6 papers · 1 filter
Can a Small Model Learn to Look Before It Leaps? Dynamic Learning and Proactive Correction for Hallucination Detection
Zepeng Bao, Shen Zhou, Qiankun Pi +5
Hallucination in large language models (LLMs) remains a critical barrier to their safe deployment. For hallucination detection to be practical in real-world scenarios, the use of e…
CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations
Xiaohu Li, Yunfeng Ning, Zepeng Bao +3
Security alignment enables the Large Language Model (LLM) to gain the protection against malicious queries, but various jailbreak attack methods reveal the vulnerability of this se…
RAJ-PGA: Reasoning-Activated Jailbreak and Principle-Guided Alignment Framework for Large Reasoning Models
Jianhao Chen, Mayi Xu, Haoyang Chen +6
Large Reasoning Models (LRMs) face a distinct safety vulnerability: their internal reasoning chains may generate harmful content even when the final output appears benign. To addre…
NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs
Birong Pan, Jianhao Chen, Mayi Xu +4
Ensuring robust safety alignment while preserving utility is critical for the reliable deployment of Large Language Models (LLMs). However, current techniques fundamentally suffer…
Aligning VLM Assistants with Personalized Situated Cognition
Yongqi Li, Shen Zhou, Xiaohu Li +9
Vision-language models (VLMs) aligned with general human objectives, such as being harmless and hallucination-free, have become valuable assistants of humans in managing visual tas…
Reasoning based on symbolic and parametric knowledge bases: a survey
Mayi Xu, Yunfeng Ning, Yongqi Li +10
Reasoning is fundamental to human intelligence, and critical for problem-solving, decision-making, and critical thinking. Reasoning refers to drawing new conclusions based on exist…