# Uncertainty-Aware Fusion: An Ensemble Framework for Mitigating Hallucinations in Large Language Models

arXiv: https://arxiv.org/abs/2503.05757 · HTML: https://mlsanity.com/paper/2503.05757/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 23 references that are in the map.
- First posted on arXiv 22 Feb 2025.

## Builds on (most cited first, 11 of 11)

- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion](https://mlsanity.com/paper/2306.02561/) (2023)
- [DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models](https://mlsanity.com/paper/2309.03883/) (2023)
- [Out-of-Distribution Detection and Selective Generation for Conditional Language Models](https://mlsanity.com/paper/2209.15558/) (2022)
- [Generating Benchmarks for Factuality Evaluation of Language Models](https://mlsanity.com/paper/2307.06908/) (2023)
- [HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection](https://mlsanity.com/paper/2409.17504/) (2024)

## Built on by (most cited first, 12 of 12)

- [Large Language Models Hallucination: A Comprehensive Survey](https://mlsanity.com/paper/2510.06265/) (2025)
- [Semantic Energy: Detecting LLM Hallucination Beyond Entropy](https://mlsanity.com/paper/2508.14496/) (2025)
- [Complementing Self-Consistency with Cross-Model Disagreement for Uncertainty Quantification](https://mlsanity.com/paper/2604.17112/) (2026)
- [Cross-Model Disagreement as a Label-Free Correctness Signal](https://mlsanity.com/paper/2603.25450/) (2026)
- [The Alignment Auditor: A Bayesian Framework for Verifying and Refining LLM Objectives](https://mlsanity.com/paper/2510.06096/) (2025)
- [Beyond Single Models: Mitigating Multimodal Hallucinations via Adaptive Token Ensemble Decoding](https://mlsanity.com/paper/2510.18321/) (2025)
- [Teaming LLMs to Detect and Mitigate Hallucinations](https://mlsanity.com/paper/2510.19507/) (2025)
- [Enhancing Factual Accuracy and Citation Generation in LLMs via Multi-Stage Self-Verification](https://mlsanity.com/paper/2509.05741/) (2025)
- [From scratch to silver: Creating trustworthy training data for patent-SDG classification using Large Language Models](https://mlsanity.com/paper/2509.09303/) (2025)
- [Large Language Models and 3D Vision for Intelligent Robotic Perception and Autonomy](https://mlsanity.com/paper/2511.11777/) (2025)
- ["I Don't Know" -- Towards Appropriate Trust with Certainty-Aware Retrieval Augmented Generation](https://mlsanity.com/paper/2605.00957/) (2026)
- [Opti-Q: A Constraint-Based Optimization Framework for Multi-LLM Question Planning](https://mlsanity.com/paper/2607.22621/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are known to hallucinate and generate non-factual outputs which can undermine user trust. Traditional methods to directly mitigate hallucinations, such as representation editing and contrastive decoding, often require additional training data and involve high implementation complexity. While ensemble-based approaches harness multiple LLMs to tap into the "wisdom of crowds", these methods overlook uncertainties in individual model responses. Recent studies reveal that uncertainty estimation can enable LLMs to self-assess the likelihood of generating hallucinations. In this work, we focus on factoid question answering (QA) and observe that LLMs accuracy and self-assessment capabilities vary widely with different models excelling in different scenarios. Leveraging this insight, we propose Uncertainty-Aware Fusion (UAF), an ensemble framework to reduces hallucinations by strategically combining multiple LLM based on their accuracy and self-assessment abilities. Empirical results on several public benchmark datasets show that UAF outperforms state-of-the-art hallucination mitigation methods by 8% in factual accuracy, while either narrowing or surpassing the performance gap with GPT-4.