Uncertainty-Aware Fusion: An Ensemble Framework for Mitigating Hallucinations in Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929748360298496 |
|---|---|
| author | Dey, Prasenjit Merugu, Srujana Kaveri, Sivaramakrishnan |
| author_facet | Dey, Prasenjit Merugu, Srujana Kaveri, Sivaramakrishnan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_05757 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Uncertainty-Aware Fusion: An Ensemble Framework for Mitigating Hallucinations in Large Language Models Dey, Prasenjit Merugu, Srujana Kaveri, Sivaramakrishnan Machine Learning Artificial Intelligence Computation and Language 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. |
| title | Uncertainty-Aware Fusion: An Ensemble Framework for Mitigating Hallucinations in Large Language Models |
| topic | Machine Learning Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2503.05757 |