Subhabrata Mukherjee

ORCID

Publication Activity (10 Years)

Years Active: 2012-2024
Publications (10 Years): 89

Top Venues

Saarland University, Saarbrücken, Germany (PHD)

Education History

Saarland University, Saarbrücken, Germany

PHD

Publications

Erik Jones, Hamid Palangi, Clarisse Simões, Varun Chandrasekaran, Subhabrata Mukherjee, Arindam Mitra, Ahmed Hassan Awadallah, Ece Kamar
Teaching Language Models to Hallucinate Less with Synthetic Tasks. ICLR (2024)
Subhabrata Mukherjee, Paul Gamble, Markel Sanz Ausin, Neel Kant, Kriti Aggarwal, Neha Manjunath, Debajyoti Datta, Zhengliang Liu, Jiayuan Ding, Sophia Busacca, Cezanne Bianco, Swapnil Sharma, Rae Lasko, Michelle Voisard, Sanchay Harneja, Darya Filippova, Gerry Meixiong, Kevin Cha, Amir Youssefi, Meyhaa Buvanesh, Howard Weingram, Sebastian Bierman-Lytle, Harpreet Singh Mangat, Kim Parikh, Saad Godil, Alex Miller
Polaris: A Safety-focused LLM Constellation Architecture for Healthcare. CoRR (2024)
Dujian Ding, Ankur Mallick, Chi Wang, Robert Sim, Subhabrata Mukherjee, Victor Rühle, Laks V. S. Lakshmanan, Ahmed Hassan Awadallah
Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing. ICLR (2024)
Dujian Ding, Ankur Mallick, Chi Wang, Robert Sim, Subhabrata Mukherjee, Victor Rühle, Laks V. S. Lakshmanan, Ahmed Hassan Awadallah
Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing. CoRR (2024)
Chuxu Zhang, Dongkuan Xu, Kaize Ding, Jundong Li, Mojan Javaheripi, Subhabrata Mukherjee, Nitesh V. Chawla, Huan Liu
RelKD 2024: The Second International Workshop on Resource-Efficient Learning for Knowledge Discovery. KDD (2024)
Hai Pham, Young Jin Kim, Subhabrata Mukherjee, David P. Woodruff, Barnabás Póczos, Hany Hassan Awadalla
Task-Based MoE for Multitask Multilingual Machine Translation. CoRR (2023)
Lei Zhang, Jie Zhang, Bowen Lei, Subhabrata Mukherjee, Xiang Pan, Bo Zhao, Caiwen Ding, Yao Li, Dongkuan Xu
Accelerating Dataset Distillation via Model Augmentation. CVPR (2023)
Mengnan Du, Subhabrata Mukherjee, Yu Cheng, Milad Shokouhi, Xia Hu, Ahmed Hassan Awadallah
Robustness Challenges in Model Distillation and Pruning for Natural Language Understanding. EACL (2023)
Ganesh Jawahar, Subhabrata Mukherjee, Debadeepta Dey, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan, Caio Mendes, Gustavo de Rosa, Shital Shah
Small Character Models Match Large Word Models for Autocomplete Under Memory Constraints. SustaiNLP (2023)
Venkata Prabhakara Sarath Nookala, Gaurav Verma, Subhabrata Mukherjee, Srijan Kumar
Adversarial Robustness of Prompt-based Few-Shot Learning for Natural Language Understanding. CoRR (2023)
Yue Zhao, Guoqing Zheng, Subhabrata Mukherjee, Robert McCann, Ahmed Hassan Awadallah
ADMoE: Anomaly Detection with Mixture-of-Experts from Noisy Labels. AAAI (2023)
Subhabrata Mukherjee, Arindam Mitra, Ganesh Jawahar, Sahaj Agarwal, Hamid Palangi, Ahmed Hassan Awadallah
Orca: Progressive Learning from Complex Explanation Traces of GPT-4. CoRR (2023)
