Shubhra K. Karmaker ("Santu") (@karmake2) profile picture

Assistant Professor of Computer Science at Auburn University. Communication Chair of ACL Rolling Reviews (ARR)

Auburn, AL
Joined October 2014
Photo by Shubhra K. Karmaker ("Santu") (@karmake2)Photo by Shubhra K. Karmaker ("Santu") (@karmake2)Photo by Shubhra K. Karmaker ("Santu") (@karmake2)Photo by Shubhra K. Karmaker ("Santu") (@karmake2)Photo by Shubhra K. Karmaker ("Santu") (@karmake2)Photo by Shubhra K. Karmaker ("Santu") (@karmake2)Photo by Shubhra K. Karmaker ("Santu") (@karmake2)Photo by Shubhra K. Karmaker ("Santu") (@karmake2)Photo by Shubhra K. Karmaker ("Santu") (@karmake2)Photo by Shubhra K. Karmaker ("Santu") (@karmake2)
Shubhra K. Karmaker ("Santu") retweeted
Thanks for the kind invitation to the inaugural UCF AI Institute's Distinguished Lecture, Amrit+Mubarak et al. -- looking forward to meeting the awesome faculty+students! 🙂 Will discuss 3 important AI challenges: Trustworthy Collaboration, World Discovery, Long-Horizon Memory Planning (across diverse domains & modalities, and real-world applications such as early medical diagnosis and classroom education engagement). Feel free to join/stop by (virtual option also available)! 👇👇
🚀UCF IAI Distinguished Speaker Series We’re thrilled to welcome Prof. @mohitban47 @UNC as our inaugural speaker! 🎙️ AI Challenges: Trustworthy Collaboration, World Discovery & Long-Horizon Memory 📅 Sept. 16, 2026 ⏰ 11 AM 📍 SPRK 101 @UCF + Zoom #AI #AgenticAI #TrustworthyAI
1
19
44
3,782
Shubhra K. Karmaker ("Santu") retweeted
Theory of Mind 🧠 is a core part of social intelligence. But most LLM benchmarks only test the final answer, not whether the model actually built the right mental model. We introduce OmniToM, a benchmark for multi-actor mental state reasoning. adam-12-0.github.io/omnitom-…
3
1
178
I will be participating as an AI Expert Panelist at the following webinar tomorrow. The @UCF and the U.S. Army DEVCOM Army Research Laboratory will jointly host the webinar. Please RSVP in case you are interested in the topic. @UCFCECS @usarmy_devcom #AI #HumanAICollaboration
1
4
152
Do you like csrankings.org? If yes, how about a similar ranking platform for LLMs? Check out our latest work on the LLM Ranking based on their psychological biases. bridgeai-lab.github.io/LLM-R… @ReviewAcl #LLM #NLP @emnlpmeeting @aclmeeting
Do large language models think like humans? Are they also prone to human-like cognitive biases? We just launched a new ranking system of LLMs based on their ability to resist cognitive biases with a large-scale study of 2.8M+ responses across 8 well-known biases.
1
4
220
Shubhra K. Karmaker ("Santu") retweeted
We are glad to share our latest NAACL 2025 paper, "LLMs as Meta-Reviewers' Assistants: A Case Study". Read the full paper at: arxiv.org/pdf/2402.15589v2 (1/2)
1
1
1
116
Shubhra K. Karmaker ("Santu") retweeted
🚨 We are hiring! 🚨 We are looking for two new members to join our communication team and help support the ARR initiative. If you’re interested, please fill out the following form: forms.gle/e2F6nASMaUD7juDi8
4
1
9
7,814
Our latest paper introduces the pre-evaluation of sentence encoders, similar to pertaining language models!! Pre-evaluation performs evaluation without a specific downstream task, that's why we call it taskless evaluation as well. @ReviewAcl
Replying to @BridgeAI_Lab
A big thanks to @eduardo_nlp for his collaboration and significant contributions to this work. Our paper introduces ALIGN-SIM, a novel task-free framework for evaluating and interpreting sentence embeddings based on various semantic similarity alignment criteria. 2/2
6
256
Shubhra K. Karmaker ("Santu") retweeted
🚨 Attention authors! The CFP has been updated for the December cycle. Be sure to double-check the latest requirements: aclrollingreview.org/cfp 📝 We have also updated the author checklist to help you avoid common issues: aclrollingreview.org/authorc…
5
21
5,370
Attending EMNLP 2024, Miami.
2
15
460
The Bangla LLaMA (BongLLaMA) is here.
We are excited to collaborate with BangaLLM to introduce BongLLaMA, the first ever and, of course, the state-of-the-art Bangla LLM (Based on Meta LLaMA). Try it out. @ReviewAcl #EMNLP #ACL #NLP #BanglaAI @UCFComputerSci arxiv.org/abs/2410.21200
6
218
Please try SEM-F1 and let us know if you see a better correlation with human judgments too!
We are happy to release our text summarization metric, Sem-F1, for public use. huggingface.co/spaces/Bridge… Sem-F1 achieves a 25% higher correlation with human judgments than Bertscore on the Overlap Summarization task. Benchmarking paper coming soon. @ReviewAcl
2
261
Here goes the Ph.D. # 4 from my lab, Congratulations Naman Bansal @ImBNaman ! Naman joined @Google as a software engineer last month. @AuburnEngineers
1
8
242
I am thrilled as well.
We are thrilled that @karmake2 has joined #UCFCS for Fall 2024! He is one of the 17 new faculty members at @ucfcecs this semester. Join us in welcoming him and learn more about his research and expertise: bit.ly/3TyXdPM
2
18
1,112
I am starting a new chapter of my career by joining UCF Artificial Intelligence Initiative (Aii) – AII as an assistant professor. @UCFComputerSci @UCFCECS
6
4
45
2,484
Shubhra K. Karmaker ("Santu") retweeted
Today 11 AM, I will be presenting our paper on state reconciliation for @ansible (infrastructure-as-code) at Acerola in the @FSEconf . In collaboration with @karmake2 and his students. This work benefitted from discussions at a @dagstuhl seminar that I attended in 2023.
Excited to present and discuss five of our papers during the week of @FSEconf . Come join these presentations and discussions. Presented papers are related to #DevOps , infrastructure-as-code, and scientific software. I am also open for collabs!
1
1
10
375