132 citations · 469 across the 30 of their papers we have counts for
33 papers
LLM Post-Training as Brownfield Maintenance: An Industrial Perspective on Dataware Engineering
Gopi Krishnan Rajbahadur, Amir M. Ebrahimi, Boyuan Chen +1
Industrial post-training is a brownfield regime. Teams inherit a deployed checkpoint and must land targeted improvements under fixed compute and mixture budgets without regressing…
To Add Is Machine, To Delete Is Human: Measuring and Mitigating Deletion Avoidance in LLM Code Editing
Amir M. Ebrahimi, Mohammed Mehedi Hasan, Aaditya Bhatia +2
Large language models increasingly write and repair production code, yet evidence is mounting that their test-passing patches leave codebases harder to maintain. We identify one co…
Don't Trust the Label: License Laundering in AI Supply Chains
James Jewitt, Hao Li, Gopi Krishnan Rajbahadur +2
AI artifacts move through a multi-platform supply chain, spanning datasets and models on Hugging Face and applications on GitHub. While each artifact carries a license whose obliga…
From Failure to Alignment: A Requirements Engineering Framework for Machine Learning Systems
Amel Bennaceur, Gopi Krishnan Rajbahadur, Prince Mercy +2
Organisations designing, developing, and deploying machine learning systems (MLS) need to be able to check that these systems are trustworthy, and communicate this clearly to their…
Edit, But Verify: An Empirical Audit of Instructed Code-Editing Benchmarks
Amir M. Ebrahimi, Gopi Krishnan Rajbahadur
Instructed code editing, where an LLM modifies existing code based on a natural language instruction, accounts for roughly 19% of real-world coding assistant interactions. Yet very…
Permissive-Washing in the Open AI Supply Chain: A Large-Scale Audit of License Integrity
James Jewitt, Gopi Krishnan Rajbahadur, Hao Li +2
Permissive licenses like MIT, Apache-2.0, and BSD-3-Clause dominate open-source AI, signaling that artifacts like models, datasets, and code can be freely used, modified, and redis…
Model Context Protocol (MCP) Tool Descriptions Are Smelly! Towards Improving AI Agent Efficiency with Augmented MCP Tool Descriptions
Mohammed Mehedi Hasan, Hao Li, Gopi Krishnan Rajbahadur +2
The Model Context Protocol (MCP) introduces a standard specification that defines how Foundation Model (FM)-based agents should interact with external systems by invoking tools. Ho…
Building an Open AIBOM Standard in the Wild
Gopi Krishnan Rajbahadur, Keheliya Gallaba, Elyas Rashno +4
Modern software engineering increasingly relies on open, community-driven standards, yet how such standards are created in fast-evolving domains like AI-powered systems remains und…
RepoForge: Training a SOTA Fast-thinking SWE Agent with an End-to-End Data Curation Pipeline Synergizing SFT and RL at Scale
Zhilong Chen, Chengzong Zhao, Boyuan Chen +9
Training software engineering (SWE) LLMs is bottlenecked by expensive infrastructure, inefficient evaluation pipelines, scarce training data, and costly quality control. We present…
An Empirical Study of Testing Practices in Open Source AI Agent Frameworks and Agentic Applications
Mohammed Mehedi Hasan, Hao Li, Emad Fallahzadeh +3
Foundation model (FM)-based AI agents are rapidly gaining adoption across diverse domains, but their inherent non-determinism and non-reproducibility pose testing and quality assur…
From Hugging Face to GitHub: Tracing License Drift in the Open-Source AI Ecosystem
James Jewitt, Hao Li, Bram Adams +2
Hidden license conflicts in the open-source AI ecosystem pose serious legal and ethical risks, exposing organizations to potential litigation and users to undisclosed risk. However…
SPICE: An Automated SWE-Bench Labeling Pipeline for Issue Clarity, Test Coverage, and Effort Estimation
Gustavo A. Oliva, Gopi Krishnan Rajbahadur, Aaditya Bhatia +7
High-quality labeled datasets are crucial for training and evaluating foundation models in software engineering, but creating them is often prohibitively expensive and labor-intens…
