ICSE was an absolute blast! Thank you for having me! Congratulations and thanks are in order for the organizing committee and Prof John Grundy ~

Ali Al-Kaswan 🍉 giving a talk based on our work on data leakage in large language models for code at the dutch National Symposium Software Engineering. Cc Arie van Deursen AISE-TUDelft SERG TU Delft #sensym #SE #ML #LLM #copilot

Great short talk by Ali Al-Kaswan 🍉 on "Copilot: An Open Source Laundromat?". LLMs can leak information. Developers who use Copilot or ChatGPT to obtain source code are responsible to check for copyright and license issues. #sensym #sensymposium

Kudos to our 2 stellar BSc teams for acing their theses on #LLMs for code last week! 🎉 A shout-out to our fantastic PhD students, jonathan katzy & Ali Al-Kaswan 🍉, for being top-notch guides in their journey👏 cc Arie van Deursen AISE-TUDelft SERG TU Delft

Why do #LLMs perform better on some programming tasks than others? In our #IEEESCAM2023 paper, we show early evidence for an inherent difference in representations of tokens between languages. arxiv.org/abs/2308.13354 Maliheh (Mali) Izadi Arie van Deursen IEEE SCAM Conference #ML #LLM #ML4SE

Heartfelt thanks to Prem பேராசிரியர் Prem Devanbu for spending an enlightening week w SERG TU Delft & delivering a thought-provoking lecture on quality of code generated by #LLMs in our course (ML4SE'23)! I am sure your expertise added a rich dimension to the learning experience of our students.

Looking forward to your NLBSE-workshop tool competition entries on code comment classification, due **Dec 9** We give a larger dataset, a new scoring formula, and a base Colab notebook to train/test your solutions. See: nlbse2024.github.io/tools/ Questions? Contact us!

A little less than 2 weeks (due Saturday, Dec 9) to submit your NLBSE-workshop tool competition paper! Looking forward to your submissions for both issue and code comment classification tasks. More info: nlbse2024.github.io/tools/

At AISE-TUDelft, we're happy to wrap up the year with 2 papers accepted at ICSE (ResearchTrack)🎉 -Language Models for Code Completion: A Practical Evaluation -Traces of Memorisation in #LLMs for Code Ali Al-Kaswan 🍉, Jonathan Katzy, Tim, Marc, Razvan & Arie van Deursen

Cool ML4SE papers presented at ICSE by our colleagues at SERG TU Delft, Ali Al-Kaswan 🍉 and Maliheh (Mali) Izadi. 1- Traces of Memorisation in Large Language Models for Code 2- Language Models for Code Completion: A Practical Evaluation #ICSE2024

Ali Al-Kaswan 🍉 presenting our recent ICSE work with Arie van Deursen on “Traces of Memorisation in Large Language Models for Code” in the final ICSE session on language models and code generation! AISE-TUDelft SERG TU Delft #llm #llm4code #ICSE2024

🗣 Call for Papers! 🗣 Are you working on #NLP methods that address #SoftwareEngineering challenges & would like to submit your work to a specialized workshop? We invite you to submit your work to the 4th edition of the NLBSE workshop co-located w/ the ICSE '25, in Canada!