Toufique Ahmed

57 papers A* 8A 4B 3C 1Journal 35Unranked 5

Year	Rank	Type	Title / Venue / Authors
2025	A*	`conf`	Calibration and Correctness of Language Models for Code. ICSE Claudio Spiess, David Gros, Kunal Suresh Pai, Michael Pradel, Md. Rafiqul Islam Rabin, Amin Alipour, Susmit Jha, Prem Devanbu, Toufique Ahmed
2025	J	`jnl`	Calibration of Large Language Models on Code Summarization. Proc. ACM Softw. Eng. Yuvraj Virk, Premkumar T. Devanbu, Toufique Ahmed
2025	A	`conf`	Can LLMs Replace Manual Annotation of Software Engineering Artifacts? MSR Toufique Ahmed, Premkumar T. Devanbu, Christoph Treude, Michael Pradel
2025	A	`conf`	CoDocBench: A Dataset for Code-Documentation Alignment in Software Maintenance. MSR Kunal Suresh Pai, Premkumar T. Devanbu, Toufique Ahmed
2025	J	`jnl`	CoDocBench: A Dataset for Code-Documentation Alignment in Software Maintenance. CoRR Kunal Suresh Pai, Premkumar T. Devanbu, Toufique Ahmed
2025	J	`jnl`	Execution-Feedback Driven Test Generation from SWE Issues. CoRR Toufique Ahmed, Jatin Ganhotra, Avraham Shinnar, Martin Hirzel
2025	B	`conf`	Finding Trojan Triggers in Code LLMs: An Occlusion-Based Human-in-the-Loop Approach. CAIN Aftab Hussain, Md. Rafiqul Islam Rabin, Toufique Ahmed, Mohammad Amin Alipour, Bowen Xu, Stephen Huang
2025	J	`jnl`	Is the Cure Still Worse Than the Disease? Test Overfitting by LLMs in Automated Program Repair. CoRR Toufique Ahmed, Jatin Ganhotra, Avraham Shinnar, Martin Hirzel
2025	A*	`conf`	Otter: Generating Tests from Issues to Validate SWE Patches. ICML Toufique Ahmed, Jatin Ganhotra, Rangeet Pan, Avraham Shinnar, Saurabh Sinha, Martin Hirzel
2025	J	`jnl`	Otter: Generating Tests from Issues to Validate SWE Patches. CoRR Toufique Ahmed, Jatin Ganhotra, Rangeet Pan, Avraham Shinnar, Saurabh Sinha, Martin Hirzel
2025	J	`jnl`	When Old Meets New: Evaluating the Impact of Regression Tests on SWE Issue Resolution. CoRR Yang Chen, Toufique Ahmed, Reyhaneh Jabbarvand, Martin Hirzel
2024	A*	`conf`	Automatic Semantic Augmentation of Language Model Prompts (for Code Summarization). ICSE Toufique Ahmed, Kunal Suresh Pai, Premkumar T. Devanbu, Earl T. Barr
2024	J	`jnl`	Calibration and Correctness of Language Models for Code. CoRR Claudio Spiess, David Gros, Kunal Suresh Pai, Michael Pradel, Md. Rafiqul Islam Rabin, Amin Alipour, Susmit Jha, Prem Devanbu, Toufique Ahmed
2024	J	`jnl`	Can LLMs Replace Manual Annotation of Software Engineering Artifacts? CoRR Toufique Ahmed, Premkumar T. Devanbu, Christoph Treude, Michael Pradel
2024	J	`jnl`	Enhancing Trust in LLM-Generated Code Summaries with Calibrated Confidence Scores. CoRR Yuvraj Virk, Premkumar T. Devanbu, Toufique Ahmed
2024	J	`jnl`	Prompting and Fine-tuning Large Language Models for Automated Code Review Comment Generation. CoRR Md. Asif Haider, Ayesha Binte Mostofa, Sk Md Mosaddek Hossain, Anindya Iqbal, Toufique Ahmed
2024	J	`jnl`	Studying LLM Performance on Closed- and Open-source Data. CoRR Toufique Ahmed, Christian Bird, Premkumar T. Devanbu, Saikat Chakraborty
