Patrick Kahardipraja (@pkhdipraja) 's Twitter Profile
Patrick Kahardipraja

@pkhdipraja

PhD student in Explainable AI @FraunhoferHHI @AIFraunhoferHHI. Interpretability, incremental NLP, and NLU.

ID: 1802409656016375808

linkhttps://pkhdipraja.github.io/ calendar_today16-06-2024 18:35:32

21 Tweet

11 Followers

41 Following

Not Me (@davidschlangen) 's Twitter Profile Photo

I'm not @ #acl2024nlp , but if you are & like cognitively plausible modes of lang. processing, check out Patrick Kahardipraja 's poster on Tuesday. Follow-up work (with @brimadu) on his master's thesis! It's also his first large conference, so go and say hello! x.com/pkhdipraja/sta…

ACLRollingReview (@reviewacl) 's Twitter Profile Photo

🚨 We are hiring! 🚨 The ACL Rolling Review is looking for motivated individuals to join our team! If you're passionate about NLP and want to contribute to the community, apply now! Editorial Assistant - docs.google.com/document/d/1FG… Workflow Manager - docs.google.com/document/d/148…

Dilyara Bareeva (@di_lya) 's Twitter Profile Photo

✨Introducing quanda: an open-source library for benchmarking training data attribution (TDA) methods in PyTorch! Quanda offers a user-friendly interface for ⚖️ evaluating attributions and 📊 benchmarking TDA methods across diverse metrics.

✨Introducing quanda: an open-source library for benchmarking training data attribution (TDA) methods in PyTorch!

Quanda offers a user-friendly interface for ⚖️ evaluating attributions and 📊 benchmarking TDA methods across diverse metrics.
ACL 2025 (@aclmeeting) 's Twitter Profile Photo

📢#ACL2025 is inviting nominations and self-nominations to the ACL 2025 programme committee (reviewers or area chair) ➡️ forms.gle/Yu34Z13YzQ3sM8… deadline for nominations 🗓️ 16 Dec 2024. 🙏

EMNLP 2025 (@emnlpmeeting) 's Twitter Profile Photo

ACLRollingReview and the EMNLP PCs are seeking input on the current state of reviewing for *CL conferences. We would love to get your feedback on the current process and how it could be improved. To contribute your ideas and opinions, please follow this link! forms.office.com/r/P68uvwXYqf

ACL Anthology (@aclanthology) 's Twitter Profile Photo

Here's a periodic reminder that you can save your readers from situations like this by using using our updated BST file, which truncates long author lists to just the first twenty github.com/acl-org/acl-st…

Here's a periodic reminder that you can save your readers from situations like this by using using our updated BST file, which truncates long author lists to just the first twenty github.com/acl-org/acl-st…
Sebastian Lapuschkin (@slapuschkin) 's Twitter Profile Photo

Have had enough of the fake "sources" "cited" by ChatGPT? We have the solution in the form of low-cost causal citations for LLMs: arxiv.org/abs/2505.15807 Thanks to my amazing co-authors Patrick Kahardipraja , Reduan Achtibat, Thomas Wiegand and Wojciech Samek from Fraunhofer HHI

Have had enough of the fake "sources" "cited" by ChatGPT? We have the solution in the form of low-cost causal citations for LLMs: arxiv.org/abs/2505.15807

Thanks to my amazing co-authors <a href="/pkhdipraja/">Patrick Kahardipraja</a>
 , Reduan Achtibat, <a href="/wiegand_t/">Thomas Wiegand</a>
 and <a href="/WojciechSamek/">Wojciech Samek</a>
 from <a href="/FraunhoferHHI/">Fraunhofer HHI</a>
Laura Kopf (@lkopf_ml) 's Twitter Profile Photo

🔍 When do neurons encode multiple concepts? We introduce PRISM, a framework for extracting multi-concept feature descriptions to better understand polysemanticity. 📄 Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework arxiv.org/abs/2506.15538 🧵

🔍 When do neurons encode multiple concepts?

We introduce PRISM, a framework for extracting multi-concept feature descriptions to better understand polysemanticity.

📄 Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework
arxiv.org/abs/2506.15538
🧵
ACLRollingReview (@reviewacl) 's Twitter Profile Photo

🚨 Calling emergency reviewers for ARR May 2025! If you are available to help, please sign up here: 🔗 forms.office.com/r/0KsvNFKbm5