SyncAI.news, a Varaisys broadcasting
Frame: Form-Restricted Authoring with Model-Based Evaluation
NJ

Nan Jiang, Mohammed Mohsin Hussain, Onkar Tiwari, Ankit Jain, Thong Q. Nguyen, Abhishek Agarwal, Vishal Chowdhary

· 1 min read

ResearcharXiv cs.AI

Frame: Form-Restricted Authoring with Model-Based Evaluation

arXiv:2611.08921v1 Announce Type: new Abstract: Many professional reports reuse the structure of prior editions while updating the content. We formalize this setting as form-restricted report generation: given a sample report and new grounding documents, generate a report that preserves the sample's form while accurately reflecting the new evidence. We introduce FRAME, a benchmark of 120 EDGAR- and arXiv-derived instances across Financial Quarterly, Financial Annual, Academic Simple, and Academic Complex categories, built with a temporal three-snapshot pipeline. We evaluate outputs with three human-validated metrics: structural similarity via semantic tree-edit distance, coverage via information unit recall, and faithfulness via claim-level grounding verification. Across five LLMs, open-source models nearly match proprietary models on structure but lag on coverage and faithfulness; all models perform better on financial than academic reports, and performance declines with longer outputs and more complex grounding.

Original source

This story was published by arXiv cs.AI and written by Nan Jiang, Mohammed Mohsin Hussain, Onkar Tiwari, Ankit Jain, Thong Q. Nguyen, Abhishek Agarwal, Vishal Chowdhary. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News