Teaching an Old LLM Secure Coding: Localized Preference Optimization on Distilled Preferences
Mohammad Saqib Hasan, Saikat Chakraborty, Santu Karmaker, Niranjan Balasubramanian
ACL 2025 | May 2025
Saikat Chakraborty
Senior Researcher
Publications
-
-
-
Towards Neural Synthesis for SMT-Assisted Proof-Oriented Programming
Saikat Chakraborty, Gabriel Ebner, Siddharth Bhat, Sarah Fakhoury, Sakina Fatima, Shuvendu Lahiri, Nikhil Swamy
International Conference on Software Engineering | April 2025
-
-
-
Leveraging LLMs for Program Verification
Adharsh Kamath, Aditya Senthilnathan, Saikat Chakraborty, Pantazis Deligiannis, Shuvendu Lahiri, Akash Lal, Aseem Rastogi, Subhajit Roy, Rahul Sharma
Formal Methods in Computer-Aided Design (FMCAD) | October 2024
-
Can Large Language Models Transform Natural Language Intent into Formal Method Postconditions?
Madeline Endres, Sarah Fakhoury, Saikat Chakraborty, Shuvendu Lahiri
The ACM International Conference on the Foundations of Software Engineering (FSE) | July 2024
GitHub page https://github.com/microsoft/nl-2-postcond/
-
NL2Fix: Generating Functionally Correct Code Edits from Bug Descriptions
Sarah Fakhoury, Saikat Chakraborty, Madan Musuvathi, Shuvendu Lahiri
International Conference on Software Engineering | May 2024
Poster track
-
LLM-Based Test-Driven Interactive Code Generation: User Study and Empirical Evaluation
Sarah Fakhoury, Aaditya Naik, Georgios Sakkas, Saikat Chakraborty, Shuvendu Lahiri
IEEE Transactions on Software Engineering | April 2024, Vol 50: pp. 2254-2268
-
-
-
Ranking LLM-Generated Loop Invariants for Program Verification
Saikat Chakraborty, Shuvendu Lahiri, Sarah Fakhoury, Madan Musuvathi, Akash Lal, Aseem Rastogi, Nikhil Swamy, Rahul Sharma
Empirical Methods in Natural Language Processing | December 2023
EMNLP-Findings 2023
-
Grace: Language Models Meet Code Edits
Priyanshu Gupta, Avishree Khare, Yasharth Bajpai, Saikat Chakraborty, Sumit Gulwani, Aditya Kanade, Arjun Radhakrishna, Gustavo Soares, Ashish Tiwari
ESEC/FSE 2023: Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering | November 2023
-
AVATAR: A Parallel Corpus for Java-Python Program Translation
Wasi Uddin Ahmad, Md Golam Rahman Tushar, Saikat Chakraborty, Kai-Wei Chang
ACL 2023 | May 2023
-
-
-
NatGen: Generative pre-training by “Naturalizing” source code
Saikat Chakraborty, Toufique Ahmed, Yangruibo Ding, Premkumar Devanbu,, Baishakhi Ray
The ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) | November 2022
-
Interactive Code Generation via Test-Driven User-Intent Formalization
Shuvendu Lahiri, Sarah Fakhoury, Aaditya Naik, Georgios Sakkas, Saikat Chakraborty, Piali Choudhury, Curtis von Veh, Madan Musuvathi, Jeevana Priya Inala, Chenglong Wang, Jianfeng Gao
August 2022
arXiv | August 2022
-
Towards Learning (Dis)-Similarity of Source Code from Program Contrasts
Yangruibo Ding, Luca Buratti, Saurabh Pujar, Alessandro Morari, Baishakhi Ray, Saikat Chakraborty
60th Annual Meeting of the Association for Computational Linguistics | May 2022
-
-
-
Deep learning based vulnerability detection: Are we there yet?
Saikat Chakraborty, Rahul Krishna, Yangruibo Ding, Baishakhi Ray
IEEE Transactions on Software Engineering | October 2021
-
Unified Pre-training for Program Understanding and Generation.
