JustiLM: Few-shot Justification Generation for Explainable Fact-Checking of Real-world 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_ | 1866929210421936128 |
|---|---|
| author | Zeng, Fengzhu Gao, Wei |
| author_facet | Zeng, Fengzhu Gao, Wei |
| contents | Justification is an explanation that supports the veracity assigned to a claim in fact-checking. However, the task of justification generation is previously oversimplified as summarization of fact-check article authored by fact-checkers. Therefore, we propose a realistic approach to generate justification based on retrieved evidence. We present a new benchmark dataset called ExClaim for \underline{Ex}plainable fact-checking of real-world \underline{Claim}s, and introduce JustiLM, a novel few-shot \underline{Justi}fication generation based on retrieval-augmented \underline{L}anguage \underline{M}odel by using fact-check articles as auxiliary resource during training only. Experiments show that JustiLM achieves promising performance in justification generation compared to strong baselines, and can also enhance veracity classification with a straightforward extension. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_08026 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | JustiLM: Few-shot Justification Generation for Explainable Fact-Checking of Real-world Claims Zeng, Fengzhu Gao, Wei Computation and Language Justification is an explanation that supports the veracity assigned to a claim in fact-checking. However, the task of justification generation is previously oversimplified as summarization of fact-check article authored by fact-checkers. Therefore, we propose a realistic approach to generate justification based on retrieved evidence. We present a new benchmark dataset called ExClaim for \underline{Ex}plainable fact-checking of real-world \underline{Claim}s, and introduce JustiLM, a novel few-shot \underline{Justi}fication generation based on retrieval-augmented \underline{L}anguage \underline{M}odel by using fact-check articles as auxiliary resource during training only. Experiments show that JustiLM achieves promising performance in justification generation compared to strong baselines, and can also enhance veracity classification with a straightforward extension. |
| title | JustiLM: Few-shot Justification Generation for Explainable Fact-Checking of Real-world Claims |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2401.08026 |