Binfeng Xu, Zhiyuan Peng, Bowen Lei, Subhabrata Mukherjee, Yuchen Liu, Dongkuan Xu
ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models. CoRR (2023)
Nitay Calderon, Subhabrata Mukherjee, Roi Reichart, Amir Kantor
A Systematic Study of Knowledge Distillation for Natural Language Generation with Pseudo-Target Training. ACL (1) (2023)
Nitay Calderon, Subhabrata Mukherjee, Roi Reichart, Amir Kantor
A Systematic Study of Knowledge Distillation for Natural Language Generation with Pseudo-Target Training. CoRR (2023)
Ganesh Jawahar, Subhabrata Mukherjee, Xiaodong Liu, Young Jin Kim, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan, Ahmed Hassan Awadallah, Sébastien Bubeck, Jianfeng Gao
AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine Translation. ACL (Findings) (2023)
Chuxu Zhang, Dongkuan Xu, Mojan Javaheripi, Subhabrata Mukherjee, Lingfei Wu, Yinglong Xia, Jundong Li, Meng Jiang, Yanzhi Wang
RelKD 2023: International Workshop on Resource-Efficient Learning for Knowledge Discovery. KDD (2023)
Erik Jones, Hamid Palangi, Clarisse Simões, Varun Chandrasekaran, Subhabrata Mukherjee, Arindam Mitra, Ahmed Hassan Awadallah, Ece Kamar
Teaching Language Models to Hallucinate Less with Synthetic Tasks. CoRR (2023)
Woojeong Jin, Subhabrata Mukherjee, Yu Cheng, Yelong Shen, Weizhu Chen, Ahmed Hassan Awadallah, Damien Jose, Xiang Ren
GRILL: Grounded Vision-language Pre-training via Aligning Text and Image Regions. CoRR (2023)
Venkata Prabhakara Sarath Nookala, Gaurav Verma, Subhabrata Mukherjee, Srijan Kumar
Adversarial Robustness of Prompt-based Few-Shot Learning for Natural Language Understanding. ACL (Findings) (2023)
Luciano Del Corro, Allie Del Giorno, Sahaj Agarwal, Bin Yu, Ahmed Hassan Awadallah, Subhabrata Mukherjee
SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference. CoRR (2023)
Mojan Javaheripi, Gustavo de Rosa, Subhabrata Mukherjee, Shital Shah, Tomasz Religa, Caio Cesar Teodoro Mendes, Sébastien Bubeck, Farinaz Koushanfar, Debadeepta Dey
LiteTransformerSearch: Training-free Neural Architecture Search for Efficient Language Models. NeurIPS (2022)
Sara Abdali, Subhabrata Mukherjee, Evangelos E. Papalexakis
Vec2Node: Self-Training with Tensor Augmentation for Text Classification with Few Labels. ECML/PKDD (2) (2022)
Yaqing Wang, Subhabrata Mukherjee, Xiaodong Liu, Jing Gao, Ahmed Hassan Awadallah, Jianfeng Gao
LiST: Lite Prompted Self-training Makes Parameter-efficient Few-shot Learners. NAACL-HLT (Findings) (2022)
Lei Zhang, Jie Zhang, Bowen Lei, Subhabrata Mukherjee, Xiang Pan, Bo Zhao, Caiwen Ding, Yao Li, Dongkuan Xu
Accelerating Dataset Distillation via Model Augmentation. CoRR (2022)
Yaqing Wang, Sahaj Agarwal, Subhabrata Mukherjee, Xiaodong Liu, Jing Gao, Ahmed Hassan Awadallah, Jianfeng Gao
AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning. EMNLP (2022)
Ganesh Jawahar, Subhabrata Mukherjee, Xiaodong Liu, Young Jin Kim, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan, Ahmed Hassan Awadallah, Sébastien Bubeck, Jianfeng Gao
