M Liu: Researcher — Prolific Citations Library

Explore 2 peer-reviewed studies by M Liu in Reinforcement Learning with Human Feedback (RLHF) and Human-AI Interaction (2023–2024). Discover research powered by Prolific's participant panel.

This page lists 2 peer-reviewed papers authored or co-authored by M Liu in the Prolific Citations Library, a curated collection of research powered by high-quality human data from Prolific.

Papers (2 of 2)

Transforming human interactions with AI via reinforcement learning with human feedback (RLHF)

Authors: GKM Liu

Year: 2024

Published in: Massachusetts Institute of Technology, 2023 - computing.mit.edu

Institution: Massachusetts Institute of Technology

Research Area: Reinforcement Learning with Human Feedback (RLHF), Human-AI Interaction

Discipline: Artificial Intelligence

The paper explores Reinforcement Learning with Human Feedback (RLHF) as a transformative tool to align AI with human values, mitigate bias, and democratize technology, while emphasizing its societal implications and ethical considerations.

Methods: The paper employs a systematic study of existing and potential societal effects of RLHF, guided by key questions addressing ethical, social, and practical impacts.

Key Findings: The study investigates how RLHF affects information integrity, societal values, social equity, access to AI, cultural relations, industrial transformation, and labor dynamics.

Citations: 17
Safe RLHF: Safe reinforcement learning from human feedback

Authors: J Dai, X Pan, R Sun, J Ji, X Xu, M Liu, Y Wang

Year: 2023

Published in: arXiv preprint arXiv ..., 2023 - arxiv.org

Institution: Cornell University, Georgia Institute of Technology

Research Area: Reinforcement Learning from Human Feedback (RLHF), Safe AI, Reinforcement Learning

Discipline: Artificial Intelligence, Machine Learning

DOI: https://doi.org/10.48550/arXiv.2310.12773

Citations: 598