ART: Adaptive Reasoning Trees for Explainable Claim Verification
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918278911229952 |
|---|---|
| author | Wadhwa, Sahil Kumar, Himanshu Yang, Guanqun Nishar, Abbaas Alif Mohamed Mohanty, Pranab Shinde, Swapnil Wu, Yue |
| author_facet | Wadhwa, Sahil Kumar, Himanshu Yang, Guanqun Nishar, Abbaas Alif Mohamed Mohanty, Pranab Shinde, Swapnil Wu, Yue |
| contents | Large Language Models (LLMs) are powerful candidates for complex decision-making, leveraging vast encoded knowledge and remarkable zero-shot abilities. However, their adoption in high-stakes environments is hindered by their opacity; their outputs lack faithful explanations and cannot be effectively contested to correct errors, undermining trustworthiness. In this paper, we propose ART (Adaptive Reasoning Trees), a hierarchical method for claim verification. The process begins with a root claim, which branches into supporting and attacking child arguments. An argument's strength is determined bottom-up via a pairwise tournament of its children, adjudicated by a judge LLM, allowing a final, transparent and contestable verdict to be systematically derived which is missing in methods like Chain-of-Thought (CoT). We empirically validate ART on multiple datasets, analyzing different argument generators and comparison strategies. Our findings show that ART's structured reasoning outperforms strong baselines, establishing a new benchmark for explainable claim verification which is more reliable and ensures clarity in the overall decision making step. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_05455 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ART: Adaptive Reasoning Trees for Explainable Claim Verification Wadhwa, Sahil Kumar, Himanshu Yang, Guanqun Nishar, Abbaas Alif Mohamed Mohanty, Pranab Shinde, Swapnil Wu, Yue Artificial Intelligence Machine Learning Large Language Models (LLMs) are powerful candidates for complex decision-making, leveraging vast encoded knowledge and remarkable zero-shot abilities. However, their adoption in high-stakes environments is hindered by their opacity; their outputs lack faithful explanations and cannot be effectively contested to correct errors, undermining trustworthiness. In this paper, we propose ART (Adaptive Reasoning Trees), a hierarchical method for claim verification. The process begins with a root claim, which branches into supporting and attacking child arguments. An argument's strength is determined bottom-up via a pairwise tournament of its children, adjudicated by a judge LLM, allowing a final, transparent and contestable verdict to be systematically derived which is missing in methods like Chain-of-Thought (CoT). We empirically validate ART on multiple datasets, analyzing different argument generators and comparison strategies. Our findings show that ART's structured reasoning outperforms strong baselines, establishing a new benchmark for explainable claim verification which is more reliable and ensures clarity in the overall decision making step. |
| title | ART: Adaptive Reasoning Trees for Explainable Claim Verification |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2601.05455 |