Search Results for author:
Found 65 papers, 50 papers with code
Good Visual Guidance Make A Better Extractor: Hierarchical Visual Prefix for Multimodal Entity and Relation Extraction
Multimodal named entity recognition and relation extraction (MNER and MRE) is a fundamental and crucial branch in information extraction.
ZJUKLAB at SemEval-2025 Task 4: Unlearning via Model Merging
This paper presents the ZJUKLAB team's submission for SemEval-2025 Task 4: Unlearning Sensitive Content from Large Language Models.
CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners
Knowledge Editing (KE) enables the modification of outdated or incorrect information in large language models (LLMs).
ReLearn: Unlearning via Learning for Large Language Models
Current unlearning methods for large language models usually rely on reverse optimization to reduce target token probabilities.
How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training
Despite exceptional capabilities in knowledge-intensive tasks, Large Language Models (LLMs) face a critical gap in understanding how they internalize new knowledge, particularly how to structurally embed acquired knowledge in their neural computations.
Exploring Model Kinship for Merging Large Language Models
With comprehensive empirical analysis, we find that there is a certain relationship between model kinship and the performance gains after model merging, which can help guide our selection of candidate models.
MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation
Multimodal Large Language Models (MLLMs) frequently exhibit hallucination phenomena, but the underlying reasons remain poorly understood.
FlipAttack: Jailbreak LLMs via Flipping
Second, we verify the strong ability of LLMs to perform the text-flipping task, and then develop 4 variants to guide LLMs to denoise, understand, and execute harmful behaviors accurately.
OneEdit: A Neural-Symbolic Collaboratively Knowledge Editing System
Knowledge representation has been a central aim of AI since its inception.
Knowledge Mechanisms in Large Language Models: A Survey and Perspective
Understanding knowledge mechanisms in Large Language Models (LLMs) is crucial for advancing towards trustworthy AGI.
Knowledge Circuits in Pretrained Transformers
To date, most studies have concentrated on isolated components within these models, such as the Multilayer Perceptrons and attention head.
DnA-Eval: Enhancing Large Language Model Evaluation through Decomposition and Aggregation
The acceleration of Large Language Models (LLMs) research has opened up new possibilities for evaluating generated texts.
Agent Planning with World Knowledge Model
Imitating humans' mental world knowledge model which provides global prior knowledge before the task and maintains local dynamic knowledge during the task, in this paper, we introduce parametric World Knowledge Model (WKM) to facilitate agent planning.
Detoxifying Large Language Models via Knowledge Editing
This paper investigates using knowledge editing techniques to detoxify Large Language Models (LLMs).
Editing Conceptual Knowledge for Large Language Models
Recently, there has been a growing interest in knowledge editing for Large Language Models (LLMs).
KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents
Large Language Models (LLMs) have demonstrated great potential in complex reasoning tasks, yet they fall short when tackling more sophisticated challenges, especially when interacting with environments through generating executable actions.
KnowPhish: Large Language Models Meet Multimodal Knowledge Graphs for Enhancing Reference-Based Phishing Detection
Phishing attacks have inflicted substantial losses on individuals and businesses alike, necessitating the development of robust and efficient automated phishing detection approaches.
A Comprehensive Study of Knowledge Editing for Large Language Models
In this paper, we first define the knowledge editing problem and then provide a comprehensive review of cutting-edge approaches.
Ranked #1 on
knowledge editing
on zsRE
(using extra training data)
Towards A Unified View of Answer Calibration for Multi-Step Reasoning
Large Language Models (LLMs) employing Chain-of-Thought (CoT) prompting have broadened the scope for improving multi-step reasoning capabilities.
Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View
This paper probes the collaboration mechanisms among contemporary NLP systems by melding practical experiments with theoretical insights.
When Do Program-of-Thoughts Work for Reasoning?
Although there are effective methods like program-of-thought prompting for LLMs which uses programming language to tackle complex reasoning tasks, the specific impact of code data on the improvement of reasoning capabilities remains under-explored.
From Sky to the Ground: A Large-scale Benchmark and Simple Baseline Towards Real Rain Removal
Learning-based image deraining methods have made great progress.
SPEECH: Structured Prediction with Energy-Based Event-Centric Hyperspheres
Event-centric structured prediction involves predicting structured outputs of events.
LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunities
We engage in experiments across eight diverse datasets, focusing on four representative tasks encompassing entity and relation extraction, event extraction, link prediction, and question-answering, thereby thoroughly exploring LLMs' performance in the domain of construction and inference.
