FACTS&EVIDENCE: An Interactive Tool for Transparent Fine-Grained Factual Verification of Machine-Generated Text
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917961036464128 |
|---|---|
| author | Boonsanong, Varich Balachandran, Vidhisha Han, Xiaochuang Feng, Shangbin Wang, Lucy Lu Tsvetkov, Yulia |
| author_facet | Boonsanong, Varich Balachandran, Vidhisha Han, Xiaochuang Feng, Shangbin Wang, Lucy Lu Tsvetkov, Yulia |
| contents | With the widespread consumption of AI-generated content, there has been an increased focus on developing automated tools to verify the factual accuracy of such content. However, prior research and tools developed for fact verification treat it as a binary classification or a linear regression problem. Although this is a useful mechanism as part of automatic guardrails in systems, we argue that such tools lack transparency in the prediction reasoning and diversity in source evidence to provide a trustworthy user experience. We develop Facts&Evidence - an interactive and transparent tool for user-driven verification of complex text. The tool facilitates the intricate decision-making involved in fact-verification, presenting its users a breakdown of complex input texts to visualize the credibility of individual claims along with an explanation of model decisions and attribution to multiple, diverse evidence sources. Facts&Evidence aims to empower consumers of machine-generated text and give them agency to understand, verify, selectively trust and use such text. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_14797 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FACTS&EVIDENCE: An Interactive Tool for Transparent Fine-Grained Factual Verification of Machine-Generated Text Boonsanong, Varich Balachandran, Vidhisha Han, Xiaochuang Feng, Shangbin Wang, Lucy Lu Tsvetkov, Yulia Computation and Language With the widespread consumption of AI-generated content, there has been an increased focus on developing automated tools to verify the factual accuracy of such content. However, prior research and tools developed for fact verification treat it as a binary classification or a linear regression problem. Although this is a useful mechanism as part of automatic guardrails in systems, we argue that such tools lack transparency in the prediction reasoning and diversity in source evidence to provide a trustworthy user experience. We develop Facts&Evidence - an interactive and transparent tool for user-driven verification of complex text. The tool facilitates the intricate decision-making involved in fact-verification, presenting its users a breakdown of complex input texts to visualize the credibility of individual claims along with an explanation of model decisions and attribution to multiple, diverse evidence sources. Facts&Evidence aims to empower consumers of machine-generated text and give them agency to understand, verify, selectively trust and use such text. |
| title | FACTS&EVIDENCE: An Interactive Tool for Transparent Fine-Grained Factual Verification of Machine-Generated Text |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2503.14797 |