Publications

Publications by categories in reversed chronological order. For recent publications, please visit my Google Scholar Page.

2025

  1. TMLR
    Combinatorial Multi-armed Bandits: Arm Selection via Group Testing
    Arpan Mukherjee, Shashanka Ubaru, Keerthiram Murugesan, and 2 more authors
    Transactions on Machine Learning Research (TMLR), 2025
  2. NAACL
    Granite Guardian: Comprehensive LLM Safeguarding
    Inkit Padhi, Manish Nagireddy, Giandomenico Cornacchia, and 19 more authors
    In 2025 Annual Conference of the North American Chapter of the Association for Computational Linguistics Industry Track, 2025
  3. KDD
    MOPI-HFRS: A Multi-objective Personalized Health-aware Food Recommendation System with LLM-enhanced Interpretation
    Zheyuan Zhang, Zehong Wang, Tianyi Ma, and 8 more authors
    In KDD 2025, 2025
  4. ACL
    NGQA: a nutritional graph question answering benchmark for personalized health-aware nutritional reasoning
    Zheyuan Zhang, Yiyang Li, Nhi Ha Lan Le, and 8 more authors
    In Association for Computational Linguistics (ACL 2025), 2025
  5. Sequential uncertainty quantification with contextual tensors for social targeting
    Tsuyoshi Idé, Keerthiram Murugesan, Djallel Bouneffouf, and 1 more author
    Knowledge and Information Systems, 2025
  6. Cross-Examiner: Evaluating Consistency of Large Language Model-Generated Explanations
    Danielle Villa, Maria Chang, Keerthiram Murugesan, and 2 more authors
    arXiv preprint arXiv:2503.08815, 2025
  7. PEEL the Layers and Find Yourself: Revisiting Inference-Time Data Leakage for Residual Neural Networks
    Huzaifa Arif, Keerthiram Murugesan, Payel Das, and 2 more authors
    In 2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), 2025
  8. NAACL
    Are Large Language Models Effective in Clinical Trial Design? A Study on Baseline Feature Generation
    Nafis Neehal, Bowen Wang, Shayom Debopadhaya, and 5 more authors
    In Findings of the Association for Computational Linguistics: NAACL 2025, 2025
  9. NAACL
    Granite Guardian: Comprehensive LLM Safeguarding
    Inkit Padhi, Manish Nagireddy, Giandomenico Cornacchia, and 8 more authors
    In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: Industry Track), 2025
  10. EfficientLLM: Efficiency in Large Language Models
    Zhengqing Yuan, Weixiang Sun, Yixin Liu, and 8 more authors
    arXiv preprint arXiv:2505.13840, 2025
  11. AutoData: A Multi-Agent System for Open Web Data Collection
    Tianyi Ma, Yiyue Qian, Zheyuan Zhang, and 8 more authors
    arXiv preprint arXiv:2505.15859, 2025
  12. PATENT
    Generating symbolic plans using transformer-based models
    Francesca Rossi, Lior Horesh, Keerthiram Murugesan, and 3 more authors
    May 2025
    US Patent App. 18/509,359
  13. TMLR
    Group Fair Federated Learning via Stochastic Kernel Regularization
    Huzaifa Arif, Pin-Yu Chen, Keerthiram Murugesan, and 1 more author
    Transactions on Machine Learning Research, May 2025
  14. ARXIV
    Context Attribution with Multi-Armed Bandit Optimization
    Deng Pan, Keerthiram Murugesan, Nuno Moniz, and 1 more author
    arXiv preprint arXiv:2506.19977, May 2025
  15. Thinking Fast and Slow in Human and Machine Intelligence
    Francesco Fabiano, Marianna B Ganapini, Andrea Loreggia, and 6 more authors
    Communications of the ACM, May 2025
  16. Highlight All the Phrases: Enhancing LLM Transparency through Visual Factuality Indicators
    Hyo Jin Do, Rachel Ostrand, Werner Geyer, and 3 more authors
    In ACM Conference on AI, Ethics and Society (AIES 2025), May 2025
  17. Language Models Coupled with Metacognition Can Outperform Reasoning Models
    Vedant Khandelwal, Francesca Rossi, Keerthiram Murugesan, and 4 more authors
    arXiv preprint arXiv:2508.17959, May 2025
  18. COLM
    The Unlearning Mirage: A Dynamic Framework for Evaluating LLM Unlearning
    Raj Sanjay Shah, Jing Huang, Keerthiram Murugesan, and 2 more authors
    In Second Conference on Language Modeling, May 2025
  19. ACL
    Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agents
    Ivoline C Ngong, Swanand Kadhe, Hao Wang, and 4 more authors
    In Findings of the Association for Computational Linguistics: ACL 2025, May 2025