2024	J	`jnl`	TDD-Bench Verified: Can LLMs Generate Tests for Issues Before They Get Resolved? CoRR Toufique Ahmed, Martin Hirzel, Rangeet Pan, Avraham Shinnar, Saurabh Sinha
2024	J	`jnl`	Trojans in Large Language Models of Code: A Critical Review through a Trigger-Based Taxonomy. CoRR Aftab Hussain, Md. Rafiqul Islam Rabin, Toufique Ahmed, Bowen Xu, Premkumar T. Devanbu, Mohammad Amin Alipour
2023	J	`jnl`	A Survey of Trojans in Neural Models of Source Code: Taxonomy and Techniques. CoRR Aftab Hussain, Md. Rafiqul Islam Rabin, Toufique Ahmed, Bowen Xu, Prem Devanbu, Mohammad Amin Alipour
2023	A*	`conf`	Better Patching Using LLM Prompting, via Self-Consistency. ASE Toufique Ahmed, Premkumar T. Devanbu
2023	A	`conf`	Extending Source Code Pre-Trained Language Models to Summarise Decompiled Binarie. SANER Ali Al-Kaswan, Toufique Ahmed, Maliheh Izadi, Anand Ashok Sawant, Premkumar T. Devanbu, Arie van Deursen
2023	J	`jnl`	Extending Source Code Pre-Trained Language Models to Summarise Decompiled Binaries. CoRR Ali Al-Kaswan, Toufique Ahmed, Maliheh Izadi, Anand Ashok Sawant, Premkumar T. Devanbu, Arie van Deursen
2023	J	`jnl`	Improving Few-Shot Prompts with Relevant Static Analysis Products. CoRR Toufique Ahmed, Kunal Suresh Pai, Premkumar T. Devanbu, Earl T. Barr
2023	A	`conf`	Large Language Models and Simple, Stupid Bugs. MSR Kevin Jesse, Toufique Ahmed, Premkumar T. Devanbu, Emily Morgan
2023	J	`jnl`	Large Language Models and Simple, Stupid Bugs. CoRR Kevin Jesse, Toufique Ahmed, Premkumar T. Devanbu, Emily Morgan
2023	—	`—`	Learning program embedding from unlabeled source code Toufique Ahmed
2023	J	`jnl`	Majority Rule: better patching via Self-Consistency. CoRR Toufique Ahmed, Premkumar T. Devanbu
2023	J	`jnl`	Occlusion-based Detection of Trojan-triggering Inputs in Large Language Models of Code. CoRR Aftab Hussain, Md. Rafiqul Islam Rabin, Toufique Ahmed, Mohammad Amin Alipour, Bowen Xu
2023	A*	`conf`	Recommending Root-Cause and Mitigation Steps for Cloud Incidents using Large Language Models. ICSE Toufique Ahmed, Supriyo Ghosh, Chetan Bansal, Thomas Zimmermann, Xuchao Zhang, Saravan Rajmohan
2023	J	`jnl`	Recommending Root-Cause and Mitigation Steps for Cloud Incidents using Large Language Models. CoRR Toufique Ahmed, Supriyo Ghosh, Chetan Bansal, Thomas Zimmermann, Xuchao Zhang, Saravan Rajmohan
2023	J	`jnl`	SynShine: Improved Fixing of Syntax Errors. IEEE Trans. Software Eng. Toufique Ahmed, Noah Rose Ledesma, Premkumar T. Devanbu
2023	J	`jnl`	Towards Understanding What Code Language Models Learned. CoRR Toufique Ahmed, Dian Yu, Chengxuan Huang, Cathy Wang, Prem Devanbu, Kenji Sagae
2022	J	`jnl`	Early prediction for merged vs abandoned code changes in modern code reviews. Inf. Softw. Technol. Md. Khairul Islam, Toufique Ahmed, Rifat Shahriyar, Anindya Iqbal, Gias Uddin
2022	A*	`conf`	Few-shot training LLMs for project-specific code-summarization. ASE Toufique Ahmed, Premkumar T. Devanbu
2022	J	`jnl`	Few-shot training LLMs for project-specific code-summarization. CoRR Toufique Ahmed, Premkumar T. Devanbu
