Haw-Shiuan Chang

52 papers A* 3A 3B 2Journal 32Unranked 12
YearRankTypeTitle / Venue / Authors
2026 J jnl
PROMPT2BOX: Uncovering Entailment Structure among LLM Prompts.
CoRR
Neeladri Bhuiya, Shib Sankar Dasgupta, Andrew McCallum, Haw-Shiuan Chang
2026 J jnl
Truncated Step-Level Sampling with Process Rewards for Retrieval-Augmented Reasoning.
CoRR
Chris Samarinas, Haw-Shiuan Chang, Hamed Zamani
2025 J jnl
CoKe: Customizable Fine-Grained Story Evaluation via Chain-of-Keyword Rationalization.
CoRR
Brihi Joshi, Sriram Venkatapathy, Mohit Bansal, Nanyun Peng, Haw-Shiuan Chang
2025 J jnl
CreativityPrism: A Holistic Benchmark for Large Language Model Creativity.
CoRR
Zhaoyi Joey Hou, Bowei Alvin Zhang, Yining Lu, Bhiman Kumar Baghel, Anneliese Brei, Ximing Lu, Meng Jiang, Faeze Brahman, Snigdha Chaturvedi, Haw-Shiuan Chang, Daniel Khashabi, Xiang Lorraine Li
2025 J jnl
Latent Traits and Cross-Task Transfer: Deconstructing Dataset Interactions in LLM Fine-tuning.
CoRR
Shambhavi Krishna, Atharva Naik, Chaitali Agarwal, Sudharshan Govindan, Taesung Lee, Haw-Shiuan Chang
2025 J jnl
REAL Sampling: Boosting Factuality and Diversity of Open-ended Generation by Extrapolating the Entropy of an Infinitely Large LM.
Trans. Assoc. Comput. Linguistics
Haw-Shiuan Chang, Nanyun Peng, Mohit Bansal, Anil Ramakrishna, Tagyoung Chung
2024 J jnl
CS4: Measuring the Creativity of Large Language Models Automatically by Controlling the Number of Story-Writing Constraints.
CoRR
Anirudh Atmakuru, Jatin Nainani, Rohith Siddhartha Reddy Bheemreddy, Anirudh Lakkaraju, Zonghai Yao, Hamed Zamani, Haw-Shiuan Chang
2024 A* conf
Explaining and Improving Contrastive Decoding by Extrapolating the Probabilities of a Huge and Hypothetical LM.
EMNLP
Haw-Shiuan Chang, Nanyun Peng, Mohit Bansal, Anil Ramakrishna, Tagyoung Chung
2024 J jnl
Explaining and Improving Contrastive Decoding by Extrapolating the Probabilities of a Huge and Hypothetical LM.
CoRR
Haw-Shiuan Chang, Nanyun Peng, Mohit Bansal, Anil Ramakrishna, Tagyoung Chung
2024 — conf
LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints.
EMNLP (Findings)
Thomas Palmeira Ferraz, Kartik Mehta, Yu-Hsiang Lin, Haw-Shiuan Chang, Shereen Oraby, Sijia Liu, Vivek Subramanian, Tagyoung Chung, Mohit Bansal, Nanyun Peng
2024 J jnl
LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints.
CoRR
Thomas Palmeira Ferraz, Kartik Mehta, Yu-Hsiang Lin, Haw-Shiuan Chang, Shereen Oraby, Sijia Liu, Vivek Subramanian, Tagyoung Chung, Mohit Bansal, Nanyun Peng
2024 J jnl
REAL Sampling: Boosting Factuality and Diversity of Open-Ended Generation via Asymptotic Entropy.
CoRR
Haw-Shiuan Chang, Nanyun Peng, Mohit Bansal, Anil Ramakrishna, Tagyoung Chung
2024 A conf
To Copy, or not to Copy; That is a Critical Issue of the Output Softmax Layer in Neural Sequential Recommenders.
WSDM
Haw-Shiuan Chang, Nikhil Agarwal, Andrew McCallum
2023 J jnl
Encoding Multi-Domain Scientific Papers by Ensembling Multiple CLS Tokens.
CoRR
Ronald Seoh, Haw-Shiuan Chang, Andrew McCallum
2023 — conf
Multi-CLS BERT: An Efficient Alternative to Traditional Ensembling.
ACL (1)
Haw-Shiuan Chang, Ruei-Yao Sun, Kathryn Ricci, Andrew McCallum
2023 — conf
Revisiting the Architectures like Pointer Networks to Efficiently Improve the Next Word Distribution, Summarization Factuality, and Beyond.
ACL (Findings)
Haw-Shiuan Chang, Zonghai Yao, Alolika Gon, Hong Yu, Andrew McCallum
2023 J jnl
Revisiting the Architectures like Pointer Networks to Efficiently Improve the Next Word Distribution, Summarization Factuality, and Beyond.
