SIC-Autonomous Ensemble: Large Language Model Hallucination Mitigation Framework Using Self Iterative Contradiction and Optimal Ensembling

Summary

Researchers propose SIC-AE, a framework that reduces hallucination in large language models by running self-correcting loops on each component model, then ranking candidate responses and fusing the top ones through an autonomous weight update mechanism. Built on low-parameter open-source LLMs, it reports accuracy gains of 1-5% over state-of-the-art self-refinement techniques and a further 1-8% from adding the ensemble across three benchmarks covering factual and logical reasoning questions.