4 papers
Rethinking Reverse KL as Adaptive Entropy Distillation
Shizhen Li, Zhiyu Shen, Yuyin Lu +4
Knowledge distillation (KD) is widely used to transfer the capabilities of large language models (LLMs) to smaller students, but existing objectives often struggle to balance faith…
Double-Calibration: Towards Reliable LLMs via Calibrating Knowledge and Reasoning Confidence
Yuyin Lu, Ziran Liang, Yanghui Rao +3
Reliable reasoning in Large Language Models (LLMs) is challenged by their propensity for hallucination. While augmenting LLMs with Knowledge Graphs (KGs) improves factual accuracy,…
Exploring the Paradigm Shift from Grounding to Skolemization for Complex Query Answering on Knowledge Graphs
Yuyin Lu, Hegang Chen, Shanrui Xie +4
Complex Query Answering (CQA) over incomplete Knowledge Graphs (KGs), typically formalized as reasoning with Existential First-Order predicate logic with one free variable (EFO\tex…
PairEdit: Learning Semantic Variations for Exemplar-based Image Editing
Haoguang Lu, Jiacheng Chen, Zhenguo Yang +4
Recent advancements in text-guided image editing have achieved notable success by leveraging natural language prompts for fine-grained semantic control. However, certain editing se…