Preetha Chatterjee

Asst. Prof. @drexelCCI @drexeluniv | Research on mining software repositories, empirical software engineering | Director of @Soar_Lab

[IST Journal @ISTJrnal]

📝 New article: "Psycholinguistic Analyses in Software Engineering Text: A Systematic Mapping Study" by Amirali Sajadi, Kostadin Damevski, Preetha Chatterjee

👉 Get your copy at https://t.co/mvlJlRKFh8

[Preetha Chatterjee @PreethaChatterj]

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:
https://t.co/1dfEnj9h8z

[Preetha Chatterjee @PreethaChatterj]

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: https://t.co/27puIGuT0A

@ASEconf2019

[Preetha Chatterjee @PreethaChatterj]

@aserebrenik @ASEconf2019 Thanks Alexander!

[Preetha Chatterjee @PreethaChatterj]

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: https://t.co/27puIGuT0A

@ASEconf2019

[Preetha Chatterjee @PreethaChatterj]

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.

[Preetha Chatterjee @PreethaChatterj]

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.

[Software Engineering Papers @ComputerPapers]

AI-Powered Commit Explorer (APCE). https://t.co/qJA8P0hHtl

[Drexel School of Computer and Information Sciences @DrexelSCIS]

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: https://t.co/sNaKNq15tV

[Preetha Chatterjee @PreethaChatterj]

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

[Preetha Chatterjee @PreethaChatterj]

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

[Preetha Chatterjee @PreethaChatterj]

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"
https://t.co/rnBhWskhiH

📌 NLBSE (Apr 27 | 11–12:30)
Analyzing Toxicity in OSS
https://t.co/YEbcq4mU7c

[Preetha Chatterjee @PreethaChatterj]

Sharing the open access link to our recent EMSE paper: https://t.co/UWEYyrs3aR

[Preetha Chatterjee @PreethaChatterj]

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? 🧵
https://t.co/6mn3VkixgL

[Marcel Böhme👨‍🔬 @mboehme_]

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!

👩‍🏭 https://t.co/t3SU3RUFgG (co-located w/ ICSE'25 in Ottawa)
📅 28.04. 11:00 GMT-4 (Also, live on Twitch)

[Preetha Chatterjee @PreethaChatterj]

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

[Preetha Chatterjee @PreethaChatterj]

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? 🧵
https://t.co/6mn3VkixgL

[Preetha Chatterjee @PreethaChatterj]

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.