QuanTemp: A real-world open-domain benchmark for fact-checking numerical claims
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913337787285504 |
|---|---|
| author | V, Venktesh Anand, Abhijit Anand, Avishek Setty, Vinay |
| author_facet | V, Venktesh Anand, Abhijit Anand, Avishek Setty, Vinay |
| contents | Automated fact checking has gained immense interest to tackle the growing misinformation in the digital era. Existing systems primarily focus on synthetic claims on Wikipedia, and noteworthy progress has also been made on real-world claims. In this work, we release QuanTemp, a diverse, multi-domain dataset focused exclusively on numerical claims, encompassing temporal, statistical and diverse aspects with fine-grained metadata and an evidence collection without leakage. This addresses the challenge of verifying real-world numerical claims, which are complex and often lack precise information, not addressed by existing works that mainly focus on synthetic claims. We evaluate and quantify the limitations of existing solutions for the task of verifying numerical claims. We also evaluate claim decomposition based methods, numerical understanding based models and our best baselines achieves a macro-F1 of 58.32. This demonstrates that QuanTemp serves as a challenging evaluation set for numerical claim verification. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_17169 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | QuanTemp: A real-world open-domain benchmark for fact-checking numerical claims V, Venktesh Anand, Abhijit Anand, Avishek Setty, Vinay Computation and Language Artificial Intelligence Automated fact checking has gained immense interest to tackle the growing misinformation in the digital era. Existing systems primarily focus on synthetic claims on Wikipedia, and noteworthy progress has also been made on real-world claims. In this work, we release QuanTemp, a diverse, multi-domain dataset focused exclusively on numerical claims, encompassing temporal, statistical and diverse aspects with fine-grained metadata and an evidence collection without leakage. This addresses the challenge of verifying real-world numerical claims, which are complex and often lack precise information, not addressed by existing works that mainly focus on synthetic claims. We evaluate and quantify the limitations of existing solutions for the task of verifying numerical claims. We also evaluate claim decomposition based methods, numerical understanding based models and our best baselines achieves a macro-F1 of 58.32. This demonstrates that QuanTemp serves as a challenging evaluation set for numerical claim verification. |
| title | QuanTemp: A real-world open-domain benchmark for fact-checking numerical claims |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2403.17169 |