AutoMoE: Neural Architecture Search for Efficient Sparsely Activated Transformers. CoRR (2022)
Mojan Javaheripi, Shital Shah, Subhabrata Mukherjee, Tomasz L. Religa, Caio C. T. Mendes, Gustavo H. de Rosa, Sébastien Bubeck, Farinaz Koushanfar, Debadeepta Dey
LiteTransformerSearch: Training-free On-device Search for Efficient Autoregressive Language Models. CoRR (2022)
Yue Zhao, Guoqing Zheng, Subhabrata Mukherjee, Robert McCann, Ahmed Hassan Awadallah
ADMoE: Anomaly Detection with Mixture-of-Experts from Noisy Labels. CoRR (2022)
Ganesh Jawahar, Subhabrata Mukherjee, Debadeepta Dey, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan, Caio César Teodoro Mendes, Gustavo Henrique de Rosa, Shital Shah
Small Character Models Match Large Word Models for Autocomplete Under Memory Constraints. CoRR (2022)
Dongkuan Xu, Subhabrata Mukherjee, Xiaodong Liu, Debadeepta Dey, Wenhui Wang, Xiang Zhang, Ahmed Hassan Awadallah, Jianfeng Gao
Few-shot Task-agnostic Neural Architecture Search for Distilling Large Language Models. NeurIPS (2022)
Yaqing Wang, Subhabrata Mukherjee, Xiaodong Liu, Jing Gao, Ahmed Hassan Awadallah, Jianfeng Gao
AdaMix: Mixture-of-Adapter for Parameter-efficient Tuning of Large Language Models. CoRR (2022)
Dongkuan Xu, Subhabrata Mukherjee, Xiaodong Liu, Debadeepta Dey, Wenhui Wang, Xiang Zhang, Ahmed Hassan Awadallah, Jianfeng Gao
AutoDistil: Few-shot Task-agnostic Neural Architecture Search for Distilling Large Language Models. CoRR (2022)
Shashank Gupta, Subhabrata Mukherjee, Krishan Subudhi, Eduardo Gonzalez, Damien Jose, Ahmed Hassan Awadallah, Jianfeng Gao
Sparsely Activated Mixture-of-Experts are Robust Multi-Task Learners. CoRR (2022)
Yaqing Wang, Sahaj Agarwal, Subhabrata Mukherjee, Xiaodong Liu, Jing Gao, Ahmed Hassan Awadallah, Jianfeng Gao
AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning. CoRR (2022)
Yaqing Wang, Subhabrata Mukherjee, Xiaodong Liu, Jing Gao, Ahmed Hassan Awadallah, Jianfeng Gao
LiST: Lite Self-training Makes Efficient Few-shot Learners. CoRR (2021)
Subhabrata Mukherjee, Qi Li, Sihong Xie, Philip S. Yu, Jing Gao
The Third International TrueFact Workshop: Making a Credible Web for Tomorrow. KDD (2021)
Meghana Moorthy Bhat, Alessandro Sordoni, Subhabrata Mukherjee
Self-training with Few-shot Rationalization: Teacher Explanations Aid Student in Few-shot NLU. CoRR (2021)
Mengnan Du, Subhabrata Mukherjee, Guanchu Wang, Ruixiang Tang, Ahmed Hassan Awadallah, Xia Hu
Fairness via Representation Neutralization. NeurIPS (2021)
Mengnan Du, Subhabrata Mukherjee, Guanchu Wang, Ruixiang Tang, Ahmed Hassan Awadallah, Xia Hu
Fairness via Representation Neutralization. CoRR (2021)
Yaqing Wang, Subhabrata Mukherjee, Haoda Chu, Yuancheng Tu, Ming Wu, Jing Gao, Ahmed Hassan Awadallah
Meta Self-training for Few-shot Neural Sequence Labeling. KDD (2021)
Mengnan Du, Subhabrata Mukherjee, Yu Cheng, Milad Shokouhi, Xia Hu, Ahmed Hassan Awadallah