The Hitchhikers Guide to Production-ready Trustworthy Foundation Model powered Software (FMware)
Kirill Vasilevski, Benjamin Rombaut, Gopi Krishnan Rajbahadur +10
Foundation Models (FMs) such as Large Language Models (LLMs) are reshaping the software industry by enabling FMware, systems that integrate these FMs as core components. In this KD…
Model Context Protocol (MCP) at First Glance: Studying the Security and Maintainability of MCP Servers
Mohammed Mehedi Hasan, Hao Li, Emad Fallahzadeh +3
Although Foundation Models (FMs), such as GPT-4, are increasingly used in domains like finance and software engineering, reliance on textual interfaces limits these models' real-wo…
LicenseGPT: A Fine-tuned Foundation Model for Publicly Available Dataset License Compliance
Jingwen Tan, Gopi Krishnan Rajbahadur, Zi Li +5
Dataset license compliance is a critical yet complex aspect of developing commercial AI products, particularly with the increasing use of publicly available datasets. Ambiguities i…
PromptExp: Multi-granularity Prompt Explanation of Large Language Models
Ximing Dong, Shaowei Wang, Dayi Lin +4
Large Language Models excel in tasks like natural language understanding and text generation. Prompt engineering plays a critical role in leveraging LLM effectively. However, LLMs…
From Cool Demos to Production-Ready FMware: Core Challenges and a Technology Roadmap
Gopi Krishnan Rajbahadur, Gustavo A. Oliva, Dayi Lin +2
The rapid expansion of foundation models (FMs), such as large language models (LLMs), has given rise to FMware, software systems that integrate FM(s) as core components. While buil…
Data Quality Antipatterns for Software Analytics
Aaditya Bhatia, Dayi Lin, Gopi Krishnan Rajbahadur +2
Background: Data quality is vital in software analytics, particularly for machine learning (ML) applications like software defect prediction (SDP). Despite the widespread use of ML…
Studying the Impact of TensorFlow and PyTorch Bindings on Machine Learning Software Quality
Hao Li, Gopi Krishnan Rajbahadur, Cor-Paul Bezemer
Bindings for machine learning frameworks (such as TensorFlow and PyTorch) allow developers to integrate a framework's functionality using a programming language different from the…
SimClone: Detecting Tabular Data Clones using Value Similarity
Xu Yang, Gopi Krishnan Rajbahadur, Dayi Lin +3
Data clones are defined as multiple copies of the same data among datasets. Presence of data clones between datasets can cause issues such as difficulties in managing data assets a…
Rethinking Software Engineering in the Foundation Model Era: A Curated Catalogue of Challenges in the Development of Trustworthy FMware
Ahmed E. Hassan, Dayi Lin, Gopi Krishnan Rajbahadur +9
Foundation models (FMs), such as Large Language Models (LLMs), have revolutionized software development by enabling new use cases and business models. We refer to software built us…
Keeping Deep Learning Models in Check: A History-Based Approach to Mitigate Overfitting
Hao Li, Gopi Krishnan Rajbahadur, Dayi Lin +3
In software engineering, deep learning models are increasingly deployed for critical tasks such as bug detection and code review. However, overfitting remains a challenge that affe…
Is my transaction done yet? An empirical study of transaction processing times in the Ethereum Blockchain Platform
Michael Pacheco, Gustavo A. Oliva, Gopi Krishnan Rajbahadur +1
Ethereum is one of the most popular platforms for the development of blockchain-powered applications. These applications are known as Dapps. When engineering Dapps, developers need…
What makes Ethereum blockchain transactions be processed fast or slow? An empirical study
Michael Pacheco, Gustavo A. Oliva, Gopi Krishnan Rajbahadur +1
The Ethereum platform allows developers to implement and deploy applications called Dapps onto the blockchain for public use through the use of smart contracts. To execute code wit…