Article

Reinforcement Learning from Brain Feedback (RLbF) for Large Language Model (LLM) Improvement: Using and Evaluating Real-Time Neurophysiological Reward Signals for System Adaptation

2026-08-19

Abstract excerpt

Large Language Models (LLMs) aligned using Reinforcement Learning from Human Feedback(RLHF) are learning what to say from discrete, voluntary preference judgments, but not how their communication lands. The LLM does not know how different answers affect a listener’s cognition and emotion in real time, regardless of how intelligent the model is on benchmark tests. This becomes a major gap in developing trust progra...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 66ff93fe-e0e9-58fd-b9a0-643ec82f0d3c
DOI: 10.20944/preprints202608.1274.v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Reinforcement Learning from Brain Feedback (RLbF) for Large Language Model (LLM) Improvement: Using and Evaluating Real-Time Neurophysiological Reward Signals for System AdaptationDOI 10.20944/preprints202608.1274.v1Read

Iterative improvements from feedback for language modelsSemantic proximity Read

Establishing a Real-Time Biomarker-to-LLM Interface: A Modular Pipeline for HRV Signal Acquisition, Processing, and Physiological State Interpretation via Generative AISemantic proximity Read

Cognitive anchoring by large language models accelerates group consensusSemantic proximity Read

Long short-term prediction guides human metacognitive reinforcement learningSemantic proximity Read

Lightweight Reinforcement Algorithms for autonomous, scalable intra-cortical Brain Machine InterfacesSemantic proximity Read

Tracking and optimizing human performance using deep reinforcement learning in closed-loop behavioral- and neuro- feedback: a proof of conceptSemantic proximity Read

Beyond Words: The Evolution of Large Language Models in Context-AwareSemantic proximity Read

BrainLM: A foundation model for brain activity recordingsSemantic proximity Read

Sparse Autoencoders as an Interpretable Interface for LLM Development and ControlSemantic proximity Read

On the misuse of prediction in NeuroAI: A case study of CentaurSemantic proximity Read

Approximated Variational Bayesian Inverse Reinforcement Learning for Large Language Model AlignmentSemantic proximity Read

Efficient and Responsible Transformer Based Conversational Agents for Emotionally Supportive DialogueSemantic proximity Read