Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Hao Fang

Hao Fang

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

AI×2Crypto×2ML×2NLP×1

Frequent co-authors

Bin Chen2×
Shu-Tao Xia2×
Jiawei Kong1×
Shunxiang Liao1×
Jinyu Li1×
Hao Wu1×

Research Timeline

2026
Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)

The paper introduces a Hybrid Utility Minimum Bayes Risk (HUMBR) framework to significantly reduce hallucinations in high-stakes enterprise AI workflows, outperforming standard consistency methods.

Prompt2Fingerprint: Plug-and-Play LLM Fingerprinting via Text-to-Weight Generation

Prompt2Fingerprint (P2F) introduces a novel, scalable framework that injects unique LLM fingerprints by mapping text descriptions directly to low-rank parameter updates, eliminating the need for resource-intensive model retraining.

Reasoning Matters: Mitigate Hallucination in Multimodal Large Reasoning Models via Reasoning-Conditioned Preference Optimization

The paper proposes Reasoning-Conditioned Direct Preference Optimization (RC-DPO) to effectively mitigate hallucinations in multimodal large reasoning models by explicitly conditioning the preference optimization on the Chain-of-Thought (CoT) process.

Highlighted terms show continued research focus across papers

Papers

cs.AIRecentMay 27, 2026

Reasoning Matters: Mitigate Hallucination in Multimodal Large Reasoning Models via Reasoning-Conditioned Preference Optimization

Jiawei Kong, Hao Fang, Shunxiang Liao, Jinyu Li +4 more

The paper proposes Reasoning-Conditioned Direct Preference Optimization (RC-DPO) to effectively mitigate hallucinations in multimodal large reasoning models by explicitly conditioning the preference o…

View →
cs.CRcs.AIcs.CLRecentMay 18, 2026

Prompt2Fingerprint: Plug-and-Play LLM Fingerprinting via Text-to-Weight Generation

Sixu Chen, Xiang Chen, Hongyao Yu, Jiaxin Hong +4 more

Prompt2Fingerprint (P2F) introduces a novel, scalable framework that injects unique LLM fingerprints by mapping text descriptions directly to low-rank parameter updates, eliminating the need for resou…

View →
cs.LGcs.CRRecentApr 13, 2026

Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)

Chenhao Fang, Jordi Mola, Mark Harman, Jason Nawrocki +9 more

The paper introduces a Hybrid Utility Minimum Bayes Risk (HUMBR) framework to significantly reduce hallucinations in high-stakes enterprise AI workflows, outperforming standard consistency methods.

View →