Bang Liu

qianggang.ding@mila.quebec

Biography

Bang Liu is an assistant professor in the Department of Computer Science and Operations Research (DIRO), and a core member of the Applied Research in Computational Linguistics Lab (RALI) at Université de Montréal. He is also an associate academic member of Mila – Quebec Artificial Intelligence Institute and a Canada CIFAR AI Chair.

Liu received his BEng from the University of Science and Technology of China in 2013, and his MSc and PhD degrees from the University of Alberta in 2015 and 2020, respectively. His research interests lie primarily in the areas of natural language processing, multimodal and embodied learning, theory and techniques for AGI (e.g., understanding and improving large language models), and AI for science (e.g., health, material science, XR).

Current Students

Qianggang Ding

PhD - Université de Montréal

Farshid Effaty

Postdoctorate - Université de Montréal

f.effaty@gmail.com

Wenhao Huang

PhD - Université de Montréal

huang.wenhao@mila.quebec

Yizhan Li

PhD - Université de Montréal

yizhan.li@mila.quebec

Kyle Roth

PhD - Université de Montréal

kyle.roth@mila.quebec

Haochen Shi

PhD - Université de Montréal

haochen.shi@mila.quebec

Xiran Song

PhD - Université de Montréal

xiran.song@mila.quebec

Github

suyuchen.wang@mila.quebec

Jia'ao Sun

PhD - Université de Montréal

sunjiaao@mila.quebec

Suyuchen Wang

PhD - Université de Montréal

PhD - Université de Montréal

xiaoqiang.wang@mila.quebec

Sifan Wu

PhD - Université de Montréal

sifan.wu@mila.quebec

Dekun Wu

PhD - Université de Montréal

dekun.wu@mila.quebec

Mengyang Xiong

Research Intern - McGill University

mengyang.xiong@mila.quebec

Yan Zhang

PhD - Université de Montréal

yan.zhang2@mila.quebec

Huan Zhang

Master's Research - Université de Montréal

huan.zhang@mila.quebec

armin.zolfagharidariani@mila.quebec

Armin Zolfagharidariani

Master's Research - Université de Montréal

Github

Blog Posts

MatSci-Instruct and HoneyBee training workflow.

October 21, 2024

Revolutionizing Materials Science with NLP: Introducing MatSci-NLP and HoneyBee

Bang Liu

Read the article

Publications

EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Time

Shengyao Lu

Keith G Mills

Jiao He

Di Niu

2024-07-07

Proceedings of the 41st International Conference on Machine Learning (published)

proceedings.mlr.press

Uncovering the essence of diverse media biases from the semantic embedding space

Hong Huang

Hua Zhu

Wenshi Liu

Hua Gao

Hai Jin

Media bias widely exists in the articles published by news media, influencing their readers’ perceptions, and bringing prejudice or injust… (see more)ice to society. However, current analysis methods usually rely on human efforts or only focus on a specific type of bias, which cannot capture the varying magnitudes, connections, and dynamics of multiple biases, thus remaining insufficient to provide a deep insight into media bias. Inspired by the Cognitive Miser and Semantic Differential theories in psychology, and leveraging embedding techniques in the field of natural language processing, this study proposes a general media bias analysis framework that can uncover biased information in the semantic embedding space on a large scale and objectively quantify it on diverse topics. More than 8 million event records and 1.2 million news articles are collected to conduct this study. The findings indicate that media bias is highly regional and sensitive to popular events at the time, such as the Russia-Ukraine conflict. Furthermore, the results reveal some notable phenomena of media bias among multiple U.S. news outlets. While they exhibit diverse biases on different topics, some stereotypes are common, such as gender bias. This framework will be instrumental in helping people have a clearer insight into media bias and then fight against it to create a more fair and objective news environment.

2024-05-21

Humanities and Social Sciences Communications (published)

GOAt: Explaining Graph Neural Networks via Graph Output Attribution

Shengyao Lu

Keith G Mills

Jiao He

Di Niu

Understanding the decision-making process of Graph Neural Networks (GNNs) is crucial to their interpretability. Most existing methods for ex… (see more)plaining GNNs typically rely on training auxiliary models, resulting in the explanations remain black-boxed. This paper introduces Graph Output Attribution (GOAt), a novel method to attribute graph outputs to input graph features, creating GNN explanations that are faithful, discriminative, as well as stable across similar samples. By expanding the GNN as a sum of scalar products involving node features, edge features and activation patterns, we propose an efficient analytical method to compute contribution of each node or edge feature to each scalar product and aggregate the contributions from all scalar products in the expansion form to derive the importance of each node and edge. Through extensive experiments on synthetic and real-world data, we show that our method not only outperforms various state-of-the-art GNN explainers in terms of the commonly used fidelity metric, but also exhibits stronger discriminability, and stability by a remarkable margin.

