Changing the file format of identical input content changes LLM workflow decisions in 41% of cases on average and can reduce accuracy by up to 56 percentage points, with CSV the most error-prone format.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Not as Sweet by Another Name: An Empirical Study of Format Robustness in LLM Document Workflows
Changing the file format of identical input content changes LLM workflow decisions in 41% of cases on average and can reduce accuracy by up to 56 percentage points, with CSV the most error-prone format.