CS faculty and students publish 27 papers at EMNLP 2024

12/12/2024 Bruce Adams

The Grainger College of Engineering Siebel School of Computing and Data Science was well represented at EMNLP 2024 in Miami, FL, November 12-16, 2024. Three papers were published by U. of I. researchers at the Workshop on Computational Models of Reference, Anaphora and Coreference, Workshop on Customizable NLP, and the SIGNLL Conference on Computational Natural Language Learning (CONLL2024). Twenty-four papers were submitted and published at the main conference.

Written by Bruce Adams

The Grainger College of Engineering Siebel School of Computing and Data Science was well represented at EMNLP 2024 in Miami, FL, November 12-16, 2024. Three papers were published by University of Illinois Urbana-Champaign researchers at the Workshop on Computational Models of Reference, Anaphora and Coreference, Workshop on Customizable NLP, and the SIGNLL Conference on Computational Natural Language Learning (CONLL 2024). Twenty-four papers were submitted and published at the main conference.

A very large group of people at a conference pose and smile for the camera.

CS professors Heng Ji, Tong Zhang, Dilek Hakkani-Tür, Gokhan Tür, Jiawei HanTal August, ChenXiang Zhai, Klara Nahrstedt  and Julia Hockenmaier all had papers published in collaboration with an extensive group of CD PhD students.

Published at EMNLP 2024 Main Conference

Authors: Jiateng Liu, Pengfei Yu, Yuji Zhang, Sha Li, Zixuan Zhang, Ruhi Sarikaya, Kevin Small, Heng Ji
Paper Title: EVEDIT: Event-based Knowledge Editing for Deterministic Knowledge Propagation

Authors: Xinyu Pi, Mingyuan Wu, Jize Jiang, Haozhen Zheng, Beitong Tian, Chenxiang Zhai, Klara Nahrstedt, Zhiting Hu
Paper Title: UOUO: Uncontextualized Uncommon Objects for Measuring Knowledge Horizons of Vision Language Models
 

Authors: Priyanka Kargupta, Ishika Agarwal, Dilek Hakkani-Tur, Jiawei Ha
Paper Title: Instruct, Not Assist: LLM-based Multi-Turn Planning and Hierarchical Questioning for Socratic Code Debugging

Authors: Sha Li, Revanth Gangi Reddy, Khanh Duy Nguyen, Qingyun Wang, Yi Fung, Chi Han, Jiawei Han, Kartik Natarajan, Clare R. Voss, Heng Ji
Paper Title: Schema-Guided Culture-Aware Complex Event Simulation with Multi-Agent Role-Play

Authors: Jiaxin Qin, Zixuan Zhang, Chi Han, Pengfei Yu, Manling Li, Heng Ji
Paper Title: Why Does New Knowledge Create Messy Ripple Effects in LLMs?

Authors: Shujin Wu, May Fung, Sha Li, Yixin Wan, Kai-Wei Chang, Heng Ji
Paper Title:  MACAROON: Training Vision-Language Models To Be Your Engaged Partners

Authors: Yong Lin, Hangyu Lin, Wei Xiong, Shizhe Diao, Jianmeng Liu, Jipeng Zhang, Rui Pan, Haoxiang Wang, Wenbin Hu, Hanning Zhang, Hanze Dong, Renjie Pi, Han Zhao, Nan Jiang, Heng Ji, Yuan Yao, Tong Zhang
Paper Title: Mitigating the Alignment Tax of RLHF

Authors: Haoxiang Wang, Wei Xiong, Tengyang Xie, Han Zhao, Tong Zhang
Paper Title: Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts

Authors: Renjie Pi, Tianyang Han, Yueqi Xie, Rui Pan, Qing Lian, Hanze Dong, Jipeng Zhang, Tong Zhang
Paper Title: MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance

Authors: Tianyang Han, Qing Lian, Rui Pan, Renjie Pi, Jipeng Zhang, Shizhe Diao, Yong Lin, Tong Zhang
Paper Title: The Instinctive Bias: Spurious Images Lead to Hallucination in MLLMs

Authors: Ruida Wang, Jipeng Zhang, Yizhen Jia, Rui Pan, Shizhe Diao, Renjie Pi, Tong Zhang
Paper Title: TheoremLlama: Transforming General-Purpose LLMs into Lean4 Experts

Authors: Jeonghwan Kim, Heng Ji
Paper Title: Finer: Investigating and Enhancing Fine-Grained Visual Concept Recognition in Large Vision Language Models

Authors: Sumuk Shashidhar, Abhinav Chinta, Vaibhav Sahai, Dilek Hakkani-Tür
Paper Title: Unsupervised Human Preference Learning

Authors: Ikhyun Cho, Gaeul Kwon, Julia Hockenmaier
Paper Title: Tutor-ICL: Guiding Large Language Models for Improved In-Context Learning Performance

