5 papers
EviAnchor: Mitigating Hallucinations in Large Vision-Language Models via Regional Visual Evidence Compensation
Sihang Jia, Shuliang Liu, Songbo Yang +1
Large vision-language models (LVLMs) frequently generate content unsupported by visual inputs. Preliminary experiments show that visual evidence is primarily incorporated into answ…
Decoding by Perturbation: Mitigating MLLM Hallucinations via Dynamic Textual Perturbation
Sihang Jia, Shuliang Liu, Songbo Yang +3
Multimodal Large Language Models frequently suffer from inference hallucinations, partially stemming from language priors dominating visual evidence. Existing training-free mitigat…
Vision-Language Introspection: Mitigating Overconfident Hallucinations in MLLMs via Interpretable Bi-Causal Steering
Shuliang Liu, Songbo Yang, Dong Fang +7
Object hallucination critically undermines the reliability of Multimodal Large Language Models, often stemming from a fundamental failure in cognitive introspection, where models b…
Evaluating Chinese Large Language Models: The Influence of Persona Assignment on Stereotypes and Safeguards
Geng Liu, Li Feng, Carlo Alberto Bono +3
Recent research has highlighted that assigning specific personas to large language models (LLMs) can significantly increase harmful content generation. However, limited attention h…
Continuous Dynamic Modeling via Neural ODEs for Popularity Trajectory Prediction
Songbo Yang, Ziwei Zhao, Zihang Chen +3
Popularity prediction for information cascades has significant applications across various domains, including opinion monitoring and advertising recommendations. While most existin…