CoRR
Haw-Shiuan Chang, Zonghai Yao, Alolika Gon, Hong Yu, Andrew McCallum
2023 J jnl
To Copy, or not to Copy; That is a Critical Issue of the Output Softmax Layer in Neural Sequential Recommenders.
CoRR
Haw-Shiuan Chang, Nikhil Agarwal, Andrew McCallum
2022 J jnl
Augmenting Scientific Creativity with Retrieval across Knowledge Domains.
CoRR
Hyeonsu B. Kang, Sheshera Mysore, Kevin Huang, Haw-Shiuan Chang, Thorben Prein, Andrew McCallum, Aniket Kittur, Elsa A. Olivetti
2022 J jnl
Multi-CLS BERT: An Efficient Alternative to Traditional Ensembling.
CoRR
Haw-Shiuan Chang, Ruei-Yao Sun, Kathryn Ricci, Andrew McCallum
2022 — conf
Softmax Bottleneck Makes Language Models Unable to Represent Multi-mode Word Distributions.
ACL (1)
Haw-Shiuan Chang, Andrew McCallum
2022 — conf
Unsupervised Partial Sentence Matching for Cited Text Identification.
SDP@COLING
Kathryn Ricci, Haw-Shiuan Chang, Purujit Goyal, Andrew McCallum
2021 A conf
Changing the Mind of Transformers for Topically-Controllable Language Generation.
EACL
Haw-Shiuan Chang, Jiaming Yuan, Mohit Iyyer, Andrew McCallum
2021 J jnl
Changing the Mind of Transformers for Topically-Controllable Language Generation.
CoRR
Haw-Shiuan Chang, Jiaming Yuan, Mohit Iyyer, Andrew McCallum
2021 A* conf
Extending Multi-Sense Word Embedding to Phrases and Sentences for Unsupervised Semantic Applications.
AAAI
Haw-Shiuan Chang, Amol Agrawal, Andrew McCallum
2021 J jnl
Extending Multi-Sense Word Embedding to Phrases and Sentences for Unsupervised Semantic Applications.
CoRR
Haw-Shiuan Chang, Amol Agrawal, Andrew McCallum
2021 A conf
Multi-facet Universal Schema.
EACL
Rohan Paul, Haw-Shiuan Chang, Andrew McCallum
2021 J jnl
Multi-facet Universal Schema.
CoRR
Rohan Paul, Haw-Shiuan Chang, Andrew McCallum
2021 — conf
Open Aspect Target Sentiment Classification with Natural Language Prompts.
EMNLP (1)
Ronald Seoh, Ian Birle, Mrinal Tak, Haw-Shiuan Chang, Brian Pinette, Alfred Hough
2021 J jnl
Open Aspect Target Sentiment Classification with Natural Language Prompts.
CoRR
Ronald Seoh, Ian Birle, Mrinal Tak, Haw-Shiuan Chang, Brian Pinette, Alfred Hough
2020 A* conf
AutoKnow: Self-Driving Knowledge Collection for Products of Thousands of Types.
KDD
Xin Luna Dong, Xiang He, Andrey Kan, Xian Li, Yan Liang, Jun Ma, Yifan Ethan Xu, Chenwei Zhang, Tong Zhao, Gabriel Blanco Saldana, Saurabh Deshpande, Alexandre Michetti Manduca, Jay Ren, Surender Pal Singh, Fan Xiao, Haw-Shiuan Chang, Giannis Karamanolakis, Yuning Mao, Yaqing Wang, Christos Faloutsos, Andrew McCallum, Jiawei Han
2020 J jnl
AutoKnow: Self-Driving Knowledge Collection for Products of Thousands of Types.
CoRR
Xin Luna Dong, Xiang He, Andrey Kan, Xian Li, Yan Liang, Jun Ma, Yifan Ethan Xu, Chenwei Zhang, Tong Zhao, Gabriel Blanco Saldana, Saurabh Deshpande, Alexandre Michetti Manduca, Jay Ren, Surender Pal Singh, Fan Xiao, Haw-Shiuan Chang, Giannis Karamanolakis, Yuning Mao, Yaqing Wang, Christos Faloutsos, Andrew McCallum, Jiawei Han
2020 J jnl
Inorganic Materials Synthesis Planning with Literature-Trained Neural Networks.
J. Chem. Inf. Model.
Edward Kim, Zach Jensen, Alexander van Grootel, Kevin Huang, Matthew Staib, Sheshera Mysore, Haw-Shiuan Chang, Emma Strubell, Andrew McCallum, Stefanie Jegelka, Elsa A. Olivetti
2020 J jnl
Using error decay prediction to overcome practical issues of deep active learning for named entity recognition.
Mach. Learn.
Haw-Shiuan Chang, Shankar Vembu, Sunil Mohan, Rheeya Uppaal, Andrew McCallum
2019 J jnl
Inorganic Materials Synthesis Planning with Literature-Trained Neural Networks.