Saikat Chakraborty, Wasi Ahmad, Baishakhi Ray, Kai-wei Chang
October 2021
-
On Multi-Modal Learning of Editing Source Code.
Saikat Chakraborty, Baishakhi Ray
The 36th IEEE/ACM International Conference on Automated Software Engineering (ASE'21) | May 2021
-
Retrieval Augmented Code Generation and Summarization.
M. Rizwan Parvez, Wasi Ahmad, Saikat Chakraborty, Baishakhi Ray, Kai-Wei Chang
Empirical Method in Natural Language Processing (EMNLP-findings) - 2021 | May 2021
-
-
-
Teaching an Old LLM Secure Coding: Localized Preference Optimization on Distilled Preferences
Mohammad Saqib Hasan, Saikat Chakraborty, Santu Karmaker, Niranjan Balasubramanian
ACL 2025 | May 2025
-
-
-
Teaching an Old LLM Secure Coding: Localized Preference Optimization on Distilled Preferences
Mohammad Saqib Hasan, Saikat Chakraborty, Santu Karmaker, Niranjan Balasubramanian
ACL 2025 | May 2025
-
Towards Neural Synthesis for SMT-Assisted Proof-Oriented Programming
Saikat Chakraborty, Gabriel Ebner, Siddharth Bhat, Sarah Fakhoury, Sakina Fatima, Shuvendu Lahiri, Nikhil Swamy
International Conference on Software Engineering | April 2025
-
Leveraging LLMs for Program Verification
Adharsh Kamath, Aditya Senthilnathan, Saikat Chakraborty, Pantazis Deligiannis, Shuvendu Lahiri, Akash Lal, Aseem Rastogi, Subhajit Roy, Rahul Sharma
Formal Methods in Computer-Aided Design (FMCAD) | October 2024
-
Can Large Language Models Transform Natural Language Intent into Formal Method Postconditions?
Madeline Endres, Sarah Fakhoury, Saikat Chakraborty, Shuvendu Lahiri
The ACM International Conference on the Foundations of Software Engineering (FSE) | July 2024
GitHub page https://github.com/microsoft/nl-2-postcond/
-
NL2Fix: Generating Functionally Correct Code Edits from Bug Descriptions
Sarah Fakhoury, Saikat Chakraborty, Madan Musuvathi, Shuvendu Lahiri
International Conference on Software Engineering | May 2024
Poster track
-
LLM-Based Test-Driven Interactive Code Generation: User Study and Empirical Evaluation
Sarah Fakhoury, Aaditya Naik, Georgios Sakkas, Saikat Chakraborty, Shuvendu Lahiri
IEEE Transactions on Software Engineering | April 2024, Vol 50: pp. 2254-2268
-
Ranking LLM-Generated Loop Invariants for Program Verification
Saikat Chakraborty, Shuvendu Lahiri, Sarah Fakhoury, Madan Musuvathi, Akash Lal, Aseem Rastogi, Nikhil Swamy, Rahul Sharma
Empirical Methods in Natural Language Processing | December 2023
EMNLP-Findings 2023
-
Grace: Language Models Meet Code Edits
Priyanshu Gupta, Avishree Khare, Yasharth Bajpai, Saikat Chakraborty, Sumit Gulwani, Aditya Kanade, Arjun Radhakrishna, Gustavo Soares, Ashish Tiwari
ESEC/FSE 2023: Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering | November 2023
-
AVATAR: A Parallel Corpus for Java-Python Program Translation
Wasi Uddin Ahmad, Md Golam Rahman Tushar, Saikat Chakraborty, Kai-Wei Chang
ACL 2023 | May 2023
-
NatGen: Generative pre-training by “Naturalizing” source code
Saikat Chakraborty, Toufique Ahmed, Yangruibo Ding, Premkumar Devanbu,, Baishakhi Ray
The ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) | November 2022
-
Interactive Code Generation via Test-Driven User-Intent Formalization
Shuvendu Lahiri, Sarah Fakhoury, Aaditya Naik, Georgios Sakkas, Saikat Chakraborty, Piali Choudhury, Curtis von Veh, Madan Musuvathi, Jeevana Priya Inala, Chenglong Wang, Jianfeng Gao
August 2022
arXiv | August 2022
-
Towards Learning (Dis)-Similarity of Source Code from Program Contrasts
Yangruibo Ding, Luca Buratti, Saurabh Pujar, Alessandro Morari, Baishakhi Ray, Saikat Chakraborty
60th Annual Meeting of the Association for Computational Linguistics | May 2022
-
Unified Pre-training for Program Understanding and Generation.
