4 citations · 10 across the 11 of their papers we have counts for
12 papers
Toward Effective and Reliable LLM Agents via Dynamic Ontology
Xiaohui Zhang, Zequn Sun, Chengyuan Yang +3
Large language model (LLM) agents rely heavily on knowledge encoded in model parameters or presented as unstructured context. In domain-specific tasks, this leaves important semant…
When Entropy Is Not Enough: Reclaiming Lost Semantics in LLM Output Length Prediction
Feiyang Ren, Shengtao Wen, Lingbing Guo +6
Efficient LLM serving is often bottlenecked by the need to pad sequences to a fixed maximum length, and this wastes compute and degrades throughput. Output length prediction enable…
Harnessing Structural Context for Entity Alignment Foundation Models
Xingyu Chen, Yuanning Cui, Zequn Sun +1
Entity alignment (EA) aims to identify equivalent entities across heterogeneous knowledge graphs (KGs) and is a key component of knowledge fusion and cross-KG reasoning. The recent…
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…
Breaking the Reasoning Horizon in Entity Alignment Foundation Models
Yuanning Cui, Zequn Sun, Wei Hu +2
Entity alignment (EA) is critical for knowledge graph (KG) fusion. Existing EA models lack transferability and are incapable of aligning unseen KGs without retraining. While using…
KGFR: A Foundation Retriever for Generalized Knowledge Graph Question Answering
Yuanning Cui, Zequn Sun, Wei Hu +1
Large language models (LLMs) excel at reasoning but struggle with knowledge-intensive questions due to limited context and parametric knowledge. However, existing methods that rely…
A Prompt-Based Knowledge Graph Foundation Model for Universal In-Context Reasoning
Yuanning Cui, Zequn Sun, Wei Hu
Extensive knowledge graphs (KGs) have been constructed to facilitate knowledge-driven tasks across various scenarios. However, existing work usually develops separate reasoning mod…
Expanding the Scope: Inductive Knowledge Graph Reasoning with Multi-Starting Progressive Propagation
Zhoutian Shao, Yuanning Cui, Wei Hu
Knowledge graphs (KGs) are widely acknowledged as incomplete, and new entities are constantly emerging in the real world. Inductive KG reasoning aims to predict missing facts for t…
Improving Continual Relation Extraction by Distinguishing Analogous Semantics
Wenzheng Zhao, Yuanning Cui, Wei Hu
Continual relation extraction (RE) aims to learn constantly emerging relations while avoiding forgetting the learned relations. Existing works store a small number of typical sampl…
Lifelong Embedding Learning and Transfer for Growing Knowledge Graphs
Yuanning Cui, Yuxin Wang, Zequn Sun +4
Existing knowledge graph (KG) embedding models have primarily focused on static KGs. However, real-world KGs do not remain static, but rather evolve and grow in tandem with the dev…
Inductive Knowledge Graph Reasoning for Multi-batch Emerging Entities
Yuanning Cui, Yuxin Wang, Zequn Sun +4
Over the years, reasoning over knowledge graphs (KGs), which aims to infer new conclusions from known facts, has mostly focused on static KGs. The unceasing growth of knowledge in…
Facing Changes: Continual Entity Alignment for Growing Knowledge Graphs
Yuxin Wang, Yuanning Cui, Wenqiang Liu +4
Entity alignment is a basic and vital technique in knowledge graph (KG) integration. Over the years, research on entity alignment has resided on the assumption that KGs are static,…