Publications

2024

Peer-reviewed

[28] 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

[27] 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

[26] 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

[25] Asymmetric Bias in Text-to-Image Generation with Adversarial Attacks

Haz Sameen Shahgir, Xianghao Kong, Greg Ver Steeg, Yue Dong

ACL Findings 2024

[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] Source-Free Domain Adaptation for Question Answering with Masked Self-training

Maxwell Yin, Boyu Wang, Yue Dong, Charles Ling

TACL 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

[19] Watermarking conditional text generation for AI detection: Unveiling challenges and a semantic-aware watermark remedy

Yu Fu, Deyi Xiong, Yue Dong

AAAI 2024

Pre-prints

• TRAWL: Tensor Reduced and Approximated Weights for Large Language Models

Y Luo, H Patel, Y Fu, D Ahn, J Chen, Yue Dong, EE Papalexakis

arXiv preprint arXiv:2406.17261

• Progressive Query Expansion for Retrieval Over Cost-constrained Data Sources

MS Rashid, JA Meem, Yue Dong, V Hristidis

arXiv preprint arXiv:2406.07136

• PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling

Y Zhang, B Gao, T Liu, K Lu, W Xiong, Yue Dong, B Chang, J Hu, W Xiao

arXiv preprint arXiv:2406.02069

• Cross-Modal Safety Alignment: Is textual unlearning all you need?

T Chakraborty, E Shayegani, Z Cai, N Abu-Ghazaleh, MS Asif, Yue Dong

arXiv preprint arXiv:2406.02575

• Uncertainty Awareness of Large Language Models Under Code Distribution Shifts: A Benchmark Study

Y Li, S Chen, Y Guo, W Yang, Yue Dong, C Liu

arXiv preprint arXiv:2402.05939

• BiRNA-BERT Allows Efficient RNA Language Modeling with Adaptive Tokenization

MT Tahmid, HS Shahgir, S Mahbub, Yue Dong, MS Bayzid

bioRxiv

• Mechanisms of non-factual hallucinations in language models

L Yu, M Cao, JCK Cheung, Yue Dong

arXiv preprint arXiv:2403.18167

2023

[18] Survey of vulnerabilities in large language models revealed by adversarial attacks

[17] Inverse Reinforcement Learning for Text Summarization

2022

[16] Learning with Rejection for Abstractive Text Summarization

[15] Hallucinated but factual! inspecting the factuality of hallucinations in abstractive summarization

[14] Faithful to the document or to the world? mitigating hallucinations via entity-linked knowledge in abstractive summarization

2021

[13] On-the-fly attention modulation for neural generation

[12] Bringing structure into summaries: a faceted summarization dataset for long scientific documents

[11] Discourse-Aware Unsupervised Summarization of Long Scientific Documents

2020

[10] Factual error correction for abstractive summarization models

[9] Multi-XScience: A large-scale dataset for extreme multi-document summarization of scientific articles

[8] Multi-fact correction in abstractive text summarization

2019

[7] Countering the Effects of Lead Bias in News Summarization via Multi-Stage Training and Auxiliary Losses

[6] Learning multi-task communication with message passing for sequence learning

[5] EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing

Before 2018

[4] Banditsum: Extractive summarization as a contextual bandit

[3] Threaded ensembles of autoencoders for stream learning

[2] A hierarchical neural attention-based text classifier

[1] Threaded ensembles of supervised and unsupervised neural networks for stream learning