Swaroop Mishra

I am a research intern at Google AI and a PhD candidate at Arizona State University, where I work on developing models that learn new tasks from instructions. I have had the pleasure of doing my research internship at Microsoft Research (2022), Allen Institute for AI (2021, 2022), Research, Technology and Innovation Center, Thermax Limited (2013), Harish-Chandra Research Institute (2012) and Institute of Physics (2011). I also had a great time working full time as Technical Consultant at Information Technology Research Academy (Government of India) (2018-19) and as a Software Engineer at MathWorks (2016-18). I am a proud alumni of IIT Kanpur.

I am currently on job market. I love to discuss new ideas. Do email to chat.

Email  /  Google Scholar  /  Semantic Scholar  /  Linkedin  /  Twitter

profile photo
Research

My main focus area is Learning from Instructions/Prompting. I am also excited about related areas such as Quantitative Reasoning, Efficient ML & NLP, Robustness & Generalization, Selective Answering, Spurious Bias and ML & NLP Applications. My strength lies in generating new ideas and I am fortunate to collaborate with a diverse set of awesome researchers through my ideas.

Learning From Instructions/Prompting
Cross-Task Generalization via Natural Language Crowdsourcing Instructions.
Swaroop Mishra, Daniel Khashabi, Chitta Baral, Hannaneh Hajishirzi
Annual Meeting of the Association for Computational Linguistics (ACL), 2022
Reframing Instructional Prompts to GPTk's Language.
Swaroop Mishra, Daniel Khashabi, Chitta Baral, Yejin Choi, Hannaneh Hajishirzi
Annual Meeting of the Association for Computational Linguistics (ACL) Findings, 2022
HELP ME THINK: A Simple Prompting Strategy for Non-experts to Create Customized Content with Models.
Swaroop Mishra, Elnaz Nouri
Preprint
Don't Blame the Annotator: Bias Already Starts in the Annotation Instructions.
Mihir Parmar*, Swaroop Mishra*, Mor Geva, Chitta Baral
Benchmarking Generalization via In-Context Instructions on 1,600+ Language Tasks.
Yizhong Wang*, Swaroop Mishra*, Pegah Alipoormolabashi, Yeganeh Kordi, ..., Chitta Baral, Yejin Choi, Noah A. Smith, Hannaneh Hajishirzi, Daniel Khashabi
Empirical Methods in Natural Language Processing (EMNLP), 2022
Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering.
Pan Lu, Swaroop Mishra, Tony Xia, Liang Qiu, Kai-Wei Chang, Song-Chun Zhu, Oyvind Tafjord, Peter Clark, Ashwin Kalyan
Conference on Neural Information Processing Systems (NeurIPS), 2022
In-BoXBART: Get Instructions into Biomedical Multi-task Learning.
Mihir Parmar, Swaroop Mishra, Mirali Purohit, Man Luo, M. Hassan Murad, Chitta Baral,
North American Chapter of the Association for Computational Linguistics (NAACL), 2022
Is a Question Decomposition Unit All We Need?
Swaroop Mishra*, Pruthvi Patel*, Mihir Parmar, Chitta Baral
Empirical Methods in Natural Language Processing (EMNLP), 2022
How Many Data Samples is an Additional Instruction Worth?
Ravsehaj Singh Puri, Swaroop Mishra, Mihir Parmar, Chitta Baral
Annual Meeting of the Association for Computational Linguistics (ACL) Workshop, 2022
Less is More: Summary of Long Instructions is Better for Program Synthesis
Swaroop Mishra*, Kirby Kuznia*, Mihir Parmar, Chitta Baral
Empirical Methods in Natural Language Processing (EMNLP), 2022
Instruction Learning for Biomedical Table Question Answering
Man Luo, Sharad Saxena, Swaroop Mishra, Mihir Parmar, Chitta Baral
BioASQ Workshop 2022
Creating Data Automatically by Instructing GPT3
Kirby Kuznia*, Maitreya Patel*, Swaroop Mishra, Santosh Mashetty, Savan Doshi, Ravsehaj Singh Puri, Mihir Parmar, Chitta Baral
Preprint
Quantitative Reasoning
NumGLUE: A Suite of Fundamental yet Challenging Mathematical Reasoning Tasks
Swaroop Mishra, Arindam Mitra, Neeraj Varshney, Bhavdeep Sachdeva, Peter Clark, Chitta Baral, Ashwin Kalyan
Annual Meeting of the Association for Computational Linguistics (ACL), 2022
LILA: A Unified Benchmark for Mathematical Reasoning
Swaroop Mishra*, Matthew Finlayson*, Pan Lu, Leonard Tang, Sean Welleck, Chitta Baral, Tanmay Rajpurohit, Oyvind Tafjord, Ashish Sabharwal, Peter Clark, Ashwin Kalyan
Empirical Methods in Natural Language Processing (EMNLP), 2022
Investigating Generalization and Catastrophic Forgetting in Numerical Reasoning
Swaroop Mishra, Chandrahaas Chintalaboguda, Sabyasachi Bisoyi, Chitta Baral
Preprint
John is 50 years old, can his son be 65? Evaluating Language Models' Understanding of Feasibility
Himanshu Gupta, Neeraj Varshney, Swaroop Mishra, Kuntal Kumar Pal, Saurabh Arjun Sawant, Kevin Joseph Scaria, Siddharth Goyal, Chitta Baral
Preprint
Efficient ML & NLP
ILDAE: Instance-Level Difficulty Analysis of Evaluation Data.
Neeraj Varshney, Swaroop Mishra, Chitta Baral
Annual Meeting of the Association for Computational Linguistics (ACL), 2022
Let the Model Decide its Curriculum for Multitask Learning
