A multi-agent forensic system integrates multiple evidence sources and debate to detect AI-generated images, reporting 97.05% accuracy on a 6,000-image benchmark while outperforming traditional classifiers.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
ReFACT benchmark reveals LLMs show a persistent salient distractor failure mode where 61% of incorrect error span predictions are semantically unrelated to actual errors, persisting across model sizes, and comparative judgment yields lower F1 than independent detection.
RAMM improves multimodal fake news detection by retrieving abstract narrative consistencies across instances and shifting to analogical reasoning via an MLLM backbone and two alignment modules.
RASR retrieves cross-video semantic evidence and domain-guided MLLM reports, then fuses multi-view features to beat FakeSV/FakeTT baselines by up to 0.93% accuracy.
Multi-agent LLM system with consensus and hierarchy outperforms individual models on disinformation detection tasks across English, Polish, Slovak, and Bulgarian datasets.
citing papers explorer
-
From Evidence to Verdict: An Agent-Based Forensic Framework for AI-Generated Image Detection
A multi-agent forensic system integrates multiple evidence sources and debate to detect AI-generated images, reporting 97.05% accuracy on a 6,000-image benchmark while outperforming traditional classifiers.
-
ReFACT: A Benchmark for Scientific Confabulation Detection with Positional Error Annotations
ReFACT benchmark reveals LLMs show a persistent salient distractor failure mode where 61% of incorrect error span predictions are semantically unrelated to actual errors, persisting across model sizes, and comparative judgment yields lower F1 than independent detection.
-
Retrieval-Augmented Multimodal Model for Fake News Detection
RAMM improves multimodal fake news detection by retrieving abstract narrative consistencies across instances and shifting to analogical reasoning via an MLLM backbone and two alignment modules.
-
RASR: Retrieval-Augmented Semantic Reasoning for Fake News Video Detection
RASR retrieves cross-video semantic evidence and domain-guided MLLM reports, then fuses multi-view features to beat FakeSV/FakeTT baselines by up to 0.93% accuracy.
-
Multi-Agentic System Leveraging Open-Source LLMs to Mitigate Disinformation Threats
Multi-agent LLM system with consensus and hierarchy outperforms individual models on disinformation detection tasks across English, Polish, Slovak, and Bulgarian datasets.