16 citations · 82 across the 19 of their papers we have counts for
19 papers
Distilling Reasoning Traces into Advisory Prompts for Software Engineering Tasks
Faizan Faisal, Prem Devanbu, Toufique Ahmed
Language models are widely used for generating and otherwise processing code (e.g., identifying code hallucinations, possible inputs, or predicting outputs); however, LLMs can make…
Calibration of Large Language Models on Code Summarization
Yuvraj Virk, Premkumar Devanbu, Toufique Ahmed
A brief, fluent, and relevant summary can be helpful during program comprehension; however, such a summary does require significant human effort to produce. Often, good summaries a…
Studying LLM Performance on Closed- and Open-source Data
Toufique Ahmed, Christian Bird, Premkumar Devanbu +1
Large Language models (LLMs) are finding wide use in software engineering practice. These models are extremely data-hungry, and are largely trained on open-source (OSS) code distri…
Towards Understanding What Code Language Models Learned
Toufique Ahmed, Dian Yu, Chengxuan Huang +3
Pre-trained language models are effective in a variety of natural language tasks, but it has been argued their capabilities fall short of fully learning meaning or understanding la…
Better patching using LLM prompting, via Self-Consistency
Toufique Ahmed, Premkumar Devanbu
Large Language models (LLMs) can be induced to solve non-trivial problems with "few-shot" prompts including illustrative problem-solution examples. Now if the few-shots also includ…
A Survey of Trojans in Neural Models of Source Code: Taxonomy and Techniques
Aftab Hussain, Md Rafiqul Islam Rabin, Toufique Ahmed +4
In this work, we study literature in Explainable AI and Safe AI to understand poisoning of neural models of code. In order to do so, we first establish a novel taxonomy for Trojan…
Automatic Semantic Augmentation of Language Model Prompts (for Code Summarization)
Toufique Ahmed, Kunal Suresh Pai, Premkumar Devanbu +1
Large Language Models (LLM) are a new class of computation engines, "programmed" via prompt engineering. We are still learning how to best "program" these LLMs to help developers.…
Large Language Models and Simple, Stupid Bugs
Kevin Jesse, Toufique Ahmed, Premkumar T. Devanbu +1
With the advent of powerful neural language models, AI-based systems to assist developers in coding tasks are becoming widely available; Copilot is one such system. Copilot uses Co…
Recommending Root-Cause and Mitigation Steps for Cloud Incidents using Large Language Models
Toufique Ahmed, Supriyo Ghosh, Chetan Bansal +3
Incident management for cloud services is a complex process involving several steps and has a huge impact on both service health and developer productivity. On-call engineers requi…
Extending Source Code Pre-Trained Language Models to Summarise Decompiled Binaries
Ali Al-Kaswan, Toufique Ahmed, Maliheh Izadi +3
Reverse engineering binaries is required to understand and analyse programs for which the source code is unavailable. Decompilers can transform the largely unreadable binaries into…
NatGen: Generative pre-training by "Naturalizing" source code
Saikat Chakraborty, Toufique Ahmed, Yangruibo Ding +2
Pre-trained Generative Language models (e.g. PLBART, CodeT5, SPT-Code) for source code yielded strong results on several tasks in the past few years, including code generation and…
Few-shot training LLMs for project-specific code-summarization
Toufique Ahmed, Premkumar Devanbu
Very large language models (LLMs), such as GPT-3 and Codex have achieved state-of-the-art performance on several natural-language tasks, and show great promise also for code. A par…
Learning code summarization from a small and local dataset
Toufique Ahmed, Premkumar Devanbu
Foundation models (e.g., CodeBERT, GraphCodeBERT, CodeT5) work well for many software engineering tasks. These models are pre-trained (using self-supervision) with billions of code…
Recent formation and likely cometary activity of near-Earth asteroid pair 2019 PR2 -- 2019 QR6
Petr Fatka, Nicholas A. Moskovitz, Petr Pravec +13
Asteroid pairs are genetically related asteroids that recently separated (few million years), but still reside on similar heliocentric orbits. A few hundred of these systems hav…
SYNFIX: Automatically Fixing Syntax Errors using Compiler Diagnostics
Toufique Ahmed, Noah Rose Ledesma, Premkumar Devanbu
Beginning programmers struggle with the complex grammar of modern programming languages like Java, and make lot of syntax errors. The diagnostic syntax error messages from compiler…
Learning to Find Usages of Library Functions in Optimized Binaries
Toufique Ahmed, Premkumar Devanbu, Anand Ashok Sawant
Much software, whether beneficent or malevolent, is distributed only as binaries, sans source code. Absent source code, understanding binaries' behavior can be quite challenging, e…
Review4Repair: Code Review Aided Automatic Program Repairing
Faria Huq, Masum Hasan, Mahim Anzum Haque Pantho +3
Context: Learning-based automatic program repair techniques are showing promise to provide quality fix suggestions for detected bugs in the source code of the software. These tools…
Early Prediction for Merged vs Abandoned Code Changes in Modern Code Reviews
Md. Khairul Islam, Toufique Ahmed, Rifat Shahriyar +2
The modern code review process is an integral part of the current software development practice. Considerable effort is given here to inspect code changes, find defects, suggest an…
Learning Lenient Parsing & Typing via Indirect Supervision
Toufique Ahmed, Premkumar Devanbu, Vincent Hellendoorn
Both professional coders and teachers frequently deal with imperfect (fragmentary, incomplete, ill-formed) code. Such fragments are common in STACKOVERFLOW; students also frequentl…