2024

  1. On the prospects of incorporating large language models (llms) in automated planning and scheduling (aps)
    Vishal Pallagani, Bharath Chandra Muppasani, Kaushik Roy, and 7 more authors
    In Proceedings of the International Conference on Automated Planning and Scheduling, May 2024
  2. AAAI
    Harnessing Large Language Models for Planning: A Lab on Strategies for Success and Mitigation of Pitfalls
    Vishal Pallagani, Keerthiram Murugesan, Biplav Srivastava, and 2 more authors
    In AAAI Conference on Artificial Intelligence, May 2024
  3. Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning
    Shuai Zhang, Heshan Devaka Fernando, Miao Liu, and 5 more authors
    May 2024
  4. EXPLORER: Exploration-guided Reasoning for Textual Reinforcement Learning
    Kinjal Basu, Keerthiram Murugesan, Subhajit Chaudhury, and 3 more authors
    In European Chapter of the Association for Computational Linguistics, May 2024
  5. ACL
    Language Guided Exploration for RL Agents in Text Environments
    Hitesh Golchha, Sahil Yerawar, Dhruvesh Patel, and 2 more authors
    In ACL Findings 2024, May 2024
  6. ARXIV
    Detectors for safe and reliable llms: Implementations, uses, and limitations
    Swapnaja Achintalwar, Adriana Alvarado Garcia, Ateret Anaby-Tavor, and 8 more authors
    arXiv preprint arXiv:2403.06009, May 2024
  7. Variance Reduction Can Improve Trade-Off in Multi-Objective Learning
    Heshan Fernando, Lisha Chen, Songtao Lu, and 7 more authors
    In ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2024
  8. ACL
    STARLING: Self-supervised Training of Text-based Reinforcement Learning Agent with Large Language Models
    Shreyas Basavatia, Keerthiram Murugesan, and Shivam Ratnakar
    ACL 2024 Findings, May 2024
  9. Leveraging Visual Handicaps for Text-Based Reinforcement Learning
    Subhajit Chaudhury, Keerthiram Murugesan, Thomas Carta, and 2 more authors
    In ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2024
  10. Moral High Ground: A text-based games benchmark for moral evaluation
    Matthew Pisano, Keerthiram Murugesan, Lamogha Chiazor, and 3 more authors
    May 2024
  11. On the Effects of Fine-tuning Language Models for Text-Based Reinforcement Learning
    Mauricio Gruppi, Soham Dan, Keerthiram Murugesan, and 1 more author
    EACL 2024, May 2024
  12. Facilitating Human-LLM Collaboration through Factuality Scores and Source Attributions
    Hyo Jin Do, Rachel Ostrand, Justin Weisz, and 5 more authors
    In ACM CHI Conference on Human Factors in Computing Systems, May 2024
  13. ICML
    SF-DQN: Provable knowledge transfer using successor feature for deep reinforcement learning
    Shuai Zhang, Heshan Devaka Fernando, Miao Liu, and 5 more authors
    In International Conference on Machine Learning (ICML 2024), May 2024
  14. ARXIV
    Ctbench: A comprehensive benchmark for evaluating language model capabilities in clinical trial design
    Nafis Neehal, Bowen Wang, Shayom Debopadhaya, and 4 more authors
    arXiv preprint arXiv:2406.17888, May 2024
  15. EMNLP
    Towards Aligning Language Models with Textual Feedback
    Saüc Abadal Lloret, Shehzaad Dhuliawala, Keerthiram Murugesan, and 1 more author
    In EMNLP 2024, May 2024
  16. NAACL
    Beyond Visual Augmentation: Investigating Bias in Multi-Modal Text Generation
    Fnu Mohbat, Vijay Sadashivaiah, Keerthiram Murugesan, and 3 more authors
    In NAACL 2024 Workshop on Trustworthy Natural Language Processing (NAACL TrustNLP 2024), May 2024
  17. NeurIPS
    Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agents
    Ivoline C Ngong, Swanand Kadhe, Hao Wang, and 4 more authors
    In NeurIPS 2024 Workshop on Socially Responsible Language Modeling Research (SoLaR), May 2024
  18. Examining Trustworthiness of LLM-as-a-Judge Systems in a Clinical Trial Design Benchmark
    Corey Curran, Nafis Neehal, Keerthiram Murugesan, and 1 more author
    In 2024 IEEE International Conference on Big Data (BigData), May 2024

