Varun Kumar

Most-cited papers

BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation
J. Dhamala, Tony Sun, Varun Kumar, Satyapriya Krishna +3 more
2021Conference on Fairness, Accountability and Transparency645 citations Open access
Semantic Scholar
Data Augmentation using Pre-trained Transformer Models
Varun Kumar, Ashutosh Choudhary, Eunah Cho
2020LIFELONGNLP420 citations Open access
Semantic Scholar
Multi-lingual Evaluation of Code Generation Models
Ben Athiwaratkun, Sanjay Krishna Gouda, Zijian Wang, Xiaopeng Li +21 more
2022International Conference on Learning Representations265 citations Open access
Semantic Scholar
ReCode: Robustness Evaluation of Code Generation Models
Shiqi Wang, Zheng Li, Haifeng Qian, Cheng Yang +10 more
2022Annual Meeting of the Association for Computational Linguistics179 citations Open access
Semantic Scholar
On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representations
Yang Trista Cao, Yada Pruksachatkun, Kai-Wei Chang, Rahul Gupta +3 more
2022Annual Meeting of the Association for Computational Linguistics116 citations Open access
Semantic Scholar
A Closer Look At Feature Space Data Augmentation For Few-Shot Intent Classification
Varun Kumar, Hadrien Glaude, Cyprien de Lichy, Wlliam Campbell
2019Conference on Empirical Methods in Natural Language Processing91 citations Open access
Semantic Scholar
Closing the Loop: User-Centered Design and Evaluation of a Human-in-the-Loop Topic Modeling System
Alison Smith-Renner, Varun Kumar, Jordan L. Boyd-Graber, Kevin Seppi +1 more
2018International Conference on Intelligent User Interfaces90 citations
Semantic Scholar
The Amazon Nova Family of Models: Technical Report and Model Card
Amazon Agi, Aaron Langford, Aayush Shah, Abhanshu Gupta +496 more
2025arXiv.org75 citations
Semantic Scholar
Training LLMs to Better Self-Debug and Explain Code
Nan Jiang, Xiao-Peng Li, Shi-Qi Wang, Qiang Zhou +5 more
2024Neural Information Processing Systems69 citations
Semantic Scholar
Reasoning in Token Economies: Budget-Aware Evaluation of LLM Reasoning Strategies
Junlin Wang, Siddhartha Jain, Dejiao Zhang, B. Ray +2 more
2024Conference on Empirical Methods in Natural Language Processing67 citations
Semantic Scholar
Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal
Umang Gupta, J. Dhamala, Varun Kumar, Apurv Verma +6 more
2022Findings66 citations Open access
Semantic Scholar
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations
Sebastian Gehrmann, H. Strobelt, Alexander M. Rush, Fabio Kepler +496 more
201955 citations Open access
Semantic Scholar
On Mitigating Code LLM Hallucinations with API Documentation
Nihal Jain, Robert Kwiatkowski, B. Ray, Murali Krishna Ramanathan +1 more
20242025 IEEE/ACM 47th International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP)42 citations Open access
Semantic Scholar
Towards Greener Yet Powerful Code Generation via Quantization: An Empirical Study
Xiao-Kai Wei, Sujan Kumar Gonugondla, Shiqi Wang, W. Ahmad +12 more
2023ESEC/SIGSOFT FSE42 citations Open access
Semantic Scholar
Fewer Truncations Improve Language Modeling
Hantian Ding, Zi-Jian Wang, Giovanni Paolini, Varun Kumar +3 more
2024International Conference on Machine Learning39 citations
Semantic Scholar
A Static Evaluation of Code Completion by Large Language Models
Hantian Ding, Varun Kumar, Yuchen Tian, Zijian Wang +8 more
2023Annual Meeting of the Association for Computational Linguistics25 citations Open access