Neeraj Varshney, Swaroop Mishra, Chitta Baral
North American Chapter of the Association for Computational Linguistics (NAACL) Workshop, 2022
How Robust are Model Rankings : A Leaderboard Customization Approach for Equitable Evaluation
Swaroop Mishra, A Arunkumar
Conference on Artificial Intelligence (AAAI), 2021
`Hardness' of Samples Need to be Quantified for a Reliable Evaluation System: Exploring Potential Opportunities with a New Task
Swaroop Mishra, Anjana Arunkumar, Chris Bryan, Chitta Baral
Preprint
Commonsense Reasoning with Implicit Knowledge in Natural Language
Pratyay Banerjee*, Swaroop Mishra*, Kuntal Kumar Pal*, Arindam Mitra*, Chitta Baral
Conference on Automated Knowledge Base Construction (AKBC), 2021
A Visual Exploration of Fair Evaluation for ML - Bridging the Gap Between Research and the Real World
A Arunkumar, Swaroop Mishra, C Bryan
IEEE Visualization (IEEE VIS) Workshop, 2020
Front Contribution instead of Back Propagation
Swaroop Mishra, A Arunkumar
Conference on Neural Information Processing Systems (NeurIPS) Workshop, 2020
Robustness and Generalization
Generalized but not Robust? Understanding the Effects of Out-of-Domain Generalization Methods.
Tejas Gokhale*, Swaroop Mishra*, Man Luo*, Bhavdeep Sachdeva, Chitta Baral
Annual Meeting of the Association for Computational Linguistics (ACL) Findings, 2022
Pretrained Transformers May Not Provide More Robust Representation Than Traditional Models On Data with Noisy Labels
Swaroop Mishra, Bhavdeep Sachdeva, Chitta Baral
Preprint
Our Evaluation Metric Needs an Update to Encourage Generalization
Swaroop Mishra, A Arunkumar, C Bryan, C Baral
International Conference on Machine Learning (ICML) Workshop, 2020
Selective Answering
Investigating Selective Prediction Approaches Across Several Tasks in IID, OOD, and Adversarial Settings.
Neeraj Varshney, Swaroop Mishra, Chitta Baral
Annual Meeting of the Association for Computational Linguistics (ACL) Findings, 2022
Towards Improving Selective Prediction Ability of NLP Systems
Neeraj Varshney, Swaroop Mishra, Chitta Baral
Annual Meeting of the Association for Computational Linguistics (ACL) Workshop, 2022
Investigating Issues with the Area Under the Curve Metric and Proposing Solutions
Swaroop Mishra, Anjana Arunkumar, Chitta Baral
Preprint
Interviewer-Candidate Role Play: Towards Developing Real-World NLP Systems
Neeraj Varshney, Swaroop Mishra, Chitta Baral
Preprint
Spurious Bias
Do We Need to Create Big Datasets to Learn a Task?
Swaroop Mishra*, B Sachdeva*
Conference on Empirical Methods in Natural Language Processing (EMNLP) Workshop 2020
Identification and Curation of Parameters to Assess and Quantify the Quality of Benchmarks in NLP
Swaroop Mishra, Anjana Arunkumar, Chris Bryan, Chitta Baral
Preprint
Is High Quality Data All You Need?
Swaroop Mishra, A Arunkumar
Conference on Neural Information Processing Systems (NeurIPS) Workshop, 2020
Real-Time Visual Feedback for Educative Benchmark Creation : A Human-and-Metric-in-the-Loop Workflow
A Arunkumar, Swaroop Mishra, B Sachdeva, C Baral, C Bryan
Conference on Neural Information Processing Systems (NeurIPS) Workshop, 2020
DQI: A Guide to Benchmark Evaluation
Swaroop Mishra, A Arunkumar, B Sachdeva, C Bryan, C Baral
International Conference on Machine Learning (ICML) Workshop, 2020
ML & NLP Applications
Constructing Flow Graphs from Procedural Cyber Security Text
Kuntal Kumar Pal*, Kazuaki Kashihara*, Pratyay Banerjee*, Swaroop Mishra, Ruoyu Wang, Chitta Baral
Annual Meeting of the Association for Computational Linguistics (ACL) Findings, 2021
Towards the Development of Disaster Management Tailored Machine Learning Systems
Swaroop Mishra, Manas Kumar Jena, Ashok Kumar Tripathy
IEEE International Conference (INDISCON), 2022
Enabling cyber-physical demand response in smart grids via conjoint communication and controller design.
Swaroop Mishra, MP Korukonda, L Behera, A Shukla
IET Cyber-Physical Systems: Theory & Applications, 2019
Hybrid adaptive framework for coordinated control of distributed generators in cyber-physical energy systems
MP Korukonda, Swaroop Mishra, K Rajawat, L Behera
IET Cyber-Physical Systems: Theory & Applications, 2018
Handling multi-parametric variations in distributed control of cyber-physical systems through optimal communication design
MP Korukonda, Swaroop Mishra, A Shukla, L Behera
IET Cyber-Physical Systems: Theory & Applications, 2017
Improving microgrid voltage stability through cyber-physical control
MP Korukonda, Swaroop Mishra, A Shukla, L Behera
National Power System Conference (NPSC), 2016
A generalized novel framework for optimal sensor-controller connection design to guarantee a stable cyber physical smart grid
Swaroop Mishra, NV Srinath, MP Korukonda, L Behera
IEEE International Conference on Industrial Informatics (INDIN), 2015

Template from the awesome Jon