Editing Large Language Models: Problems, Methods, and Opportunities
Our objective is to provide valuable insights into the effectiveness and feasibility of each editing technique, thereby assisting the community in making informed decisions on the selection of the most appropriate method for a specific task or context.
Reasoning with Language Model Prompting: A Survey
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.
Schema-aware Reference as Prompt Improves Data-Efficient Knowledge Graph Construction
With the development of pre-trained language models, many prompt-based approaches to data-efficient knowledge graph construction have been proposed and achieved impressive performance.
Multimodal Analogical Reasoning over Knowledge Graphs
Analogical reasoning is fundamental to human cognition and holds an important place in various fields.
Construction and Applications of Billion-Scale Pre-Trained Multimodal Business Knowledge Graph
We release all the open resources (OpenBG benchmarks) derived from it for the community and report experimental results of KG-centric tasks.
Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learning
Specifically, vanilla prompt learning may struggle to utilize atypical instances by rote during fully-supervised training or overfit shallow patterns with low-shot data.
Good Visual Guidance Makes A Better Extractor: Hierarchical Visual Prefix for Multimodal Entity and Relation Extraction
To deal with these issues, we propose a novel Hierarchical Visual Prefix fusion NeTwork (HVPNeT) for visual-enhanced entity and relation extraction, aiming to achieve more effective and robust performance.
Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion
Since most MKGs are far from complete, extensive knowledge graph completion studies have been proposed focusing on the multimodal entity, relation extraction and link prediction.
Information Extraction in Low-Resource Scenarios: Survey and Perspective
Information Extraction (IE) seeks to derive structured information from unstructured texts, often facing challenges in low-resource scenarios due to data scarcity and unseen classes.
From Discrimination to Generation: Knowledge Graph Completion with Generative Transformer
Knowledge graph completion aims to address the problem of extending a KG with missing triples.
Ranked #51 on
Link Prediction
on FB15k-237
Ontology-enhanced Prompt-tuning for Few-shot Learning
Specifically, we develop the ontology transformation based on the external knowledge graph to address the knowledge missing issue, which fulfills and converts structure knowledge to text.
OntoProtein: Protein Pretraining With Gene Ontology Embedding
We construct a novel large-scale knowledge graph that consists of GO and its related proteins, and gene annotation texts or protein sequences describe all nodes in the graph.
DeepKE: A Deep Learning Based Knowledge Extraction Toolkit for Knowledge Base Population
We present an open-source and extensible knowledge extraction toolkit DeepKE, supporting complicated low-resource, document-level and multimodal scenarios in the knowledge base population.
Knowledge Graph Embedding in E-commerce Applications: Attentive Reasoning, Explanations, and Transferable Rules
We first identity three important desiderata for e-commerce KG systems: 1) attentive reasoning, reasoning over a few target relations of more concerns instead of all; 2) explanation, providing explanations for a prediction to help both users and business operators understand why the prediction is made; 3) transferable rules, generating reusable rules to accelerate the deployment of a KG to new systems.
LOGEN: Few-shot Logical Knowledge-Conditioned Text Generation with Self-training
Previous works leverage logical forms to facilitate logical knowledge-conditioned text generation.
Molecular Contrastive Learning with Chemical Element Knowledge Graph
To address these issues, we construct a Chemical Element Knowledge Graph (KG) to summarize microscopic associations between elements and propose a novel Knowledge-enhanced Contrastive Learning (KCL) framework for molecular representation learning.
Learning to Ask for Data-Efficient Event Argument Extraction
Event argument extraction (EAE) is an important task for information extraction to discover specific argument roles.
LightNER: A Lightweight Tuning Paradigm for Low-resource NER via Pluggable Prompting
Most NER methods rely on extensive labeled data for model training, which struggles in the low-resource scenarios with limited training data.
Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners
Large-scale pre-trained language models have contributed significantly to natural language processing by demonstrating remarkable abilities as few-shot learners.
Ranked #1 on
Few-Shot Learning
on CR
Document-level Relation Extraction as Semantic Segmentation
Specifically, we leverage an encoder module to capture the context information of entities and a U-shaped segmentation module over the image-style feature map to capture global interdependency among triples.
Ranked #4 on
Relation Extraction
on GDA
AliCG: Fine-grained and Evolvable Conceptual Graph Construction for Semantic Search at Alibaba
Conceptual graphs, which is a particular type of Knowledge Graphs, play an essential role in semantic search.
