1 code implementation • 27 Mar 2024 • Lei Yu, Meng Cao, Jackie Chi Kit Cheung, Yue Dong
Our study investigates the mechanistic causes of hallucination, specifically non-factual ones where the LM incorrectly predicts object attributes in response to subject-relation queries.
1 code implementation • 23 Mar 2024 • HAZ Sameen Shahgir, Khondker Salman Sayeed, Abhik Bhattacharjee, Wasi Uddin Ahmad, Yue Dong, Rifat Shahriyar
GPT4V, the best-performing VLM, achieves 62. 99% accuracy (4-shot) on the comprehension task and 49. 7% on the localization task (4-shot and Chain-of-Thought).
Ranked #1 on Object Localization on IllusionVQA
no code implementations • 19 Feb 2024 • Chong Zeng, Yue Dong, Pieter Peers, Youkang Kong, Hongzhi Wu, Xin Tong
To provide the content creator with fine-grained control over the lighting during image generation, we augment the text-prompt with detailed lighting information in the form of radiance hints, i. e., visualizations of the scene geometry with a homogeneous canonical material under the target lighting.
no code implementations • 16 Feb 2024 • Muhammad Shihab Rashid, Jannat Ara Meem, Yue Dong, Vagelis Hristidis
We study how to maximize the re-ranking performance given a budget, by navigating the vast search spaces of prompt choices, LLM APIs, and budget splits.
no code implementations • 16 Feb 2024 • Jannat Ara Meem, Muhammad Shihab Rashid, Yue Dong, Vagelis Hristidis
Existing work on Temporal Question Answering (TQA) has predominantly focused on questions anchored to specific timestamps or events (e. g. "Who was the US president in 1970?").
1 code implementation • 12 Jan 2024 • Yufei Li, Simin Chen, Yanghong Guo, Wei Yang, Yue Dong, Cong Liu
We observe that these methods generally improve the uncertainty awareness of CodeLlama, with increased calibration quality and higher uncertainty estimation~(UE) precision.
1 code implementation • 22 Dec 2023 • HAZ Sameen Shahgir, Xianghao Kong, Greg Ver Steeg, Yue Dong
The widespread use of Text-to-Image (T2I) models in content generation requires careful examination of their safety, including their robustness to adversarial attacks.
no code implementations • 12 Dec 2023 • Yu Fu, Yufei Li, Wen Xiao, Cong Liu, Yue Dong
Recent developments in balancing the usefulness and safety of Large Language Models (LLMs) have raised a critical question: Are mainstream NLP tasks adequately aligned with safety consideration?
no code implementations • 15 Nov 2023 • Brooklyn Sheppard, Anna Richter, Allison Cohen, Elizabeth Allyn Smith, Tamara Kneese, Carolyne Pelletier, Ioana Baldini, Yue Dong
Using novel approaches to dataset development, the Biasly dataset captures the nuance and subtlety of misogyny in ways that are unique within the literature.
no code implementations • 16 Oct 2023 • Erfan Shayegani, Md Abdullah Al Mamun, Yu Fu, Pedram Zaree, Yue Dong, Nael Abu-Ghazaleh
Large Language Models (LLMs) are swiftly advancing in architecture and capability, and as they integrate more deeply into complex systems, the urgency to scrutinize their security properties grows.
1 code implementation • 25 Aug 2023 • Chong Zeng, Guojun Chen, Yue Dong, Pieter Peers, Hongzhi Wu, Xin Tong
This paper presents a novel neural implicit radiance representation for free viewpoint relighting from a small set of unstructured photographs of an object lit by a moving point light source different from the view position.
no code implementations • 26 Jul 2023 • Erfan Shayegani, Yue Dong, Nael Abu-Ghazaleh
Specifically, we develop cross-modality attacks on alignment where we pair adversarial images going through the vision encoder with textual prompts to break the alignment of the language model.
1 code implementation • 25 Jul 2023 • Yu Fu, Deyi Xiong, Yue Dong
To mitigate potential risks associated with language models, recent AI detection research proposes incorporating watermarks into machine-generated text through random vocabulary restrictions and utilizing this information for detection.
1 code implementation • 16 Feb 2023 • Meng Cao, Yue Dong, Jingyi He, Jackie Chi Kit Cheung
State-of-the-art abstractive summarization systems frequently hallucinate content that is not supported by the source document, mainly due to noise in the training dataset.
no code implementations • 19 Dec 2022 • Yu Fu, Deyi Xiong, Yue Dong
We introduce inverse reinforcement learning (IRL) as an effective paradigm for training abstractive summarization models, imitating human summarization behaviors.
no code implementations • NAACL (ACL) 2022 • Eric Malmi, Yue Dong, Jonathan Mallinson, Aleksandr Chuklin, Jakub Adamek, Daniil Mirylenka, Felix Stahlberg, Sebastian Krause, Shankar Kumar, Aliaksei Severyn
Text-editing models have recently become a prominent alternative to seq2seq models for monolingual text-generation tasks such as grammatical error correction, simplification, and style transfer.
no code implementations • 28 Apr 2022 • Yue Dong, John Wieting, Pat Verga
In this work, we show that these entities are not aberrations, but they instead require utilizing external world knowledge to infer reasoning paths from entities in the source.
1 code implementation • ACL 2022 • Meng Cao, Yue Dong, Jackie Chi Kit Cheung
State-of-the-art abstractive summarization systems often generate \emph{hallucinations}; i. e., content that is not directly inferable from the source text.