Semantic Scholar
Resolving Ambiguities in Text-to-Image Generative Models
Ninareh Mehrabi, Palash Goyal, Apurv Verma, J. Dhamala +6 more
2023Annual Meeting of the Association for Computational Linguistics25 citations Open access
Semantic Scholar
Why Didn’t You Listen to Me? Comparing User Control of Human-in-the-Loop Topic Models
Varun Kumar, Alison Smith-Renner, Leah Findlater, Kevin Seppi +1 more
2019Annual Meeting of the Association for Computational Linguistics25 citations Open access
Semantic Scholar
Cyber-Zero: Training Cybersecurity Agents without Runtime
Terry Yue Zhuo, Ding-Min Wang, Hantian Ding, Varun Kumar +1 more
2025arXiv.org23 citations
Semantic Scholar
Learning Code Preference via Synthetic Evolution
Jia-Wei Liu, Thanh Nguyen, Ming-Yue Shang, Hantian Ding +4 more
2024arXiv.org22 citations
Semantic Scholar
Digging into user control: perceptions of adherence and instability in transparent models
Alison Smith-Renner, Varun Kumar, Kevin Seppi, Leah Findlater
2020International Conference on Intelligent User Interfaces21 citations Open access
Semantic Scholar
Mining Shapes of Expertise in Online Social Q&A Communities
Varun Kumar, N. Pedanekar
2016CSCW Companion20 citations
Semantic Scholar
Protoda: Efficient Transfer Learning for Few-Shot Intent Classification
Manoj Kumar, Varun Kumar, Hadrien Glaude, Cyprien de Lichy +2 more
2021Spoken Language Technology Workshop18 citations Open access
Semantic Scholar
Efficient Semi-Supervised Learning for Natural Language Understanding by Optimizing Diversity
Eunah Cho, He Xie, John P. Lalor, Varun Kumar +1 more
2019Automatic Speech Recognition & Understanding17 citations Open access
Semantic Scholar
Training Language Model Agents to Find Vulnerabilities with CTF-Dojo
Terry Yue Zhuo, Ding-Min Wang, Hantian Ding, Varun Kumar +1 more
2025arXiv.org16 citations
Semantic Scholar
An Analysis of The Effects of Decoding Algorithms on Fairness in Open-Ended Language Generation
J. Dhamala, Varun Kumar, Rahul Gupta, Kai-Wei Chang +1 more
2022Spoken Language Technology Workshop13 citations Open access
Semantic Scholar
The GW/UMD CLPsych 2016 Shared Task System
Ayah Zirikly, Varun Kumar, P. Resnik
2016CLPsych@HLT-NAACL13 citations Open access
Semantic Scholar
Empowering Multi-Turn Tool-Integrated Agentic Reasoning with Group Turn Policy Optimization
Yi-Feng Ding, Hung Le, Song Han, Kang-Rui Ruan +4 more
2025Annual Meeting of the Association for Computational Linguistics12 citations Open access
Semantic Scholar
Industry Scale Semi-Supervised Learning for Natural Language Understanding
Luoxin Chen, F. Garcia, Varun Kumar, He Xie +1 more
2021North American Chapter of the Association for Computational Linguistics10 citations Open access
Semantic Scholar
CodeAssistBench (CAB): Dataset & Benchmarking for Multi-turn Chat-Based Code Assistance
Myeongsoo Kim, Shweta Garg, B. Ray, Varun Kumar +1 more
2025Neural Information Processing Systems9 citations
Semantic Scholar
Coherence Collapse: Diagnosing Why Code Agents Fail After Reaching the Right Code
Myeongsoo Kim, Ding-Min Wang, Siwei Cui, Farima Farmahinifarahani +5 more
20268 citations
Semantic Scholar
Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks
Shoumik Saha, Ji-Fan Chen, Sam Mayers, Sanjay Krishna Gouda +2 more
2025Transactions of the Association for Computational Linguistics8 citations
Semantic Scholar
