10 papers
Teacher-Guided Tool Learning for Small Language Models via Bidirectional KL Constraints
Haoxuan Gao, Qin-Wen Luo, Xiang Chen +5
External tools can extend the capabilities of small language models (SLMs), enabling their deployment in resource constrained environments. However, their limited capabilities make…
Mind the Execution Gap: Action-Semantic Mismatch in World-Model Control
Shengtao Wen, Xiang Chen, Yu Tian +3
World-model controllers rely on action-conditioned dynamics for prediction and planning, yet real control systems often execute commands asynchronously due to communication delay,…
Decoupling Knowledge and Privacy: Post-Task Self-Distillation Replay for LLM Continual Learning
Shengtao Wen, Yunying Yang, Xiang Chen +3
Privacy-preserving continual learning (PPCL) must reduce the reproduction of sensitive content while retaining useful knowledge across sequential tasks. Formal privacy guarantees c…
SafeThinker: Reasoning about Risk to Deepen Safety Beyond Shallow Alignment
Xianya Fang, Xianying Luo, Yadong Wang +8
Despite the intrinsic risk-awareness of Large Language Models (LLMs), current defenses often result in shallow safety alignment, rendering models vulnerable to disguised attacks (e…
Beyond Superficial Unlearning: Sharpness-Aware Robust Erasure of Hallucinations in Multimodal LLMs
Xianya Fang, Feiyang Ren, Xiang Chen +4
Multimodal LLMs are powerful but prone to object hallucinations, which describe non-existent entities and harm reliability. While recent unlearning methods attempt to mitigate this…
Retrieval-augmented Prompt Learning for Pre-trained Foundation Models
Xiang Chen, Yixin Ou, Quan Feng +8
The pre-trained foundation models (PFMs) have become essential for facilitating large-scale multimodal learning. Researchers have effectively employed the ``pre-train, prompt, and…
MultiMedEdit: A Scenario-Aware Benchmark for Evaluating Knowledge Editing in Medical VQA
Shengtao Wen, Haodong Chen, Yadong Wang +6
Knowledge editing (KE) provides a scalable approach for updating factual knowledge in large language models without full retraining. While previous studies have demonstrated effect…
Tailored Teaching with Balanced Difficulty: Elevating Reasoning in Multimodal Chain-of-Thought via Prompt Curriculum
Xinglong Yang, Quan Feng, Zhongying Pan +7
The effectiveness of Multimodal Chain-of-Thought (MCoT) prompting is often limited by the use of randomly or manually selected examples. These examples fail to account for both mod…
Reflect then Learn: Active Prompting for Information Extraction Guided by Introspective Confusion
Dong Zhao, Yadong Wang, Xiang Chen +6
Large Language Models (LLMs) show remarkable potential for few-shot information extraction (IE), yet their performance is highly sensitive to the choice of in-context examples. Con…
Graph-guided Cross-composition Feature Disentanglement for Compositional Zero-shot Learning
Yuxia Geng, Runkai Zhu, Jiaoyan Chen +7
Disentanglement of visual features of primitives (i.e., attributes and objects) has shown exceptional results in Compositional Zero-shot Learning (CZSL). However, due to the featur…