Fyan: A Human--AI Harness with Semantic Auditing for Document-Level Formalization (Q7367935)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
No description defined
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Fyan: A Human--AI Harness with Semantic Auditing for Document-Level Formalization |
No description defined |
Statements
Fyan: A Human--AI Harness with Semantic Auditing for Document-Level Formalization (English)
0 references
30 September 2026
0 references
cs.AI
0 references
Wei Zhao
0 references
Yangshuo Zou
0 references
Chengxiang Ding
0 references
Yifan Wu
0 references
Xuchuan Wang
0 references
Zimu Mao
0 references
Lei Zhang
0 references
Tao Luo
0 references
We present FYAN, an end-to-end human--AI harness for document-level formalization with evidence-grounded semantic auditing; it proves more theorems (86/143) and outperforms a direct LLM judge on consistency checks (recall 0.777 vs. 0.636).
0 references
AI
0 references
Document-Level
0 references
Formalization
0 references
Human-AI Harness
0 references
Semantic Auditing
0 references
1 reference
1 reference