OntoED: Low-resource Event Detection with Ontology Embedding
Most of current methods to ED rely heavily on training instances, and almost ignore the correlation of event types.
MLBiNet: A Cross-Sentence Collective Event Detection Network
We consider the problem of collectively detecting multiple events, particularly in cross-sentence settings.
KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction
To this end, we focus on incorporating knowledge among relation labels into prompt-tuning for relation extraction and propose a Knowledge-aware Prompt-tuning approach with synergistic optimization (KnowPrompt).
Ranked #5 on
Dialog Relation Extraction
on DialogRE
(F1 (v1) metric)
Disentangled Contrastive Learning for Learning Robust Textual Representations
Although the self-supervised pre-training of transformer models has resulted in the revolutionizing of natural language processing (NLP) applications and the achievement of state-of-the-art results with regard to various benchmarks, this process is still vulnerable to small and imperceptible permutations originating from legitimate inputs.
Text-guided Legal Knowledge Graph Reasoning
In this paper, we propose a novel legal application of legal provision prediction (LPP), which aims to predict the related legal provisions of affairs.
Normal vs. Adversarial: Salience-based Analysis of Adversarial Samples for Relation Extraction
Recent neural-based relation extraction approaches, though achieving promising improvement on benchmark datasets, have reported their vulnerability towards adversarial attacks.
ZJUKLAB at SemEval-2021 Task 4: Negative Augmentation with Language Model for Reading Comprehension of Abstract Meaning
This paper presents our systems for the three Subtasks of SemEval Task4: Reading Comprehension of Abstract Meaning (ReCAM).
Ranked #1 on
Reading Comprehension
on ReCAM
(using extra training data)
Towards Robust Textual Representations with Disentangled Contrastive Learning
Although the self-supervised pre-training of transformer models has resulted in the revolutionizing of natural language processing (NLP) applications and the achievement of state-of-the-art results with regard to various benchmarks, this process is still vulnerable to small and imperceptible permutations originating from legitimate inputs.
Summarizing Chinese Medical Answer with Graph Convolution Networks and Question-focused Dual Attention
It is desirable to generate answer summaries for online search engines, particularly summaries that can reveal direct answers to questions.
Bridging Text and Knowledge with Multi-Prototype Embedding for Few-Shot Relational Triple Extraction
Current supervised relational triple extraction approaches require huge amounts of labeled data and thus suffer from poor performance in few-shot settings.
OpenUE: An Open Toolkit of Universal Extraction from Text
We introduce a prototype model and provide an open-source and extensible toolkit called OpenUE for various extraction tasks.
Ranked #3 on
Joint Entity and Relation Extraction
on WebNLG
The Devil is the Classifier: Investigating Long Tail Relation Classification with Decoupling Analysis
Long-tailed relation classification is a challenging problem as the head classes may dominate the training phase, thereby leading to the deterioration of the tail performance.
Contrastive Triple Extraction with Generative Transformer
In this paper, we revisit the end-to-end triple extraction task for sequence generation.
Ranked #9 on
Relation Extraction
on WebNLG
On Robustness and Bias Analysis of BERT-based Relation Extraction
Fine-tuning pre-trained models have achieved impressive performance on standard natural language processing benchmarks.
Relation Adversarial Network for Low Resource Knowledge Graph Completion
Specifically, the framework takes advantage of a relation discriminator to distinguish between samples from different relations, and help learn relation-invariant features more transferable from source relations to target relations.
Meta-Learning with Dynamic-Memory-Based Prototypical Network for Few-Shot Event Detection
Differing from vanilla prototypical networks simply computing event prototypes by averaging, which only consume event mentions once, our model is more robust and is capable of distilling contextual information from event mentions for multiple times due to the multi-hop mechanism of DMNs.
When Low Resource NLP Meets Unsupervised Language Model: Meta-pretraining Then Meta-learning for Few-shot Text Classification
Text classification tends to be difficult when data are deficient or when it is required to adapt to unseen classes.
Ranked #1 on
Multi-Domain Sentiment Classification
on ARSC
Transfer Learning for Relation Extraction via Relation-Gated Adversarial Learning
However, the human annotation is expensive, while human-crafted patterns suffer from semantic drift and distant supervision samples are usually noisy.
Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks
Here, the challenge is to learn accurate "few-shot" models for classes existing at the tail of the class distribution, for which little data is available.
Attention-Based Capsule Networks with Dynamic Routing for Relation Extraction
A capsule is a group of neurons, whose activity vector represents the instantiation parameters of a specific type of entity.