What do Compressed Large Language Models Forget? Robustness Challenges in Model Compression. CoRR (2021)
Mengzhou Xia, Guoqing Zheng, Subhabrata Mukherjee, Milad Shokouhi, Graham Neubig, Ahmed Hassan Awadallah
MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning. CoRR (2021)
Mengzhou Xia, Guoqing Zheng, Subhabrata Mukherjee, Milad Shokouhi, Graham Neubig, Ahmed Hassan Awadallah
MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning. NAACL-HLT (2021)
Giannis Karamanolakis, Subhabrata Mukherjee, Guoqing Zheng, Ahmed Hassan Awadallah
Self-Training with Weak Supervision. NAACL-HLT (2021)
Giannis Karamanolakis, Subhabrata Mukherjee, Guoqing Zheng, Ahmed Hassan Awadallah
Self-Training with Weak Supervision. CoRR (2021)
Subhabrata Mukherjee, Ahmed Hassan Awadallah, Jianfeng Gao
XtremeDistilTransformers: Task Transfer for Task-agnostic Distillation. CoRR (2021)
Subhabrata Mukherjee, Xiaodong Liu, Guoqing Zheng, Saghar Hosseini, Hao Cheng, Greg Yang, Christopher Meek, Ahmed Hassan Awadallah, Jianfeng Gao
CLUES: Few-Shot Learning Evaluation in Natural Language Understanding. CoRR (2021)
Meghana Moorthy Bhat, Alessandro Sordoni, Subhabrata Mukherjee
Self-training with Few-shot Rationalization. EMNLP (1) (2021)
Subhabrata Mukherjee, Xiaodong Liu, Guoqing Zheng, Saghar Hosseini, Hao Cheng, Ge Yang, Christopher Meek, Ahmed Hassan Awadallah, Jianfeng Gao
Few-Shot Learning Evaluation in Natural Language Understanding. NeurIPS Datasets and Benchmarks (2021)
Nikitha Rao, Chetan Bansal, Subhabrata Mukherjee, Chandra Shekhar Maddila
Product Insights: Analyzing Product Intents in Web Search. CIKM (2020)
Kai Shu, Guoqing Zheng, Yichuan Li, Subhabrata Mukherjee, Ahmed Hassan Awadallah, Scott Ruston, Huan Liu
Leveraging Multi-Source Weak Social Supervision for Early Detection of Fake News. CoRR (2020)
Subhabrata Mukherjee, Ahmed Hassan Awadallah
TinyMBERT: Multi-Stage Distillation Framework for Massive Multi-lingual NER. CoRR (2020)
Subhabrata Mukherjee, Ahmed Hassan Awadallah
Uncertainty-aware Self-training for Few-shot Text Classification. NeurIPS (2020)
Kai Shu, Guoqing Zheng, Yichuan Li, Subhabrata Mukherjee, Ahmed Hassan Awadallah, Scott Ruston, Huan Liu
Early Detection of Fake News with Multi-source Weak Social Supervision. ECML/PKDD (3) (2020)
Jieyu Zhao, Subhabrata Mukherjee, Saghar Hosseini, Kai-Wei Chang, Ahmed Hassan Awadallah
Gender Bias in Multilingual Embeddings and Cross-Lingual Transfer. CoRR (2020)
Subhabrata Mukherjee, Ahmed Hassan Awadallah
Uncertainty-aware Self-training for Text Classification with Few Labels. CoRR (2020)
Yaqing Wang, Subhabrata Mukherjee, Haoda Chu, Yuancheng Tu, Ming Wu, Jing Gao, Ahmed Hassan Awadallah
Adaptive Self-training for Few-shot Neural Sequence Labeling. CoRR (2020)
Sudipto Mukherjee, Subhabrata Mukherjee, Marcello Hasegawa, Ahmed Hassan Awadallah, Ryen White
Smart To-Do: Automatic Generation of To-Do Items from Emails. ACL (2020)
Subhabrata Mukherjee, Ahmed Hassan Awadallah