Authors: Linyi Ding, Jinfeng Xiao*, Sizhe Zhou, Chaoqi Yang, Jiawei Han
Paper Title: Topic-Oriented Open Relation Extraction with A Priori Seed Generation

Author: Mengfei Lan, Lecheng Zheng, Shufan Ming, Halil Kilicoglu
Paper Title: Multi-label Sequential Sentence Classification via Large Language Model

Authors: SeongKu Kang, Yunyi Zhang, Pengcheng Jiang, Dongha Lee, Jiawei Han, Hwanjo Yu,
Paper Title: Taxonomy-guided Semantic Indexing for Academic Paper Search 

Authors:  Yu Zhang, Xiusi Chen, Bowen Jin, Sheng Wang, Shuiwang Ji, Wei Wang, Jiawei Han
Paper Title: A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery

Authors: Sizhe Zhou, Yu Meng, Bowen Jin, Jiawei Han
Paper Title: Grasping the Essentials: Tailoring Large Language Models for Zero-Shot Relation Extraction 

Authors: Siru Ouyang, Shuohang Wang, Minhao Jiang, Ming Zhong, Donghan Yu, Jiawei Han, Yelong Shen
Paper Title: Temperature-Centric Investigation of Speculative Decoding with Knowledge Distillation 

Authors: Revanth Gangi Reddy, Omar Attia, Yunyao Li, Heng Ji, Saloni Potdar
Paper Title: AGRaME: Any-Granularity Ranking with Multi-Vector Embeddings

Authors: Revanth Gangi Reddy, JaeHyeok Doo, Yifei Xu, Md Arafat Sultan, Deevya Swain, Avirup Sil, Heng Ji
Paper Title: FIRST: Faster Improved Listwise Reranking with Single Token Decoding

Authors: Zhiwen You, Kanyao Han, Haotian Zhu, Bertram Ludaescher, Jana Diesner
Paper Title: SciPrompt: Knowledge-augmented Prompting for Fine-grained Categorization of Scientific Topics

Authors: Li Lucy, Tal August, Rose E. Wang, Luca Soldaini, Courtney Allison, Kyle Lo
Title: MathFish: Evaluating Language Model Math Reasoning via Grounding in Educational Curricula (Findings)

Authors: Yue Guo, Tal August, Gondy Leroy, Trevor Cohen, Lucy Lu Wang
Title: APPLS: Evaluating Evaluation Metrics for Plain Language Summarization

Authors: Xudong Lin, Manling Li, Richard Zemel, Heng Ji, Shih-Fu Chang
Title: Training-free Deep Concept Injection Enables Language Models for Video Question Answering

Authors: Xiangru Tang, Chunyuan Deng, Hanmin Wang, Haoran Wang, Yilun Zhao, Wenqi Shi, Yi Fung, Wangchunshu Zhou, Jiannan Cao, Heng Ji, Arman Cohan, Mark Gerstein
Title: MIMIR: A Customizable Agent Tuning Platform for Enhanced Scientific Applications

Published at EMNLP 2024 Workshops

Proc. EMNLP2024 Workshop on Computational Models of Reference, Anaphora and Coreference
Authors: Zixuan Zhang and Heng Ji
Title: Enriching Conceptual Knowledge in Language Models through Metaphorical Reference Explanation

Proc. EMNLP2024 Workshop on Customizable NLP
Authors: Yangyi Chen, Binxuan Huang, Yifan Gao, Zhengyang Wang, Jingfeng Yang and Heng Ji
Title: Scaling Laws for Predicting Downstream Performance in LLMs

Proc. The SIGNLL Conference on Computational Natural Language Learning (CONLL2024)
Authors: Pengfei Yu and Heng Ji
Title: Information Association for Language Model Updating by Mitigating LM-Logical Discrepancy


Grainger Engineering Affiliations

Heng Ji is an Illinois Grainger Engineering professor of computer science and is affiliated with electrical and computer engineering and coordinated science laboratory.  

Tong Zhang is an Illinois Grainger Engineering professor of computer science. 

Dilek Hakkani-Tür is an Illinois Grainger Engineering professor of computer science. 

Gokhan Tür is an Illinois Grainger Engineering professor of computer science. 

Jiawei Han is an Illinois Grainger Engineering professor of computer science. Jiawei Han holds the Michael Aiken Chair. 

Julia Hockenmaier is an Illinois Grainger Engineering professor of computer science. Julia Hockenmaier holds the Willett Faculty Scholar position. 

Tal August is an Illinois Grainger Engineering professor of computer science. 

ChenXiang Zhai is an Illinois Grainger Engineering professor of computer science. ChenXiag Zhai is Donald Biggar Willett Professor in Engineering. 

Klara Nahrstedt is an Illinois Grainger Engineering professor of computer science and is director of the Coordinated Science Laboratory. Klara Nahrstedt holds the Swanlund Endowed Chair and Grainger Distinguished Chair in Engineering. 

 


Share this story

This story was published December 12, 2024.