Preetha Chatterjee

📝 New article: "Psycholinguistic Analyses in Software Engineering Text: A Systematic Mapping Study" by Amirali Sajadi, Kostadin Damevski, Preetha Chatterjee 👉 Get your copy at doi.org/10.1016/j.infs…

We are disappointed to miss he 40th IEEE/ACM International Conference on Automated Software Engineering (ASE 2025) in person this year in Seoul, but our presentation is now available online. If you are interested in the work, here’s the recording: youtube.com/watch?v=qvHNUf…

@aserebrenik @ASEconf2019 Thanks Alexander!

@PreethaChatterj @ASEconf2019 Congratulations

LLMs can repair code, but often miss the broader context developers use every day. We propose a 3-layer knowledge injection framework that incrementally feeds LLMs with bug, repository, and project knowledge. Preprint of our ASE '25 paper: arxiv.org/pdf/2506.24015 @ASEconf2019

Error analysis reveals that unresolved bugs are not randomly distributed; they cluster around specific bug types and higher complexity profiles. In particular, Program Anomaly, Network, and GUI bugs remain the most challenging for both models.

Evaluated on 314 real-world Python bugs, we observed consistent gains in both #fixed and Pass@k scores for Llama 3.3 and GPT-4o-mini, demonstrating a 23% improvement over prior work.

AI-Powered Commit Explorer (APCE). arxiv.org/abs/2507.16063

Congrats to all the exceptional students, faculty and professional staff who were recognized for their hard work at our annual College Awards Cermony. 👏 View the full album: ow.ly/nJIn50W5Kb7

@Lin0Tan @yiwu5cs @PurdueCS @anikbera @ieee_ras_icra Congratulations!

Our SELP paper is an #ICRA25 Best Paper Award Finalist, among a selected few from 4,153 submissions! 🏆 Proud of my PhD student @yiwu5cs & the team! cs.purdue.edu/homes/lintan/p… #robotics #LLM #ConstrainedDecoding #Agent #LLMPlanner @PurdueCS @anikbera @ieee_ras_icra

@mboehme_ Just wanted to say, I loved reading this paper!

If you want to learn more how to detect spurious correlations, check out Niklas' other work on "Uncovering the Limits of Machine Learning for Automatic Vulnerability Detection": mpi-softsec.github.io/papers/USENIX2…

Our paper "Top Score on the Wrong Exam" paper will be presented at #ISSTA25 🐣 in Trondheim! 📝mpi-softsec.github.io/papers/ISSTA25… 🧑‍💻github.com/niklasrisse/To… // @niklas2484 @fuzzjing.

Headed to @ICSEconf? Don’t miss two exciting talks from our lab! 📌 MSR (Apr 29 | 14–15:30) "Towards Detecting Prompt Knowledge Gaps for Improved LLM-guided Issue Resolution" arxiv.org/abs/2501.11709 📌 NLBSE (Apr 27 | 11–12:30) Analyzing Toxicity in OSS arxiv.org/abs/2412.13133

Sharing the open access link to our recent EMSE paper: link.springer.com/article/10.100…

Benchmarks are our measures of progress. Or are they? Looking forward to exploring promises & perils of measuring tool capabilities @SBFTworkshop'25! Thanks for the invite! 👩‍🏭 sbft25.github.io (co-located w/ ICSE'25 in Ottawa) 📅 28.04. 11:00 GMT-4 (Also, live on Twitch)

💡 If you are building, evaluating, or relying on LLMs for software development, please ask yourself: Did it warn you about the hidden security risk?

As a preliminary solution to this problem, we built a CLI tool prototype that integrates static analysis with LLM prompting, aiming to make AI code suggestions more secure by design.

LLMs are great at generating code, but are they silently spreading vulnerabilities? TLDR: Yes. In our latest EMSE paper, we look into: when developers unknowingly share vulnerable code with LLMs, do these models proactively raise security red flags? 🧵 arxiv.org/abs/2502.14202