Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915934572118016 |
|---|---|
| author | Fang, Chenhao Mola, Jordi Harman, Mark Nawrocki, Jason Shrivastava, Vaibhav Cheng, Yue Shah, Jay Minesh Zand, Katayoun Tripathi, Mansi Pudota, Arya Becker, Matthew Robert, Hervé Gulati, Abhishek |
| author_facet | Fang, Chenhao Mola, Jordi Harman, Mark Nawrocki, Jason Shrivastava, Vaibhav Cheng, Yue Shah, Jay Minesh Zand, Katayoun Tripathi, Mansi Pudota, Arya Becker, Matthew Robert, Hervé Gulati, Abhishek |
| contents | Although LLMs drive automation, it is critical to ensure immense consideration for high-stakes enterprise workflows such as those involving legal matters, risk management, and privacy compliance. For Meta, and other organizations like ours, a single hallucinated clause in such high stakes workflows risks material consequences. We show that by framing hallucination mitigation as a Minimum Bayes Risk (MBR) problem, we can dramatically reduce this risk. Specifically, we introduce a Hybrid Utility MBR (HUMBR) framework that synthesizes semantic embedding similarity with lexical precision to identify consensus without ground-truth references, for which we derive rigorous error bounds. We complement this theoretical analysis with a comprehensive empirical evaluation on widely-used public benchmark suites (TruthfulQA and LegalBench) and also real world data from Meta production deployment. The results from our empirical study show that MBR significantly outperforms standard Universal Self-Consistency. Notably, 81% of the pipeline's suggestions were preferred over human-crafted ground truth, and critical recall failures were virtually eliminated. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_11141 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR) Fang, Chenhao Mola, Jordi Harman, Mark Nawrocki, Jason Shrivastava, Vaibhav Cheng, Yue Shah, Jay Minesh Zand, Katayoun Tripathi, Mansi Pudota, Arya Becker, Matthew Robert, Hervé Gulati, Abhishek Machine Learning Cryptography and Security Although LLMs drive automation, it is critical to ensure immense consideration for high-stakes enterprise workflows such as those involving legal matters, risk management, and privacy compliance. For Meta, and other organizations like ours, a single hallucinated clause in such high stakes workflows risks material consequences. We show that by framing hallucination mitigation as a Minimum Bayes Risk (MBR) problem, we can dramatically reduce this risk. Specifically, we introduce a Hybrid Utility MBR (HUMBR) framework that synthesizes semantic embedding similarity with lexical precision to identify consensus without ground-truth references, for which we derive rigorous error bounds. We complement this theoretical analysis with a comprehensive empirical evaluation on widely-used public benchmark suites (TruthfulQA and LegalBench) and also real world data from Meta production deployment. The results from our empirical study show that MBR significantly outperforms standard Universal Self-Consistency. Notably, 81% of the pipeline's suggestions were preferred over human-crafted ground truth, and critical recall failures were virtually eliminated. |
| title | Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR) |
| topic | Machine Learning Cryptography and Security |
| url | https://arxiv.org/abs/2604.11141 |