2024-01-15

ICLR.cc/2024/Conference (poster)

Efficient Classification of Long Documents via State-Space Models

Peng Lu

Suyuchen Wang

Mehdi Rezagholizadeh

Ivan Kobyzev

2023-10-06

EMNLP/2023/Conference (accepted)

HoneyBee: Progressive Instruction Finetuning of Large Language Models for Materials Science

Yu Song

Santiago Miret

Huan Zhang

2023-10-06

EMNLP/2023/Conference (accepted)

MAPO: Boosting Large Language Model Performance with Model-Adaptive Prompt Optimization

Yuyan Chen

Zhihao Wen

Ge Fan

Zhengyu Chen

Wei Wu

Dayiheng Liu

Zhixu Li

Yanghua Xiao

2023-10-06

EMNLP/2023/Conference (accepted)

XMQAs: Constructing Complex-Modified Question-Answering Dataset for Robust Question Understanding

Yuyan Chen

Yanghua Xiao

Zhixu Li

Question understanding is an important issue to the success of a Knowledge-based Question Answering (KBQA) system.However, the existing stud… (see more)y does not pay enough attention to this issue given that the questions in the existing KBQA datasets are usually expressed in simple and straightforward way. This is not in line with the actual linguistic conventions, which often use a lot of modifiers. To facilitate the study on evaluating and enhancing the question understanding ability of the KBQA systems, this paper proposes to construct a complex-modified question-answering (XMQAs) dataset based on existing KBQA datasets. With the help of knowledge bases and dictionaries, three kinds of modifiers are defined and applied to original simple-expressed questions. These modifiers could make the expression of these questions complex without changing their semantics. Based on XMQAs, we then propose a novel question understanding algorithm upon existing KBQA models, which greatly improves the robustness of their question understanding abilities. We conduct extensive experiments on XMQAs and two widely acknowledged KBQA datasets. The empirical results demonstrate that our proposed algorithm can improve the performance of KBQA models on not only the complex-modified questions, but also simple-expressed questions.

2023-08-09

IEEE Transactions on Knowledge and Data Engineering (unknown)

SkillQG: Learning to Generate Question for Reading Comprehension Assessment

Xiaoqiang Wang

Siliang Tang

Lingfei Wu

2023-06-30

Findings of the Association for Computational Linguistics: ACL 2023 (published)

MatSci-NLP: Evaluating Scientific Language Models on Materials Science Language Tasks Using Text-to-Schema Modeling

Yurun Song

Santiago Miret

2023-05-13

ArXiv (preprint)

DenseShift: Towards Accurate and Efficient Low-Bit Power-of-Two Quantization

Xinlin Li

Rui Heng Yang

Vanessa Courville

Chao Xing

Vahid Partovi Nia

Efficiently deploying deep neural networks on low-resource edge devices is challenging due to their ever-increasing resource requirements. T… (see more)o address this issue, researchers have proposed multiplication-free neural networks, such as Power-of-Two quantization, or also known as Shift networks, which aim to reduce memory usage and simplify computation. However, existing low-bit Shift networks are not as accurate as their full-precision counterparts, typically suffering from limited weight range encoding schemes and quantization loss. In this paper, we propose the DenseShift network, which significantly improves the accuracy of Shift networks, achieving competitive performance to full-precision networks for vision and speech applications. In addition, we introduce a method to deploy an efficient DenseShift network using non-quantized floating-point activations, while obtaining 1.6X speed-up over existing methods. To achieve this, we demonstrate that zero-weight values in low-bit Shift networks do not contribute to model capacity and negatively impact inference computation. To address this issue, we propose a zero-free shifting mechanism that simplifies inference and increases model capacity. We further propose a sign-scale decomposition design to enhance training efficiency and a low-variance random initialization strategy to improve the model's transfer learning performance. Our extensive experiments on various computer vision and speech tasks demonstrate that DenseShift outperforms existing low-bit multiplication-free networks and achieves competitive performance compared to full-precision networks. Furthermore, our proposed approach exhibits strong transfer learning performance without a drop in accuracy. Our code was released on GitHub.

2022-12-31

IEEE/CVF Conference on Computer Vision and Pattern Recognition (published)

Fine-tuning Happens in Tiny Subspaces: Exploring Intrinsic Task-specific Subspaces of Pre-trained Language Models

Zhong Zhang

Junming Shao

2022-12-31

ACL (1) (published)

QRelScore: Better Evaluating Generated Questions with Deeper Understanding of Context-aware Relevance

Xiaoqiang Wang

Siliang Tang

Lingfei Wu

Existing metrics for assessing question generation not only require costly human reference but also fail to take into account the input cont… (see more)ext of generation, rendering the lack of deep understanding of the relevance between the generated questions and input contexts. As a result, they may wrongly penalize a legitimate and reasonable candidate question when it (1) involves complicated reasoning with the context or (2) can be grounded by multiple evidences in the context.In this paper, we propose QRelScore, a context-aware Relevance evaluation metric for Question Generation.Based on off-the-shelf language models such as BERT and GPT2, QRelScore employs both word-level hierarchical matching and sentence-level prompt-based generation to cope with the complicated reasoning and diverse generation from multiple evidences, respectively.Compared with existing metrics, our experiments demonstrate that QRelScore is able to achieve a higher correlation with human judgments while being much more robust to adversarial samples.

2022-11-30

Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (published)