Saikat Chakraborty, Wasi Ahmad, Baishakhi Ray, Kai-wei Chang
October 2021
-
Deep learning based vulnerability detection: Are we there yet?
Saikat Chakraborty, Rahul Krishna, Yangruibo Ding, Baishakhi Ray
IEEE Transactions on Software Engineering | October 2021
-
On Multi-Modal Learning of Editing Source Code.
Saikat Chakraborty, Baishakhi Ray
The 36th IEEE/ACM International Conference on Automated Software Engineering (ASE'21) | May 2021
-
Retrieval Augmented Code Generation and Summarization.
M. Rizwan Parvez, Wasi Ahmad, Saikat Chakraborty, Baishakhi Ray, Kai-Wei Chang
Empirical Method in Natural Language Processing (EMNLP-findings) - 2021 | May 2021
-
-
-
Teaching an Old LLM Secure Coding: Localized Preference Optimization on Distilled Preferences
Mohammad Saqib Hasan, Saikat Chakraborty, Santu Karmaker, Niranjan Balasubramanian
ACL 2025 | May 2025
-
-
-
Can Large Language Models Transform Natural Language Intent into Formal Method Postconditions?
Madeline Endres, Sarah Fakhoury, Saikat Chakraborty, Shuvendu Lahiri
The ACM International Conference on the Foundations of Software Engineering (FSE) | July 2024
GitHub page https://github.com/microsoft/nl-2-postcond/
-
Ranking LLM-Generated Loop Invariants for Program Verification
Saikat Chakraborty, Shuvendu Lahiri, Sarah Fakhoury, Madan Musuvathi, Akash Lal, Aseem Rastogi, Nikhil Swamy, Rahul Sharma
Empirical Methods in Natural Language Processing | December 2023
EMNLP-Findings 2023
-
Grace: Language Models Meet Code Edits
Priyanshu Gupta, Avishree Khare, Yasharth Bajpai, Saikat Chakraborty, Sumit Gulwani, Aditya Kanade, Arjun Radhakrishna, Gustavo Soares, Ashish Tiwari
ESEC/FSE 2023: Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering | November 2023
-
AVATAR: A Parallel Corpus for Java-Python Program Translation
Wasi Uddin Ahmad, Md Golam Rahman Tushar, Saikat Chakraborty, Kai-Wei Chang
ACL 2023 | May 2023
-
Retrieval Augmented Code Generation and Summarization.
M. Rizwan Parvez, Wasi Ahmad, Saikat Chakraborty, Baishakhi Ray, Kai-Wei Chang
Empirical Method in Natural Language Processing (EMNLP-findings) - 2021 | May 2021
-
-
-
Teaching an Old LLM Secure Coding: Localized Preference Optimization on Distilled Preferences
Mohammad Saqib Hasan, Saikat Chakraborty, Santu Karmaker, Niranjan Balasubramanian
ACL 2025 | May 2025
-
Towards Neural Synthesis for SMT-Assisted Proof-Oriented Programming
Saikat Chakraborty, Gabriel Ebner, Siddharth Bhat, Sarah Fakhoury, Sakina Fatima, Shuvendu Lahiri, Nikhil Swamy
International Conference on Software Engineering | April 2025
-
Leveraging LLMs for Program Verification
Adharsh Kamath, Aditya Senthilnathan, Saikat Chakraborty, Pantazis Deligiannis, Shuvendu Lahiri, Akash Lal, Aseem Rastogi, Subhajit Roy, Rahul Sharma
Formal Methods in Computer-Aided Design (FMCAD) | October 2024
-
Can Large Language Models Transform Natural Language Intent into Formal Method Postconditions?
