6 papers
Adaptive and Explicit safe: Triggering Latent Safety Awareness in Large Reasoning Models
Ke Miao, Jiaxin Li, Hongliang Chen +2
While Large Reasoning Models (LRMs) excel at complex tasks, they remain highly vulnerable to sophisticated jailbreaks and direct harmful queries. To address this vulnerability, pri…
Pointing to a Llama and Call it a Camel: On the Sycophancy of Multimodal Large Language Models
Renjie Pi, Kehao Miao, Li Peihang +4
Multimodal large language models (MLLMs) have demonstrated extraordinary capabilities in conducting conversations based on image inputs. However, we observe that MLLMs exhibit a pr…
An Investigation on Group Query Hallucination Attacks
Kehao Miao, Xiaolong Jin
With the widespread use of large language models (LLMs), understanding their potential failure modes during user interactions is essential. In practice, users often pose multiple q…
Towards Evaluation for Real-World LLM Unlearning
Ke Miao, Yuke Hu, Xiaochen Li +4
This paper analyzes the limitations of existing unlearning evaluation metrics in terms of practicality, exactness, and robustness in real-world LLM unlearning scenarios. To overcom…
VL-GenRM: Enhancing Vision-Language Verification via Vision Experts and Iterative Training
Jipeng Zhang, Kehao Miao, Renjie Pi +4
Reinforcement Fine-Tuning (RFT) with verifiable rewards has advanced large language models but remains underexplored for Vision-Language (VL) models. The Vision-Language Reward Mod…
ExeSQL: Self-Taught Text-to-SQL Models with Execution-Driven Bootstrapping for SQL Dialects
Jipeng Zhang, Haolin Yang, Kehao Miao +4
Recent text-to-SQL models have achieved strong performance, but their effectiveness remains largely confined to SQLite due to dataset limitations. However, real-world applications…