Across nine LLMs, version resolution on amended customs documents tops out at 68.5% accuracy, with detection of a non-governing version at 26.7% and context misalignment at 27.62% even with gold documents.
Title resolution pending
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
-
Time Present and Time Past: Benchmarking Large Language Models on Temporally Evolving Document Understanding
Across nine LLMs, version resolution on amended customs documents tops out at 68.5% accuracy, with detection of a non-governing version at 26.7% and context misalignment at 27.62% even with gold documents.