XtremeDistil: Multi-stage Distillation for Massive Multilingual Models. ACL (2020)
Kai Shu, Subhabrata Mukherjee, Guoqing Zheng, Ahmed Hassan Awadallah, Milad Shokouhi, Susan T. Dumais
Learning with Weak Supervision for Email Intent Detection. CoRR (2020)
Sudipto Mukherjee, Subhabrata Mukherjee, Marcello Hasegawa, Ahmed Hassan Awadallah, Ryen White
Smart To-Do : Automatic Generation of To-Do Items from Emails. CoRR (2020)
Kai Shu, Subhabrata Mukherjee, Guoqing Zheng, Ahmed Hassan Awadallah, Milad Shokouhi, Susan T. Dumais
Learning with Weak Supervision for Email Intent Detection. SIGIR (2020)
Jieyu Zhao, Subhabrata Mukherjee, Saghar Hosseini, Kai-Wei Chang, Ahmed Hassan Awadallah
Gender Bias in Multilingual Embeddings and Cross-Lingual Transfer. ACL (2020)
Nikitha Rao, Chetan Bansal, Subhabrata Mukherjee, Chandra Shekhar Maddila
Product Insights: Analyzing Product Intents in Web Search. CoRR (2020)
Dongxu Zhang, Subhabrata Mukherjee, Colin Lockard, Xin Luna Dong, Andrew McCallum
OpenKI: Integrating Open Information Extraction and Knowledge Bases with Relation Inference. CoRR (2019)
Subhabrata Mukherjee, Ahmed Hassan Awadallah
Distilling Transformers into Simple Neural Networks with Unlabeled Transfer Data. CoRR (2019)
Kashyap Popat, Subhabrata Mukherjee, Andrew Yates, Gerhard Weikum
STANCY: Stance Classification Based on Consistency Cues. CoRR (2019)
Kashyap Popat, Subhabrata Mukherjee, Andrew Yates, Gerhard Weikum
STANCY: Stance Classification Based on Consistency Cues. EMNLP/IJCNLP (1) (2019)
Subhabrata Mukherjee, Stephan Günnemann
GhostLink: Latent Network Inference for Influence-aware Recommendation. WWW (2019)
Subhabrata Mukherjee, Stephan Günnemann
GhostLink: Latent Network Inference for Influence-aware Recommendation. CoRR (2019)
Dongxu Zhang, Subhabrata Mukherjee, Colin Lockard, Xin Luna Dong, Andrew McCallum
OpenKI: Integrating Open Information Extraction and Knowledge Bases with Relation Inference. NAACL-HLT (1) (2019)
Guineng Zheng, Subhabrata Mukherjee, Xin Luna Dong, Feifei Li
OpenTag: Open Attribute Value Extraction from Product Profiles. KDD (2018)
Guineng Zheng, Subhabrata Mukherjee, Xin Luna Dong, Feifei Li
OpenTag: Open Attribute Value Extraction from Product Profiles. CoRR (2018)
Kashyap Popat, Subhabrata Mukherjee, Jannik Strötgen, Gerhard Weikum
CredEye: A Credibility Lens for Analyzing and Explaining Misinformation. WWW (Companion Volume) (2018)
Kashyap Popat, Subhabrata Mukherjee, Andrew Yates, Gerhard Weikum
DeClarE: Debunking Fake News and False Claims using Evidence-Aware Deep Learning. CoRR (2018)
Kashyap Popat, Subhabrata Mukherjee, Andrew Yates, Gerhard Weikum
DeClarE: Debunking Fake News and False Claims using Evidence-Aware Deep Learning. EMNLP (2018)
Subhabrata Mukherjee, Hemank Lamba, Gerhard Weikum
Item Recommendation with Evolving User Preferences and Experience. CoRR (2017)
Subhabrata Mukherjee, Sourav Dutta, Gerhard Weikum
Credible Review Detection with Limited Information using Consistency Analysis. CoRR (2017)