2023

  1. Plansformer: Generating Multi-Domain Symbolic Plans using Transformers
    Vishal Pallagani, Bharath Chandra Muppasani, Keerthiram Murugesan, and 5 more authors
    May 2023
  2. ICLR
    Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Approach
    Heshan Devaka Fernando, Han Shen, Miao Liu, and 3 more authors
    In Proceeding of 11th International Conference on Learning Representations (ICLR 2023), May 2023
  3. ARXIV
    Fast and slow planning
    Francesco Fabiano, Vishal Pallagani, Marianna Bergamaschi Ganapini, and 5 more authors
    arXiv preprint arXiv:2303.04283, May 2023
  4. ARXIV
    Understanding the capabilities of large language models for automated planning
    Vishal Pallagani, Bharath Muppasani, Keerthiram Murugesan, and 5 more authors
    arXiv preprint arXiv:2305.16151, May 2023
  5. Complexworld: A large language model-based interactive fiction learning environment for text-based reinforcement learning agents
    Shreyas Basavatia, Shivam Ratnakar, and Keerthiram Murugesan
    In International Joint Conference on Artificial Intelligence 2023 Workshop on Knowledge-Based Compositional Generalization, May 2023
  6. ACL
    MISMATCH: Fine-grained Evaluation of Machine-generated Text with Mismatch Error Types
    Keerthiram Murugesan, Sarathkrishna Swaminathan, Soham Dan, and 8 more authors
    ACL 2023 (Findings), May 2023
  7. ACL
    Learning Symbolic Rules over Abstract Meaning Representations for Textual Reinforcement Learning
    Subhajit Chaudhury, Sarathkrishna Swaminathan, Daiki Kimura, and 8 more authors
    ACL 2023, May 2023
  8. ARXIV
    Value-based fast and slow ai nudging
    Marianna B Ganapini, Francesco Fabiano, Lior Horesh, and 7 more authors
    arXiv preprint arXiv:2307.07628, May 2023
  9. IJCAI
    Probabilistic Rule Induction from Event Sequences with Logical Summary Markov Models.
    Debarun Bhattacharjya, Oktie Hassanzadeh, Ronny Luss, and 1 more author
    In IJCAI, May 2023
  10. IJCAI
    Plansformer Tool: Demonstrating Generation of Symbolic Plans Using Transformers.
    Vishal Pallagani, Bharath Muppasani, Biplav Srivastava, and 8 more authors
    In IJCAI, May 2023
  11. NeurIPS
    On the convergence and sample complexity analysis of deep q-networks with $\backslashepsilon $-greedy exploration
    Shuai Zhang, Hongkang Li, Meng Wang, and 6 more authors
    Advances in Neural Information Processing Systems, May 2023
  12. Plan-SOFAI: A neuro-symbolic planning architecture
    Francesco Fabiano, Vishal Pallagani, Marianna Bergamaschi Ganapini, and 5 more authors
    In Neuro-Symbolic Learning and Reasoning in the era of Large Language Models, May 2023
  13. To Transfer or Not to Transfer: Suppressing Concepts from Source Representations
    Vijay Sadashivaiah, Keerthiram Murugesan, Ronny Luss, and 4 more authors
    Transactions on Machine Learning Research, May 2023

