15 papers
One Model Is Not a Crowd: Multi-LLM and Aspect-Conditioned Diverse Comment Generation
Nafis Irtiza Tripto, Delvin Ce Zhang, Mahjabin Nahar +1
Human communication on the internet is shaped by diverse perspectives, most visibly expressed in online comment spaces. As large language model (LLM)based AI agents begin to inhabi…
TRILOGUE: A Trilingual Spoken Dialogue Fact-Checking Benchmark with Evidence and Paired Audio
Chaewan Chun, Meruyert Aristombayeva, Jiyoung Choi +3
Modern misinformation is often heard before it is read, yet fact-checking systems are still evaluated mainly on clean written claims. Spoken dialogue remains different even when sy…
PPE-Bench: A Benchmark for Evaluating MLLM Unlearning under Private-Public Entanglement
Xianren Zhang, Delvin Ce Zhang, Dongwon Lee +1
Multimodal Large Language Models (MLLMs) have shown strong capabilities, but they may memorize private information from web data, raising privacy concerns. Machine unlearning offer…
StateBridge: Training-free Hidden-state Alignment for Latent Communication in LLM Multi-Agent Systems
Yanwen Peng, Delvin Ce Zhang, Xi Wang +1
Large language model based multi-agent systems usually communicate in text, i.e., using discrete tokens. However, text introduces a discrete bottleneck. Converting the sender's con…
HyperClaim: Fine-Grained Cross-Modal Hypergraph Reasoning for Video Misinformation Detection
Xiangbo Wang, Jiasheng Zhang, Xingtong Yu +2
Video misinformation detection is often approached through global multimodal fusion or free-form multimodal reasoning. Both paradigms can under-represent localized authenticity cue…
Context-Aware Multimodal Claim Verification in Spoken Dialogues
Chaewan Chun, Delvin Ce Zhang, Dongwon Lee
Spoken factual claims often occur within multi-turn conversations, where surrounding dialogue can provide context unavailable from the claim alone. Yet most fact-checking research…
When Misinformation Speaks and Converses: Rethinking Fact-Checking in Audio Platforms
Chaewan Chun, Delvin Ce Zhang, Dongwon Lee
Audio platforms have evolved beyond entertainment. They have become central to public discourse, from podcasts and radio to WhatsApp voice notes and live streams. With millions of…
M2-Verify: A Large-Scale Multidomain Benchmark for Checking Multimodal Claim Consistency
Abolfazl Ansari, Delvin Ce Zhang, Zhuoyang Zou +2
Evaluating scientific arguments requires assessing the strict consistency between a claim and its underlying multimodal evidence. However, existing benchmarks lack the scale, domai…
DIAGPaper: Diagnosing Valid and Specific Weaknesses in Scientific Papers via Multi-Agent Reasoning
Zhuoyang Zou, Abolfazl Ansari, Delvin Ce Zhang +2
Paper weakness identification using single-agent or multi-agent LLMs has attracted increasing attention, yet existing approaches exhibit key limitations. Many multi-agent systems s…
MEVER: Multi-Modal and Explainable Claim Verification with Graph-based Evidence Retrieval
Delvin Ce Zhang, Suhan Cui, Zhelin Chu +2
Verifying the truthfulness of claims usually requires joint multi-modal reasoning over both textual and visual evidence, such as analyzing both textual caption and chart image for…
Unmasking Fake Careers: Detecting Machine-Generated Career Trajectories via Multi-layer Heterogeneous Graphs
Michiharu Yamashita, Thanh Tran, Delvin Ce Zhang +1
The rapid advancement of Large Language Models (LLMs) has enabled the generation of highly realistic synthetic data. We identify a new vulnerability, LLMs generating convincing car…
MAD: A Benchmark for Multi-Turn Audio Dialogue Fact-Checking
Chaewan Chun, Lysandre Terrisse, Delvin Ce Zhang +1
Despite the growing popularity of audio platforms, fact-checking spoken content remains significantly underdeveloped. Misinformation in speech often unfolds across multi-turn dialo…
Echoes of Automation: The Increasing Use of LLMs in Newsmaking
Abolfazl Ansari, Delvin Ce Zhang, Nafis Irtiza Tripto +1
The rapid rise of Generative AI (GenAI), particularly LLMs, poses concerns for journalistic integrity and authorship. This study examines AI-generated content across over 40,000 ne…
SUA: Stealthy Multimodal Large Language Model Unlearning Attack
Xianren Zhang, Hui Liu, Delvin Ce Zhang +4
Multimodal Large Language Models (MLLMs) trained on massive data may memorize sensitive personal information and photos, posing serious privacy risks. To mitigate this, MLLM unlear…
CORRECT: Context- and Reference-Augmented Reasoning and Prompting for Fact-Checking
Delvin Ce Zhang, Dongwon Lee
Fact-checking the truthfulness of claims usually requires reasoning over multiple evidence sentences. Oftentimes, evidence sentences may not be always self-contained, and may requi…