
Heng Ji
information extraction
large language model
contrastive learning
fact-checking
event extraction
large language models
relation extraction
personalization
cross-lingual transfer
social media
computational social science
pre-training
dataset
misinformation
sentiment analysis
79
presentations
172
number of views
SHORT BIO
Heng Ji is a professor at Computer Science Department, and an affiliated faculty member at Electrical and Computer Engineering Department and Coordinated Science Laboratory of University of Illinois Urbana-Champaign. She is an Amazon Scholar. She is the Director of Amazon-Illinois Center on AI for Interactive Conversational Experiences (AICE). She received her B.A. and M. A. in Computational Linguistics from Tsinghua University, and her M.S. and Ph.D. in Computer Science from New York University. Her research interests focus on Natural Language Processing, especially on Multimedia Multilingual Information Extraction, Knowledge-enhanced Large Language Models, Knowledge-driven Generation and Conversational AI.
Presentations

Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning
Kung-Hsiang Huang and 7 other authors

SciMON: Scientific Inspiration Machines Optimized for Novelty
Qingyun Wang and 3 other authors

ActionIE: Action Extraction from Scientific Literature with Programming Languages
Xianrui Zhong and 8 other authors

R-Tuning: Instructing Large Language Models to Say ‘I Don’t Know’
Hanning Zhang and 8 other authors

LETI: Learning to Generate from Textual Interactions
Xingyao Wang and 3 other authors

LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models
Chi Han and 6 other authors

Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models
Yangyi Chen and 4 other authors

Named Entity Recognition Under Domain Shift via Metric Learning for Life Sciences
Hongyi Liu and 3 other authors

Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration
Zhenhailong Wang and 5 other authors

Fact Checking Beyond Training Set
Payam Karisani and 1 other author

Towards Better Generalization in Open-Domain Question Answering by Mitigating Context Memorization
Zixuan Zhang and 4 other authors

WebWISE: Unlocking Web Interface Control for LLMs via Sequential Exploration
Heyi Tao and 5 other authors

Language + Molecules
Carl Edwards and 2 other authors

Chem-FINESE: Validating Fine-Grained Few-shot Entity Extraction through Text Reconstruction
Qingyun Wang and 6 other authors

Decoding the Silent Majority: Inducing Belief Augmented Social Graph with Large Language Model for Response Forecasting
Chenkai Sun and 6 other authors

NORMSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly | VIDEO
Yi Fung and 5 other authors