Madeline Endres, Sarah Fakhoury, Saikat Chakraborty, Shuvendu Lahiri
The ACM International Conference on the Foundations of Software Engineering (FSE) | July 2024
GitHub page https://github.com/microsoft/nl-2-postcond/
-
NL2Fix: Generating Functionally Correct Code Edits from Bug Descriptions
Sarah Fakhoury, Saikat Chakraborty, Madan Musuvathi, Shuvendu Lahiri
International Conference on Software Engineering | May 2024
Poster track
-
Ranking LLM-Generated Loop Invariants for Program Verification
Saikat Chakraborty, Shuvendu Lahiri, Sarah Fakhoury, Madan Musuvathi, Akash Lal, Aseem Rastogi, Nikhil Swamy, Rahul Sharma
Empirical Methods in Natural Language Processing | December 2023
EMNLP-Findings 2023
-
Grace: Language Models Meet Code Edits
Priyanshu Gupta, Avishree Khare, Yasharth Bajpai, Saikat Chakraborty, Sumit Gulwani, Aditya Kanade, Arjun Radhakrishna, Gustavo Soares, Ashish Tiwari
ESEC/FSE 2023: Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering | November 2023
-
AVATAR: A Parallel Corpus for Java-Python Program Translation
Wasi Uddin Ahmad, Md Golam Rahman Tushar, Saikat Chakraborty, Kai-Wei Chang
ACL 2023 | May 2023
-
NatGen: Generative pre-training by “Naturalizing” source code
Saikat Chakraborty, Toufique Ahmed, Yangruibo Ding, Premkumar Devanbu,, Baishakhi Ray
The ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) | November 2022
-
Towards Learning (Dis)-Similarity of Source Code from Program Contrasts
Yangruibo Ding, Luca Buratti, Saurabh Pujar, Alessandro Morari, Baishakhi Ray, Saikat Chakraborty
60th Annual Meeting of the Association for Computational Linguistics | May 2022
-
Unified Pre-training for Program Understanding and Generation.
Saikat Chakraborty, Wasi Ahmad, Baishakhi Ray, Kai-wei Chang
October 2021
-
On Multi-Modal Learning of Editing Source Code.
Saikat Chakraborty, Baishakhi Ray
The 36th IEEE/ACM International Conference on Automated Software Engineering (ASE'21) | May 2021
-
Retrieval Augmented Code Generation and Summarization.
M. Rizwan Parvez, Wasi Ahmad, Saikat Chakraborty, Baishakhi Ray, Kai-Wei Chang
Empirical Method in Natural Language Processing (EMNLP-findings) - 2021 | May 2021
-
-
-
LLM-Based Test-Driven Interactive Code Generation: User Study and Empirical Evaluation
Sarah Fakhoury, Aaditya Naik, Georgios Sakkas, Saikat Chakraborty, Shuvendu Lahiri
IEEE Transactions on Software Engineering | April 2024, Vol 50: pp. 2254-2268
-
Deep learning based vulnerability detection: Are we there yet?
Saikat Chakraborty, Rahul Krishna, Yangruibo Ding, Baishakhi Ray
IEEE Transactions on Software Engineering | October 2021
-
-
-
Interactive Code Generation via Test-Driven User-Intent Formalization
Shuvendu Lahiri, Sarah Fakhoury, Aaditya Naik, Georgios Sakkas, Saikat Chakraborty, Piali Choudhury, Curtis von Veh, Madan Musuvathi, Jeevana Priya Inala, Chenglong Wang, Jianfeng Gao
August 2022
arXiv | August 2022
-