Skip to content
conftrace_
2026 EMNLP EMNLP 2026

Same Meaning, Different Wording: Evaluating Paraphrase Robustness in Financial Natural Language Inference

AbstractWe present FinNLI-Para, a paraphrased version of financial natural language inference (FinNLI). We investigate how much predictions on FinNLI depend on the particular wording used to express a financial hypothesis. We generate three paraphrases for each FinNLI hypothesis and use them to test prediction consistency across eleven model–prompt configurations. Models change their predictions on 7.9–12.3% of paraphrased examples, despite 98.35% of paraphrases preserving the original NLI label, indicating that financial NLI systems remain sensitive to hypothesis wording.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

More from EMNLP 2026

All EMNLP 2026 papers →