4 papers · 1 filter
AERO: Adaptive Ensemble-Disagreement Routing for Oracle Feedback in Sample-Efficient Online RLHF
Shrey Singhal, Nannan Huang, Haytham M. Fayek
Aligning Large Language Models (LLMs) with human preferences via Reinforcement Learning from Human Feedback (RLHF) has driven substantial improvements across a wide range of tasks,…
When to Trust: A Causality-Aware Calibration Framework for Accurate Knowledge Graph Retrieval-Augmented Generation
Jing Ren, Bowen Li, Ziqi Xu +3
Knowledge Graph Retrieval-Augmented Generation (KG-RAG) extends the RAG paradigm by incorporating structured knowledge from knowledge graphs, enabling Large Language Models (LLMs)…
Fine-Grained Traceability for Transparent ML Pipelines
Liping Chen, Mujie Liu, Haytham Fayek
Modern machine learning systems are increasingly realised as multistage pipelines, yet existing transparency mechanisms typically operate at a model level: they describe what a sys…
When to Invoke: Refining LLM Fairness with Toxicity Assessment
Jing Ren, Bowen Li, Ziqi Xu +6
Large Language Models (LLMs) are increasingly used for toxicity assessment in online moderation systems, where fairness across demographic groups is essential for equitable treatme…