• [05/2025] Our paper “Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models” was accepted to ICML as a spotlight poster.

• [2/2025] Our paper “TRAWL: Tensor Reduced and Approximated Weights for Large Language Models” was accepted to PAKDD 2025 workshop.

• [1/2025] Our paper “VIKI: Systematic Cross-Platform Profile Inference of Tech Users” was accepted to WebSci 2025.

• [1/2025] Our paper “LaMMA-P: Generalizable Multi-Agent Long-Horizon Task Allocation and Planning with LM-Driven PDDL Planner” has been accepted at ICRA 2025.

• [1/2025] Our paper Not all heads matter: A head-level KV cache compression method with integrated retrieval and reasoning, led by my PhD student Yu Fu, has been accepted into ICLR 2025!

• [11/2024] I am honored to serve as a senior area chair for ACL 2025.

• [10/2024] 5 papers from my group have been accepted to SoCal NLP Symposium 2024.

• [9/2024] Three papers on hallucination interpretability, cross-modal unlearning, and adversarial attacks have been accepted to EMNLP Findings.

• [9/2024] I am honored to serve as a senior area chair for NAACL 2025 and area chair for ICLR 2025.

• [7/2024] Our paper on Personalized Conversational Information Retrieval has been accepted at CIKM 2024.

Welcome to UCR NLP Lab!

Lab Members

Director

Yue Dong, assistant professor of computer science and engineering

PhD Students

• Yu Fu, since Fall 2023

  • 2023:EMNLP 2023 Findings

  • 2024: AAAI 2024, NNACL 2024 TrustNLP workshop, ACL 2024, Microsoft 24 Summer Intern

  • 2025: PAKDD 2025, ICLR 2025, Amazon 25 Summer Intern

• Erfan Shayegani (co-advise with Prof. Nael B. Abu-Ghazaleh), since Summer 2023

Publications

2025

[35] Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models
Saketh Bachu, Erfan Shayegani, Rohit Lal, Trishna Chakraborty, Arindam Dutta, Chengyu Song, Yue Dong, Nael B. Abu-Ghazaleh, Amit Roy-Chowdhury
ICML 2025

[34] LaMMA-P: Generalizable Multi-Agent Long-Horizon Task Allocation and Planning with LM-Driven PDDL Planner
Xiaopan Zhang*, Hao Qin*, Fuquan Wang, Yue Dong, Jiachen Li
ICRA 2025

[33] Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning
Yu Fu, Zefan Cai, Abedelkadir Asi, Wayne Xiong, Yue Dong, Wen Xiao
ICLR 2025

2024

[32] Mechanisms of non-factual hallucinations in language models
Yu Lei, Meng Cao, JCK Cheung, Yue Dong
EMNLP 2024 Findings

[31] Adversarial Attacks on Parts of Speech: An Empirical Study in Text-to-Image Generation
GM Shahariar, Jia Chen, Jiachen Li, Yue Dong
EMNLP 2024 Findings

[30] How to Leverage Personal Textual Knowledge for Personalized Conversational Information Retrieval
Fengran Mo, Longxiang Zhao, Kaiyu Huang, Yue Dong, Degen Huang, Jian-Yun Nie
CIKM 2024

[29] IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models
Haz Sameen Shahgir, Khondker Salman Sayeed, Abhik Bhattacharjee, Wasi Uddin Ahmad, Yue Dong, Rifat Shahriyar
Conference on Language Modeling (COLM) 2024

[28] Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack
Yu Fu, Yufei Li, Wen Xiao, Cong Liu, Yue Dong
ACL 2024

[27] Source-Free Domain Adaptation for Question Answering with Masked Self-training
Maxwell Yin, Boyu Wang, Yue Dong, Charles Ling
TACL 2024

[26] Asymmetric Bias in Text-to-Image Generation with Adversarial Attacks
Haz Sameen Shahgir, Xianghao Kong, Greg Ver Steeg, Yue Dong
ACL Findings 2024

[25] Cross-Modal Safety Alignment: Is textual unlearning all you need?
Trishna Chakraborty, Erfan Shayegani, Zikui Cai, Nael Abu-Ghazaleh, M Salman Asif, Yue Dong, Amit Roy-Chowdhury, Chengyu Song
EMNLP 2024 Findings

[24] Subtle Misogyny Detection and Mitigation: An Expert-Annotated Dataset
Brooklyn Sheppard, Anna Richter, Allison Cohen, Elizabeth Allyn Smith, Tamara Kneese, Carolyne Pelletier, Ioana Baldini, Yue Dong
ACL Findings 2024