2022	J	`jnl`	Learning code summarization from a small and local dataset. CoRR Toufique Ahmed, Premkumar T. Devanbu
2022	J	`jnl`	Learning to Find Usages of Library Functions in Optimized Binaries. IEEE Trans. Software Eng. Toufique Ahmed, Premkumar T. Devanbu, Anand Ashok Sawant
2022	A*	`conf`	Multilingual training for Software Engineering. ICSE Toufique Ahmed, Premkumar T. Devanbu
2022	J	`jnl`	NatGen: Generative pre-training by "Naturalizing" source code. CoRR Saikat Chakraborty, Toufique Ahmed, Yangruibo Ding, Premkumar T. Devanbu, Baishakhi Ray
2022	—	`conf`	NatGen: generative pre-training by "naturalizing" source code. ESEC/SIGSOFT FSE Saikat Chakraborty, Toufique Ahmed, Yangruibo Ding, Premkumar T. Devanbu, Baishakhi Ray
2022	J	`jnl`	Review4Repair: Code review aided automatic program repairing. Inf. Softw. Technol. Faria Huq, Masum Hasan, Md. Mahim Anjum Haque, Sazan Mahbub, Anindya Iqbal, Toufique Ahmed
2021	J	`jnl`	Finding Inlined Functions in Optimized Binaries. CoRR Toufique Ahmed, Premkumar T. Devanbu, Anand Ashok Sawant
2021	J	`jnl`	Learning lenient parsing & typing via indirect supervision. Empir. Softw. Eng. Toufique Ahmed, Premkumar T. Devanbu, Vincent J. Hellendoorn
2021	—	`conf`	Learning type annotation: is big data enough? ESEC/SIGSOFT FSE Kevin Jesse, Premkumar T. Devanbu, Toufique Ahmed
2021	J	`jnl`	Multilingual training for Software Engineering. CoRR Toufique Ahmed, Premkumar T. Devanbu
2021	J	`jnl`	SYNFIX: Automatically Fixing Syntax Errors using Compiler Diagnostics. CoRR Toufique Ahmed, Noah Rose Ledesma, Premkumar T. Devanbu
2020	J	`jnl`	Review4Repair: Code Review Aided Automatic Program Repairing. CoRR Faria Huq, Masum Hasan, Mahim Anzum Haque Pantho, Sazan Mahbub, Anindya Iqbal, Toufique Ahmed
2019	J	`jnl`	Accepted or Abandoned? Predicting the Fate of Code Changes. CoRR Md. Khairul Islam, Toufique Ahmed, Fahim Ahmed, Anindya Iqbal
2019	J	`jnl`	Learning Lenient Parsing & Typing via Indirect Supervision. CoRR Toufique Ahmed, Vincent J. Hellendoorn, Premkumar T. Devanbu
2018	C	`conf`	SOQDE: A Supervised Learning Based Question Difficulty Estimation Model for Stack Overflow. APSEC Sk Adnan Hassan, Dipto Das, Anindya Iqbal, Amiangshu Bosu, Rifat Shahriyar, Toufique Ahmed
2017	A*	`conf`	SentiCR: a customized sentiment analysis tool for code review interactions. ASE Toufique Ahmed, Amiangshu Bosu, Anindya Iqbal, Shahram Rahimi
2017	B	`conf`	Weighted Optimal Sequenced Group Trip Planning Queries. MDM Sukarna Barua, Roksana Jahan, Toufique Ahmed
2016	—	`conf`	Efficient Routing in a Sensor Network Using Collaborative Ants. ICSI (2) Md. Shaifur Rahman, Mahmuda Naznin, Toufique Ahmed
2016	B	`conf`	Energy efficient local search based target localization in an UWSN. WiMob Nazia Majadi, Mahmuda Naznin, Toufique Ahmed
2016	—	`conf`	Poster: ETRACK: Energy Efficient Tracking a Mobile Object Using Under Water Sensors. MobiSys (Companion Volume) Nazia Majadi, Mahmuda Naznin, Toufique Ahmed
2016	—	`conf`	Poster: Measuring Developers' Sentiments in the Android Open Source Project. MobiSys (Companion Volume) Toufique Ahmed