2022

  1. AAAI
    Eye of the Beholder: Improved Relation Generalization for Text-based Reinforcement Learning Agents
    Keerthiram Murugesan, Subhajit Chaudhury, and Kartik Talamadupula
    In Proceedings of the 36th AAAI Conference on Artificial Intelligence, May 2022
  2. ICLR
    Case-based Reasoning for Better Generalization in Text-Adventure Games
    Mattia Atzeni, Shehzaad Dhuliawala, Keerthiram Murugesan, and 1 more author
    In Proceedings of 10th International Conference on Learning Representations (ICLR 2022), May 2022
  3. ICLR
    Auto-Transfer: Learning to Route Transferrable Representations
    Keerthiram Murugesan, Vijay Sadashivaiah, Ronny Luss, and 3 more authors
    In Proceedings of 10th International Conference on Learning Representations (ICLR 2022), May 2022
  4. SCERL: A Text-based Safety Benchmark for Reinforcement Learning Problems
    Lan Hoang, Nicolas Galichet, Akifumi Wachi, and 7 more authors
    May 2022
  5. VISUALHANDICAPS: Systematic Handicaps for Text-based Games
    Subhajit Chaudhury, Keerthiram Murugesan, Thomas CARTA, and 2 more authors
    May 2022
  6. SCERL: A Benchmark for intersecting language and safe reinforcement learning
    Lan Hoang, Shivam Ratnakar, Nicolas Galichet, and 6 more authors
    In Second Workshop on Language and Reinforcement Learning, May 2022
  7. ARXIV
    Mitigating gradient bias in multi-objective learning: A provably convergent stochastic approach
    Heshan Fernando, Han Shen, Miao Liu, and 3 more authors
    arXiv preprint arXiv:2210.12624, May 2022
  8. NeurIPS
    A Text-based Safety Benchmark for Reinforcement Learning Problems
    Ngoc Lan Hoang, Nicolas Galichet, Akifumi Wachi, and 7 more authors
    In Annual Conference on Neural Information Processing Systems, May 2022
  9. ARXIV
    Targeted advertising on social networks using online variational tensor regression
    Tsuyoshi Idé, Keerthiram Murugesan, Djallel Bouneffouf, and 1 more author
    arXiv preprint arXiv:2208.10627, May 2022
  10. PATENT
    Influence maximization on social networks with tensor bandits
    Keerthiram Murugesan, Tsuyoshi Ide, and Djallel Bouneffouf
    Apr 2022
    US Patent App. 17/069,829
  11. Controllable Concept Transfer of Intermediate Representations
    Vijay Sadashivaiah, Keerthiram Murugesan, Ronny Luss, and 4 more authors
    Apr 2022
  12. EMNLP
    X-factor: A cross-metric evaluation of factual correctness in abstractive summarization
    Subhajit Chaudhury, Sarathkrishna Swaminathan, Chulaka Gunasekara, and 8 more authors
    In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, Apr 2022
  13. ARXIV
    Plansformer: Generating symbolic plans using transformers
    Vishal Pallagani, Bharath Muppasani, Keerthiram Murugesan, and 5 more authors
    arXiv preprint arXiv:2212.08681, Apr 2022

2021

  1. AAAI
    Text-based rl agents with commonsense knowledge: New challenges, environments and baselines
    Keerthiram Murugesan, Mattia Atzeni, Pavan Kapanipathi, and 6 more authors
    In Proceedings of the AAAI Conference on Artificial Intelligence, Apr 2021
    arXiv HTML
    72 Google Scholar citations
  2. AAAI
    Thinking fast and slow in AI
    Grady Booch, Francesco Fabiano, Lior Horesh, and 8 more authors
    In Proceedings of the AAAI Conference on Artificial Intelligence, Apr 2021
    arXiv PDF
    150 Google Scholar citations
  3. ACL
    Efficient Text-based Reinforcement Learning by Jointly Leveraging State and Commonsense Graph Representations
    Keerthiram Murugesan, Mattia Atzeni, Pavan Kapanipathi, and 3 more authors
    In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics (ACL), Apr 2021
  4. A hybrid neuro-symbolic approach for text-based games using inductive logic programming
    Kinjal Basu, Keerthiram Murugesan, Mattia Atzeni, and 6 more authors
    In Combining learning and reasoning: programming languages, formalisms, and representations, Apr 2021
  5. AAAI
    Epistemic Planning in a Fast and Slow Setting.
    Francesco Fabiano, Marianna Bergamaschi Ganapini, Lior Horesh, and 6 more authors
    In TFSOCTAI@ AAAI Fall Symposium, Apr 2021

