Why Are LLMs Confidently Wrong? Correcting Overconfident Errors via Causal Head Intervention
Paper • 2610.34994 • Published
AI & ML interests
RAG frameworks empower LLMs for specific tasks.
Recent Activity
View all activity
aisuko
authored a
paper 7 days ago
aisuko
authored 2
papers 8 months ago
aisuko
authored 4
papers 10 months ago
Securing LLM-as-a-Service for Small Businesses: An Industry Case Study of a Distributed Chatbot Deployment Platform
Paper • 2601.15528 • Published
When to Invoke: Refining LLM Fairness with Toxicity Assessment
Paper • 2601.09250 • Published
When to Trust: A Causality-Aware Calibration Framework for Accurate Knowledge Graph Retrieval-Augmented Generation
Paper • 2601.09241 • Published
Debiasing Large Language Models via Adaptive Causal Prompting with Sketch-of-Thought
Paper • 2601.08108 • Published