Papers by Matthew Sarte
VeriFastScore: Speeding up long-form factuality evaluation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | VeriFastScore model can be used to evaluate long-form factuality but requires multiple LLM calls and can take up to 100s to evaluate a single response. |
| Approach: | They propose a model that leverages synthetic data to fine-tune Llama3.1 8B for extracting and verifying all verifiable claims within a given text based on evidence from Google Search. |
| Outcome: | The proposed model achieves strong correlation with the original VeriScore pipeline at both the example level and system level while achieving an overall speedup of 6.6 over Veriscore. |