2020

  1. ARXIV
    Enhancing text-based reinforcement learning agents with commonsense knowledge
    Keerthiram Murugesan, Mattia Atzeni, Pushkar Shukla, and 3 more authors
    arXiv preprint arXiv:2005.00811, Apr 2020
  2. ARXIV
    Thinking fast and slow in ai (2020)
    Grady Booch, Francesco Fabiano, Lior Horesh, and 8 more authors
    arXiv preprint arXiv:2010.06002, Apr 2020

2018

  1. Scalable Multitask and Lifelong Learning
    Keerthiram Murugesan
    Apr 2018
  2. Lifelong Learning with Output Kernels
    Keerthiram Murugesan, and Jaime Carbonell
    Apr 2018

2017

  1. Multi-Task Multiple Kernel Relationship Learning
    Keerthiram Murugesan, and Jaime Carbonell
    In Proceedings of the 17th SIAM International Conference on Data Mining (SDM 2017), Houston, Texas, USA, 2017, Apr 2017
  2. IJCAI
    Self-Paced Multitask Learning with Shared Knowledge
    Keerthiram Murugesan, and Jaime Carbonell
    In Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI-17), Melbourne, Australia, 2017., Apr 2017
  3. ARXIV
    Co-clustering for multitask learning
    Keerthiram Murugesan, Jaime Carbonell, and Yiming Yang
    arXiv preprint arXiv:1703.00994, Apr 2017
  4. NeurIPS
    Active learning from peers
    Keerthiram Murugesan, and Jaime Carbonell
    Advances in Neural Information Processing Systems, Apr 2017
  5. Online and adaptive methods for multitask learning
    Keerthiram Murugesan
    Carnegie Mellon University, Apr 2017
  6. Multitask matrix completion for learning protein protein interactions across diseases
    Meghana Kshirsagar, Keerthiram Murugesan, Jaime Carbonell, and 1 more author
    Journal of Computational Biology, Apr 2017

2016

  1. NeurIPS
    Adaptive Smoothed Online Multi-Task Learning
    Keerthiram Murugesan, Hanxiao Liu, Jaime Carbonell, and 1 more author
    In Advances in Neural Information Processing Systems (NIPS 2016), Apr 2016
  2. Multitask Matrix Completion for Learning Protein Interactions Across Diseases
    Meghana Kshirsagar, Jaime Carbonell, Judith Klein-Seetharaman, and 1 more author
    In International Conference on Research in Computational Molecular Biology (RECOMB), Apr 2016

2015

  1. Predicting Workplace Incidents with Temporal Graph-guided Fused Lasso
    Keerthiram Murugesan, and Jaime Carbonell
    Apr 2015

2013

  1. Learning Latent Tree Structure for Natural Language
    Keerthiram Murugesan
    Apr 2013

2011

  1. Hybrid hierarchical clustering: An experimental analysis
    Keerthiram Murugesan, and Jun Zhang
    University of Kentucky, Lexington, Technical Report: CMIDA-HiPSCCS, Apr 2011
  2. Hybrid bisect K-means clustering algorithm
    Keerthiram Murugesan, and Jun Zhang
    In 2011 International Conference on Business Computing and Global Informatization, Apr 2011
  3. A New Term Weighting Scheme for Document Clustering
    Keerthiram Murugesan, and Jun Zhang
    Apr 2011
  4. Cluster-Based Term Weighting and Document Ranking Models
    Keerthiram Murugesan
    University of Kentucky, Apr 2011
  5. A New Term Weighting Scheme for Document Clustering
    A KEERTHIRAM MURUGESAN, and B JUN ZHANG
    In DMIN 2011: proceedings of the 2011 international conference on data mining (Las Vegas NV, July 18-21, 2011), Apr 2011