Abstractive Text Summarization Reinforcement Learning (RL) +1
1 code implementation • ACL 2021 • Rui Meng, Khushboo Thaker, Lei Zhang, Yue Dong, Xingdi Yuan, Tong Wang, Daqing He
Faceted summarization provides briefings of a document from different perspectives.
Ranked #1 on Unsupervised Extractive Summarization on FacetSum
1 code implementation • EACL 2021 • Yue Dong, Andrei Mircea, Jackie Chi Kit Cheung
We propose an unsupervised graph-based ranking model for extractive summarization of long scientific documents.
1 code implementation • ICLR 2021 • Shengyu Zhao, Jonathan Cui, Yilun Sheng, Yue Dong, Xiao Liang, Eric I Chang, Yan Xu
To overcome this challenge, we propose a generic new approach that bridges the gap between image-conditional and recent modulated unconditional generative architectures via co-modulation of both conditional and stochastic style representations.
Ranked #3 on Image Inpainting on FFHQ 512 x 512
no code implementations • Findings (ACL) 2021 • Yue Dong, Chandra Bhagavatula, Ximing Lu, Jena D. Hwang, Antoine Bosselut, Jackie Chi Kit Cheung, Yejin Choi
Despite considerable advancements with deep neural language models (LMs), neural text generation still suffers from degeneration: the generated text is repetitive, generic, self-contradictory, and often lacks commonsense.
1 code implementation • EMNLP 2020 • Yao Lu, Yue Dong, Laurent Charlin
Multi-document summarization is a challenging task for which there exists little large-scale datasets.
1 code implementation • 25 Oct 2020 • Wenxin Hou, Yue Dong, Bairong Zhuang, Longfei Yang, Jiatong Shi, Takahiro Shinozaki
In this paper, we report a large-scale end-to-end language-independent multilingual model for joint automatic speech recognition (ASR) and language identification (LID).
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
1 code implementation • EMNLP 2020 • Meng Cao, Yue Dong, Jiapeng Wu, Jackie Chi Kit Cheung
Experimental results show that our model is able to correct factual errors in summaries generated by other neural summarization models and outperforms previous models on factual consistency evaluation on the CNN/DailyMail dataset.
no code implementations • EMNLP 2020 • Yue Dong, Shuohang Wang, Zhe Gan, Yu Cheng, Jackie Chi Kit Cheung, Jingjing Liu
Pre-trained neural abstractive summarization systems have dominated extractive strategies on news summarization performance, at least in terms of ROUGE.
no code implementations • ECCV 2020 • Xin Wei, Guojun Chen, Yue Dong, Stephen Lin, Xin Tong
With the estimated lighting, virtual objects can be rendered in AR scenarios with shading that is consistent to the real scene, leading to improved realism.
1 code implementation • 1 May 2020 • Yue Dong, Andrei Mircea, Jackie C. K. Cheung
We propose an unsupervised graph-based ranking model for extractive summarization of long scientific documents.
Ranked #1 on Unsupervised Extractive Summarization on Pubmed
3 code implementations • CVPR 2020 • Shengyu Zhao, Yilun Sheng, Yue Dong, Eric I-Chao Chang, Yan Xu
In this paper, we propose an asymmetric occlusion-aware feature matching module, which can learn a rough occlusion mask that filters useless (occluded) areas immediately after feature warping without any explicit supervision.
Ranked #2 on Optical Flow Estimation on KITTI 2012
no code implementations • IJCNLP 2019 • Matt Grenander, Yue Dong, Jackie Chi Kit Cheung, Annie Louis
Sentence position is a strong feature for news summarization, since the lead often (but not always) summarizes the key points of the article.
5 code implementations • ICCV 2019 • Shengyu Zhao, Yue Dong, Eric I-Chao Chang, Yan Xu
We present recursive cascaded networks, a general architecture that enables learning deep cascades, for deformable image registration.
1 code implementation • ACL 2019 • Yue Dong, Zichao Li, Mehdi Rezagholizadeh, Jackie Chi Kit Cheung
We present the first sentence simplification model that learns explicit edit operations (ADD, DELETE, and KEEP) via a neural programmer-interpreter approach.
Ranked #2 on Text Simplification on PWKP / WikiSmall (SARI metric)
no code implementations • CVPR 2019 • Xiao Li, Yue Dong, Pieter Peers, Xin Tong
Key to our method is a novel multi-projection generative adversarial network (MP-GAN) that trains a 3D shape generator to be consistent with multiple 2D projections of the 3D shapes, and without direct access to these 3D shapes.
no code implementations • 26 Nov 2018 • Pengfei Liu, Jie Fu, Yue Dong, Xipeng Qiu, Jackie Chi Kit Cheung
We present two architectures for multi-task learning with neural sequence models.
1 code implementation • EMNLP 2018 • Koustuv Sinha, Yue Dong, Jackie Chi Kit Cheung, Derek Ruths
Deep neural networks have been displaying superior performance over traditional supervised classifiers in text classification.
1 code implementation • EMNLP 2018 • Yue Dong, Yikang Shen, Eric Crawford, Herke van Hoof, Jackie Chi Kit Cheung
In this work, we propose a novel method for training neural networks to perform single-document extractive summarization without heuristically-generated extractive labels.
Ranked #10 on Extractive Text Summarization on CNN / Daily Mail
no code implementations • 19 Mar 2018 • Yue Dong
Automatic text summarization, the automated process of shortening a text while reserving the main ideas of the document(s), is a critical research area in natural language processing.
1 code implementation • CVPR 2017 • Jian Shi, Yue Dong, Hao Su, Stella X. Yu
Rendered with realistic environment maps, millions of synthetic images of objects and their corresponding albedo, shading, and specular ground-truth images are used to train an encoder-decoder CNN.