Greener yet Powerful: Taming Large Code Generation Models with Quantization
Xiao-Kai Wei, Sujan Kumar Gonugondla, W. Ahmad, Shiqi Wang +12 more
2023arXiv.org8 citations Open access
Semantic Scholar
Is the Elephant Flying? Resolving Ambiguities in Text-to-Image Generative Models
Ninareh Mehrabi, Palash Goyal, Apurv Verma, J. Dhamala +6 more
2022arXiv.org8 citations Open access
Semantic Scholar
CodeScout: Contextual Problem Statement Enhancement for Software Agents
Manan Suri, Xiangci Li, Mehdi Shojaie, Song Han +4 more
2026Annual Meeting of the Association for Computational Linguistics7 citations
Semantic Scholar
FairCoder: Evaluating Social Bias of LLMs in Code Generation
Yong-Kang Du, Jen-Tse Huang, Jie-Yu Zhao, Lu Lin +80 more
7 citations
Semantic Scholar
CODESTRUCT: Code Agents over Structured Action Spaces
Myeongsoo Kim, J. Hsu, Di Wang, Shweta Garg +2 more
2026Annual Meeting of the Association for Computational Linguistics6 citations
Semantic Scholar
Planning-Aware Code Infilling via Horizon-Length Prediction
Yi-Feng Ding, Hantian Ding, Shi-Qi Wang, Qing Sun +2 more
2024Conference on Empirical Methods in Natural Language Processing6 citations Open access
Semantic Scholar
TRAJEVAL: Decomposing Code Agent Trajectories for Fine-Grained Diagnosis
Myeongsoo Kim, Ding-Min Wang, Siwei Cui, Farima Farmahinifarahani +5 more
2026arXiv.org5 citations
Semantic Scholar
Automatically augmenting learning material with practical questions to increase its relevance
G. Singh, Varun Kumar, S. Bhat, N. Pedanekar
2015Frontiers in Education Conference5 citations
Semantic Scholar
SpecAgent: A Speculative Retrieval and Forecasting Agent for Code Completion
George Ma, Anurag Koul, Qi Chen, Yawen Wu +5 more
2025Annual Meeting of the Association for Computational Linguistics4 citations
Semantic Scholar
Horizon-Length Prediction: Advancing Fill-in-the-Middle Capabilities for Code Generation with Lookahead Planning
Yi-Feng Ding, Hantian Ding, Shi-Qi Wang, Qing Sun +2 more
2024arXiv.org4 citations
Semantic Scholar
Proceedings of the 28th International Conference on Computational Linguistics: Industry Track
Nria Bel, Cheng-Qing Zong, L. Wanner, Horacio Saggion +172 more
20203 citations Open access
Semantic Scholar
Automatically Retrieving Explanatory Analogies from Webpages
Varun Kumar, S. Bhat, N. Pedanekar
2014European Conference on Information Retrieval3 citations
Semantic Scholar
PUSTACK: towards an augmented, scalable and personalized interface for paper textbooks
Naman Gandhi, V. Gaikwad, Pratik Kasat, Nikita Garg +5 more
2013Asia-Pacific Computer and Human Interaction3 citations
Semantic Scholar
AHEAD: Adaptive Hindsight with Environment-Augmented Distillation for Agentic RL
Xiaolong Jin, Ding-Min Wang, Vijay Lingam, Varun Kumar
20262 citations
Semantic Scholar
Recent Trends in Text-to-Image GAN
Varun Kumar, Dharmender Kumar
2024IEEE International Symposium on Compound Semiconductors2 citations
Semantic Scholar
Assessing the Need of Augmenting Video Lectures with Supporting Information
G. Singh, A. Doke, Varun Kumar, S. Bhat +1 more
2014Interacción2 citations
Semantic Scholar
Lis-ten to Me? Comparing User Control of Human-in-the-Loop
Varun Kumar, Alison Smith, Leah Findlater, Kevin Seppi
20231 citations
Semantic Scholar
ANTE: Anticipate, Then Execute -- Learning Internal World Models for Coding Agents from Verified Beliefs
Yi-Rou Ge, Kang-Rui Ruan, Ji-Fan Chen, Manish Prajapat +5 more
20260 citations
Semantic Scholar