CoRR
Edward Kim, Zach Jensen, Alexander van Grootel, Kevin Huang, Matthew Staib, Sheshera Mysore, Haw-Shiuan Chang, Emma Strubell, Andrew McCallum, Stefanie Jegelka, Elsa A. Olivetti
2019 J jnl
Overcoming Practical Issues of Deep Active Learning and its Applications on Named Entity Recognition.
CoRR
Haw-Shiuan Chang, Shankar Vembu, Sunil Mohan, Rheeya Uppaal, Andrew McCallum
2019 — conf
The Materials Science Procedural Text Corpus: Annotating Materials Synthesis Procedures with Shallow Semantic Structures.
LAW@ACL
Sheshera Mysore, Zach Jensen, Edward Kim, Kevin Huang, Haw-Shiuan Chang, Emma Strubell, Jeffrey Flanigan, Andrew McCallum, Elsa A. Olivetti
2019 J jnl
The Materials Science Procedural Text Corpus: Annotating Materials Synthesis Procedures with Shallow Semantic Structures.
CoRR
Sheshera Mysore, Zach Jensen, Edward Kim, Kevin Huang, Haw-Shiuan Chang, Emma Strubell, Jeffrey Flanigan, Andrew McCallum, Elsa A. Olivetti
2018 J jnl
Active Learning for Crowdsourced QoE Modeling.
IEEE Trans. Multim.
Haw-Shiuan Chang, Chih-Fan Hsu, Tobias Hoßfeld, Kuan-Ta Chen
2018 — conf
Distributional Inclusion Vector Embedding for Unsupervised Hypernymy Detection.
NAACL-HLT
Haw-Shiuan Chang, Ziyun Wang, Luke Vilnis, Andrew McCallum
2018 — conf
Efficient Graph-based Word Sense Induction by Distributional Inclusion Vector Embeddings.
TextGraphs@NAACL-HLT
Haw-Shiuan Chang, Amol Agrawal, Ananya Ganesh, Anirudha Desai, Vinayak Mathur, Alfred Hough, Andrew McCallum
2018 J jnl
Efficient Graph-based Word Sense Induction by Distributional Inclusion Vector Embeddings.
CoRR
Haw-Shiuan Chang, Amol Agrawal, Ananya Ganesh, Anirudha Desai, Vinayak Mathur, Alfred Hough, Andrew McCallum
2017 — conf
Active Bias: Training More Accurate Neural Networks by Emphasizing High Variance Samples.
NIPS
Haw-Shiuan Chang, Erik G. Learned-Miller, Andrew McCallum
2017 J jnl
Active Bias: Training a More Accurate Neural Network by Emphasizing High Variance Samples.
CoRR
Haw-Shiuan Chang, Erik G. Learned-Miller, Andrew McCallum
2017 J jnl
Automatically Extracting Action Graphs from Materials Science Synthesis Procedures.
CoRR
Sheshera Mysore, Edward Kim, Emma Strubell, Ao Liu, Haw-Shiuan Chang, Srikrishna Kompella, Kevin Huang, Andrew McCallum, Elsa A. Olivetti
2017 J jnl
Unsupervised Hypernym Detection by Distributional Inclusion Vector Embedding.
CoRR
Haw-Shiuan Chang, Ziyun Wang, Luke Vilnis, Andrew McCallum
2016 — conf
Extracting Multilingual Relations under Limited Resources: TAC 2016 Cold-Start KB construction and Slot-Filling using Compositional Universal Schema.
TAC
Haw-Shiuan Chang, Abdurrahman Munir, Ao Liu, Johnny Tian-Zheng Wei, Aaron Traylor, Ajay Nagesh, Nicholas Monath, Patrick Verga, Emma Strubell, Andrew McCallum
2015 B conf
Modeling Exercise Relationships in E-Learning: A Unified Approach.
EDM
Haw-Shiuan Chang, Hwai-Jung Hsu, Kuan-Ta Chen
2015 J jnl
Optimizing the decomposition for multiple foreground cosegmentation.
Comput. Vis. Image Underst.
Haw-Shiuan Chang, Yu-Chiang Frank Wang
2014 — conf
Simple-to-Complex Discriminative Clustering for Hierarchical Image Segmentation.
ACCV (3)
Haw-Shiuan Chang, Yu-Chiang Frank Wang
2013 J jnl
Exploring Visual and Motion Saliency for Automatic Video Object Extraction.
IEEE Trans. Image Process.
Wei-Te Li, Haw-Shiuan Chang, Kuo-Chin Lien, Hui-Tang Chang, Yu-Chiang Frank Wang
2013 B conf
Superpixel-based large displacement optical flow.
ICIP
Haw-Shiuan Chang, Yu-Chiang Frank Wang