framework, and results on multiple benchmarks demonstrate that our model outperforms the majority of existing approaches.
Researcher Affiliation Academia 1The Chinese University of Hong Kong (Shenzhen) 2University of Science and Technology of China
Pseudocode Yes Algorithm 1 Adaptive Theory of Mind Collaboration Hierarchical Learning Algorithm
Open Source Code No The paper does not provide any specific links to source code or explicitly state that the code for the described methodology is publicly available.
Open Datasets Yes We provide some implementation details and show ablation studies to evaluate the performance of our framework on the Watch-and-help dataset (Puig et al., 2020) and Hand Me That dataset (Wan et al., 2022).
Dataset Splits No The paper mentions that 'During training, the ground-truth goal of the person is shown to the robot as supervision; during testing, the robot no longer has access to the ground-truth goal' and that tasks were run 'five times using different random seeds.' However, it does not provide explicit training, validation, or test split percentages or exact sample counts for the datasets.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., GPU models, CPU specifications) used to run the experiments.
Software Dependencies No The paper does not specify any software dependencies with version numbers.
Experiment Setup No The paper mentions metrics used and how tasks were run 'five times using different random seeds' and split into 'four levels', but it does not provide specific hyperparameter values (e.g., learning rate, batch size, epochs, optimizer settings) or other detailed training configurations.