View of Refusal-Aware Instruction Tuning through Gradient-Guided Optimization and Knowledge-Flow Calibration for Hallucination Mitigation under Uncertain Knowledge Boundaries and Conflicting Evidence in Large Language Models

Return to Issue Details Refusal-Aware Instruction Tuning through Gradient-Guided Optimization and Knowledge-Flow Calibration for Hallucination Mitigation under Uncertain Knowledge Boundaries and Conflicting Evidence in Large Language Models Download Download PDF