Subhabrata Mukherjee, Kashyap Popat, Gerhard Weikum
Exploring Latent Semantic Factors to Find Useful Product Reviews. CoRR (2017)
Subhabrata Mukherjee, Kashyap Popat, Gerhard Weikum
Exploring Latent Semantic Factors to Find Useful Product Reviews. SDM (2017)
Kashyap Popat, Subhabrata Mukherjee, Jannik Strötgen, Gerhard Weikum
Where the Truth Lies: Explaining the Credibility of Emerging Claims on the Web and Social Media. WWW (Companion Volume) (2017)
Subhabrata Mukherjee, Gerhard Weikum
People on Media: Jointly Identifying Credible News and Trustworthy Citizen Journalists in Online Communities. CoRR (2017)
Subhabrata Mukherjee, Stephan Günnemann, Gerhard Weikum
Personalized Item Recommendation with Continuous Experience Evolution of Users using Brownian Motion. CoRR (2017)
Subhabrata Mukherjee
Probabilistic Graphical Models for Credibility Analysis in Evolving Online Communities. CoRR (2017)
Subhabrata Mukherjee, Gerhard Weikum, Cristian Danescu-Niculescu-Mizil
People on Drugs: Credibility of User Statements in Health Communities. CoRR (2017)
Subhabrata Mukherjee, Stephan Günnemann, Gerhard Weikum
Continuous Experience-aware Language Model. KDD (2016)
Kashyap Popat, Subhabrata Mukherjee, Jannik Strötgen, Gerhard Weikum
Credibility Assessment of Textual Claims on the Web. CIKM (2016)
Subhabrata Mukherjee, Sourav Dutta, Gerhard Weikum
Credible Review Detection with Limited Information Using Consistency Features. ECML/PKDD (2) (2016)
Subhabrata Mukherjee, Hemank Lamba, Gerhard Weikum
Experience-Aware Item Recommendation in Evolving Review Communities. ICDM (2015)
Subhabrata Mukherjee, Gerhard Weikum
Leveraging Joint Interactions for Credibility Analysis in News Communities. CIKM (2015)
Subhabrata Mukherjee, Sachindra Joshi
Help yourself: a virtual self-assist system. WWW (Companion Volume) (2014)
Subhabrata Mukherjee, Gerhard Weikum, Cristian Danescu-Niculescu-Mizil
People on drugs: credibility of user statements in health communities. KDD (2014)
Subhabrata Mukherjee, Sachindra Joshi
Author-Specific Sentiment Aggregation for Polarity Prediction of Reviews. LREC (2014)
Subhabrata Mukherjee, Jitendra Ajmera, Sachindra Joshi
Unsupervised approach for shallow domain ontology construction from corpus. WWW (Companion Volume) (2014)
Subhabrata Mukherjee, Jitendra Ajmera, Sachindra Joshi
Domain Cartridge: Unsupervised Framework for Shallow Domain Ontology Construction from Corpus. CIKM (2014)
Subhabrata Mukherjee, Gaurab Basu, Sachindra Joshi
Joint Author Sentiment Topic Model. SDM (2014)
Subhabrata Mukherjee, Gaurab Basu, Sachindra Joshi
Incorporating author preference in sentiment rating prediction of reviews. WWW (Companion Volume) (2013)
Subhabrata Mukherjee, Pushpak Bhattacharyya
Sentiment Analysis : A Literature Survey CoRR (2013)
Subhabrata Mukherjee, Sachindra Joshi
Sentiment Aggregation using ConceptNet Ontology. IJCNLP (2013)

Subhabrata Mukherjee.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

Subhabrata Mukherjee