A new SEC-filing QA benchmark shows that retrieval models lose 13 to 20.5 points of ranking accuracy when plausible but wrong disclosures are used as distractors.
Dense Passage Retrieval for Open-Domain Question Answering , booktitle =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FinRank: An Evidence-Grounded Benchmark for Financial Question Answering and Retrieval over SEC Filings
A new SEC-filing QA benchmark shows that retrieval models lose 13 to 20.5 points of ranking accuracy when plausible but wrong disclosures are used as distractors.