[23] Cross-task defense: Instruction-tuning LLMs for content safety
Yu Fu, Wen Xiao, Jia Chen, Jiachen Li, Evangelos Papalexakis, Aichi Chien, Yue Dong
TrustNLP Workshop @ NAACL 2024

[22] PAT-Questions: A Self-Updating Benchmark for Present-Anchored Temporal Question-Answering
Jannat Ara Meem, Muhammad Shihab Rashid, Yue Dong, Vagelis Hristidis
ACL Findings 2024

[21] EcoRank: Budget-Constrained Text Re-ranking Using Large Language Models
Muhammad Shihab Rashid, Jannat Ara Meem, Yue Dong, Vagelis Hristidis
ACL Findings 2024

[20] Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models
Erfan Shayegani, Yue Dong, Nael Abu-Ghazaleh
ICLR 2024 (Spotlight), Best Paper Award at 2023 SoCal NLP Symposium

[19] Watermarking conditional text generation for AI detection: Unveiling challenges and a semantic-aware watermark remedy
Yu Fu, Deyi Xiong, Yue Dong
AAAI 2024

2023

[18] Subtle Misogyny Detection and Mitigation: An Expert-Annotated Dataset
Brooklyn Sheppard, Anna Richter, Allison Cohen, Elizabeth Allyn Smith, Tamara Kneese, Carolyne Pelletier, Ioana Baldini, Yue Dong
NeurIPS 2023 SoLaR Workshop (Spotlight)

[17] Inverse Reinforcement Learning for Text Summarization
Yu Fu, Deyi Xiong, Yue Dong
Findings of EMNLP 2023

• [Spring 2024] CS 173 - Introduction to Natural Language Processing

• [Winter 2024] CS 222 - Natural Language Processing

• [Spring 2023] CS 173 - Introduction to Natural Language Processing

• [Winter 2023] CS 260 - Seminar in Natural Language Processing

Lead-organizer

• ACL 2024 Tutorial on Vulnerabilities of Large Language Models to Adversarial Attacks

• EMNLP 2023 workshop on New Frontiers in Summarization

Co-organizer

• NeurIPS 2024 workshop on [Efficient Natural Language and Speech Processing (ENLSP-IV)]

• NeurIPS 2023 workshop on Efficient Natural Language and Speech Processing (ENLSP-III)

• KDD 2023 tutorial on Fast Text Generation with Text-Editing Models

• NeurIPS 2022 workshop on Efficient Natural Language and Speech Processing (ENLSP-II)

• EMNLP 2021 workshop on New Frontiers in Summarization

Invited talks

• [11/2023] Exploring Safety in Large Language Models YouTube 40:30 mins | News

  • 80th Annual Convention of Jiaotong University Alumni Association in SoCal (交通大学南加州校友会80周年庆), Los Angeles, CA, US

• [11/04/2023] AI and Large Language Models

  • UCR Family Day/Homecoming seminar, Riverside CA, US

• [08/2023] Fast Text Generation with Text-Editing Models

  • KDD Tutorial, Long Beach, CA, US

Fundings:

• NSF CISE MSI, Co-PI, Jan. 2025- Dec. 2027

• UTCRS, Co-PI, June 2024 - June 2025

• Regents Faculty Fellowship grant, PI, July 2023 - June 2025

• UCR OASIS Internal Funding Awards, PI, June 2023 - June 2024

Academic Awards:

• Best Paper Award, Southern California NLP Symposium, 2023

• Alexander Graham Bell Canada Graduate Scholarship - Doctoral (CGS D) - Accepted, 2018-2019

• [ Best Paper Award ] at Canadian conference on artificial intelligence

• NSERC Postgraduate Scholarship - Doctoral (PGS D) - Accepted, 2017-2018

• FRQNT Doctoral Scholarship - Declined (rank first in all 2016 applicants in mathematics), 2016

• FRQNT Master’s Research Scholarship, 2016

• NSERC Canada Graduate Scholarships - CGS Master’s, 2015

• University of Ottawa Excellence Scholarship, 2015 - 2016

• NSERC Undergraduate Student Research Awards (USRA), Summer 2014

• Dean’s Merit Scholarships - Faculty of Science, University of Ottawa, 2014

• University of Ottawa Women’s Summer Research Award, Summer 2013

• University of Ottawa Work/Study Research Award, Summer 2012