RW-Post: Auditable Evidence-Grounded Multimodal Fact-Checking in the Wild
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910210384199680 |
|---|---|
| author | Xu, Danni Fan, Shaojing Cheng, Harry Kankanhalli, Mohan |
| author_facet | Xu, Danni Fan, Shaojing Cheng, Harry Kankanhalli, Mohan |
| contents | Multimodal misinformation increasingly leverages visual persuasion, where repurposed or manipulated images strengthen misleading text. We introduce RW-Post, a post-aligned text--image benchmark for real-world multimodal fact-checking with auditable annotations: each instance links the original social-media post with reasoning traces and explicitly linked evidence items derived from human fact-check articles via an LLM-assisted extraction-and-auditing pipeline. RW-Post supports controlled evaluation across closed-book, evidence-bounded, and open-web regimes, enabling systematic diagnosis of visual grounding and evidence utilization. We provide AgentFact as a reference verification baseline and benchmark strong open-source LVLMs under unified protocols. Experiments show substantial headroom: current models struggle with faithful evidence grounding, while evidence-bounded evaluation improves both accuracy and faithfulness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_22933 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RW-Post: Auditable Evidence-Grounded Multimodal Fact-Checking in the Wild Xu, Danni Fan, Shaojing Cheng, Harry Kankanhalli, Mohan Artificial Intelligence Computation and Language Multimodal misinformation increasingly leverages visual persuasion, where repurposed or manipulated images strengthen misleading text. We introduce RW-Post, a post-aligned text--image benchmark for real-world multimodal fact-checking with auditable annotations: each instance links the original social-media post with reasoning traces and explicitly linked evidence items derived from human fact-check articles via an LLM-assisted extraction-and-auditing pipeline. RW-Post supports controlled evaluation across closed-book, evidence-bounded, and open-web regimes, enabling systematic diagnosis of visual grounding and evidence utilization. We provide AgentFact as a reference verification baseline and benchmark strong open-source LVLMs under unified protocols. Experiments show substantial headroom: current models struggle with faithful evidence grounding, while evidence-bounded evaluation improves both accuracy and faithfulness. |
| title | RW-Post: Auditable Evidence-Grounded Multimodal Fact-Checking in the Wild |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2512.22933 |