Abstract
This paper introduces ReActIn, a framework designed to infuse human feedback into the intermediate prompting steps of large language models. The practicality and effectiveness of ReActIn are validated through experiments that apply four established prompting strategies, evaluated both with and without human feedback integration. The proposed architecture's performance is compared against traditional large language models across various tasks using four standard evaluation tests. Our findings reveal that the integration of human feedback has a direct impact on the reasoning, action prompting, and overall decision-making capabilities of the language models. This study underscores the potential of ReActIn to shape a future where sophisticated, context-aware AI systems, empowered by human feedback, can effectively navigate complex real-world scenarios.
Cite this work
Wangfan Li, Claire Gendron, and Carlos Toxtli-Hernández. 2024. Infusing Human Feedback into Intermediate Prompting Steps of Large Language Models. The 8th International Conference on Applied Cognitive Computing (ACC'24), World Congress in Computer Science, Computer Engineering & Applied Computing (CSCE 2024). Springer Nature, Cham.. https://doi.org/10.1007/978-3-031-85628-0_4
@misc{Li2024Infusing,
doi = {10.13140/RG.2.2.12282.71364},
url = {https://www.researchgate.net/doi/10.13140/RG.2.2.12282.71364},
author = {{Wangfan Li} and Gendron, Claire and Toxtli, Carlos},
language = {en},
title = {Infusing Human Feedback into Intermediate Prompting Steps of Large Language Models},
publisher = {Unpublished},
year = {2024},
howpublished = {Preprint, ResearchGate},
note = {Preprint}
}
