Search
5 articles for “Reinforcement Learning from Human Feedback”
-
Reward-Aligned Reinforcement Learning from Human Feedback for Emotion-Sensitive Large Language Model Therapists: Balancing Empathetic Engagement, Boundary Safety, and Clinical Accountability
Abstract: The deployment of large language models (LLMs) in mental health therapy contexts introduces a critical alignment challenge: these systems must simultaneously cultivate genuine empathic rapport, observe clinically grounded safety boundaries, and remain auditable under institutional accountability frameworks. Existing reinforcement learning from human feedback (RLHF) pipelines optimize for a scalar reward signal that is demonstrably insufficient for the multi-objective, temporally extended nature of therapeutic conversation. This paper presents RA-RLHF-T (Reward-Aligned RLHF …
Published in International Journal of Tropical Medicines · Vol. 3, Issue 2, 2026 Read article
-
Real-time Emotion-aware AI Counseling System with Memory Retention Polymer Composites
Abstract: The availability of mental health services is still a major barrier, with many individuals constrained by financial limitations, social stigma, and a shortage of accessible counselors. This work introduces an emotion-aware AI counselor designed to provide empathetic and personalized emotional support via voice-based interfaces. The system leverages Natural Language Processing (NLP) and sentiment analysis to detect emotional cues from speech and generate contextually appropriate, comforting responses. A key innovation is …
Published in Journal of Polymer & Composites · Vol. 14, Issue 1, 2026 · pp. 1395–1407 Read article
-
Automating Compiler Optimization: A Machine Learning Approach
Abstract: This study reports on an ML-based approach to compiler optimization, complementing traditional optimization methods that rely strongly on hand-tuned settings. Compiler optimization plays a key role in performance-speedup and energy optimization of complex contemporary software systems. However, the traditional approach to optimizer settings involves laborious, error-prone, and scale-insensitive human-in-the-loop intervention, especially in the complex and high-demand environments in which today's computing application thrives. By integrating RL and GA, we can …
Published in Journal of Artificial Intelligence Research & Advances · Vol. 12, Issue 1, 2025 · pp. 12–16 Read article
-
An Overview of Intelligent Operating Systems (iOS)
Abstract: The rapid convergence of artificial-intelligence techniques with core operating system services is ushering in a new class of platforms—intelligent operating systems (iOS)—that can anticipate, adapt, and optimize on behalf of both applications and users. This paper surveys the architectural shifts required to embed learning, reasoning, and self-healing capabilities into the kernel, scheduler, memory manager, and I/O subsystems. We present a prototype framework, NeuroKernel, that augments traditional OS primitives with three …
Published in Journal of Operating Systems Development & Trends · Vol. 13, Issue 1, 2026 · pp. 21–28 Read article
-
Exploring AI-Driven Student Performance Analysis as a Dimension of an AI-Powered Assessment and Feedback System: A Comprehensive Review
Abstract: The rapid proliferation of artificial intelligence (AI) in educational technology has heralded a paradigmatic transformation in assessment methodologies, transitioning from static, summative evaluations to dynamic, data-driven systems that emphasize continuous formative feedback. This comprehensive review interrogates AI-driven student performance analysis as a cardinal dimension of AI-powered assessment and feedback systems (AI-PAFS), synthesizing findings from forty-five rigorously curated open-access empirical studies published between 2015 and 2024. Employing a methodological lens, the …
Published in Current Trends in Information Technology · Vol. 16, Issue 1, 2025 · pp. 24–31 Read article