370 citations · 1.5k across the 61 of their papers we have counts for
49 papers · 1 filter
A Comprehensive Study of Knowledge Editing for Large Language Models
Ningyu Zhang, Yunzhi Yao, Bozhong Tian +19
Large Language Models (LLMs) have shown extraordinary capabilities in understanding and generating text that closely mirrors human communication. However, a primary limitation lies…
Towards A Unified View of Answer Calibration for Multi-Step Reasoning
Shumin Deng, Ningyu Zhang, Nay Oo +1
Large Language Models (LLMs) employing Chain-of-Thought (CoT) prompting have broadened the scope for improving multi-step reasoning capabilities. We generally divide multi-step rea…
Agents: An Open-source Framework for Autonomous Language Agents
Wangchunshu Zhou, Yuchen Eleanor Jiang, Long Li +15
Recent advances on large language models (LLMs) enable researchers and developers to build autonomous language agents that can automatically solve various tasks and interact with e…
SeqGPT: An Out-of-the-box Large Language Model for Open Domain Sequence Understanding
Tianyu Yu, Chengyue Jiang, Chao Lou +12
Large language models (LLMs) have shown impressive ability for open-domain NLP tasks. However, LLMs are sometimes too footloose for natural language understanding (NLU) tasks which…
How to Unleash the Power of Large Language Models for Few-shot Relation Extraction?
Xin Xu, Yuqi Zhu, Xiaohan Wang +1
Scaling language models have revolutionized widespread NLP tasks, yet little comprehensively explored few-shot relation extraction with large language models. In this paper, we inv…
SPEECH: Structured Prediction with Energy-Based Event-Centric Hyperspheres
Shumin Deng, Shengyu Mao, Ningyu Zhang +1
Event-centric structured prediction involves predicting structured outputs of events. In most NLP cases, event structures are complex with manifold dependency, and it is challengin…
Editing Large Language Models: Problems, Methods, and Opportunities
Yunzhi Yao, Peng Wang, Bozhong Tian +5
Despite the ability to train capable LLMs, the methodology for maintaining their relevancy and rectifying errors remains elusive. To this end, the past few years have witnessed a s…
LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunities
Yuqi Zhu, Xiaohan Wang, Jing Chen +6
This paper presents an exhaustive quantitative and qualitative evaluation of Large Language Models (LLMs) for Knowledge Graph (KG) construction and reasoning. We engage in experime…
Making Language Models Better Tool Learners with Execution Feedback
Shuofei Qiao, Honghao Gui, Chengfei Lv +3
Tools serve as pivotal interfaces that enable humans to understand and reshape the environment. With the advent of foundation models, AI systems can utilize tools to expand their c…
InstructIE: A Bilingual Instruction-based Information Extraction Dataset
Honghao Gui, Shuofei Qiao, Jintian Zhang +6
Large language models can perform well on general natural language tasks, but their effectiveness is still suboptimal for information extraction (IE). Recent works indicate that th…
Knowledge Rumination for Pre-trained Language Models
Yunzhi Yao, Peng Wang, Shengyu Mao +4
Previous studies have revealed that vanilla pre-trained language models (PLMs) lack the capacity to handle knowledge-intensive NLP tasks alone; thus, several works have attempted t…
Schema-adaptable Knowledge Graph Construction
Hongbin Ye, Honghao Gui, Xin Xu +3
Conventional Knowledge Graph Construction (KGC) approaches typically follow the static information extraction paradigm with a closed set of pre-defined schema. As a result, such ap…
Continual Multimodal Knowledge Graph Construction
Xiang Chen, Jintian Zhang, Xiaohan Wang +5
Current Multimodal Knowledge Graph Construction (MKGC) models struggle with the real-world dynamism of continuously emerging entities and relations, often succumbing to catastrophi…
One Model for All Domains: Collaborative Domain-Prefix Tuning for Cross-Domain NER
Xiang Chen, Lei Li, Shuofei Qiao +5
Cross-domain NER is a challenging task to address the low-resource problem in practical scenarios. Previous typical solutions mainly obtain a NER model by pre-trained language mode…
Editing Language Model-based Knowledge Graph Embeddings
Siyuan Cheng, Ningyu Zhang, Bozhong Tian +3
Recently decades have witnessed the empirical success of framing Knowledge Graph (KG) embeddings via language models. However, language model-based KG embeddings are usually deploy…
Reasoning with Language Model Prompting: A Survey
Shuofei Qiao, Yixin Ou, Ningyu Zhang +6
Reasoning, as an essential ability for complex problem-solving, can provide back-end support for various real-world applications, such as medical diagnosis, negotiation, etc. This…
Towards Realistic Low-resource Relation Extraction: A Benchmark with Empirical Baseline Study
Xin Xu, Xiang Chen, Ningyu Zhang +3
This paper presents an empirical study to build relation extraction systems in low-resource settings. Based upon recent pre-trained language models, we comprehensively investigate…
Multimodal Analogical Reasoning over Knowledge Graphs
Ningyu Zhang, Lei Li, Xiang Chen +3
Analogical reasoning is fundamental to human cognition and holds an important place in various fields. However, previous studies mainly focus on single-modal analogical reasoning a…
Good Visual Guidance Makes A Better Extractor: Hierarchical Visual Prefix for Multimodal Entity and Relation Extraction
Xiang Chen, Ningyu Zhang, Lei Li +6
Multimodal named entity recognition and relation extraction (MNER and MRE) is a fundamental and crucial branch in information extraction. However, existing approaches for MNER and…
Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion
Xiang Chen, Ningyu Zhang, Lei Li +6
Multimodal Knowledge Graphs (MKGs), which organize visual-text factual knowledge, have recently been successfully applied to tasks such as information retrieval, question answering…
Relation Extraction as Open-book Examination: Retrieval-enhanced Prompt Tuning
Xiang Chen, Lei Li, Ningyu Zhang +4
Pre-trained language models have contributed significantly to relation extraction by demonstrating remarkable few-shot learning abilities. However, prompt tuning methods for relati…
Contrastive Demonstration Tuning for Pre-trained Language Models
Xiaozhuan Liang, Ningyu Zhang, Siyuan Cheng +3
Pretrained language models can be effectively stimulated by textual prompts or demonstrations, especially in low-data scenarios. Recent works have focused on automatically searchin…
From Discrimination to Generation: Knowledge Graph Completion with Generative Transformer
Xin Xie, Ningyu Zhang, Zhoubo Li +5
Knowledge graph completion aims to address the problem of extending a KG with missing triples. In this paper, we provide an approach GenKGC, which converts knowledge graph completi…
Ontology-enhanced Prompt-tuning for Few-shot Learning
Hongbin Ye, Ningyu Zhang, Shumin Deng +5
Few-shot Learning (FSL) is aimed to make predictions based on a limited number of samples. Structured data such as knowledge graphs and ontology libraries has been leveraged to ben…