A 7,500-question SEC-filing benchmark with a 13-type error taxonomy shows LLM accuracy falls by 14–19 points when reasoning moves from single documents to cross-company or multi-year tasks.
Title resolution pending
1 Pith paper cite this work, alongside 4 external citations. Polarity classification is still indexing.
1
Pith paper citing it
4
external citations · OpenAlex
fields
cs.CE 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Fin-RATE: A Real-world Financial Analytics and Tracking Evaluation Benchmark for LLMs on SEC Filings
A 7,500-question SEC-filing benchmark with a 13-type error taxonomy shows LLM accuracy falls by 14–19 points when reasoning moves from single documents to cross-company or multi-year tasks.