Patrick Kahardipraja
@pkhdipraja.bsky.social
PhD student @ Fraunhofer HHI. Interpretability, incremental NLP, and NLU. https://pkhdipraja.github.io/
Now accepted at #NeurIPS2025 :)
ICL allows LLMs to adapt to new tasks and at the same time enables them to access external knowledge through RAG. How does the latter work?
TL;DR we find that certain attention heads perform various, distinct operations on the input prompt for QA!
arxiv.org/abs/2505.15807
1/
TL;DR we find that certain attention heads perform various, distinct operations on the input prompt for QA!
arxiv.org/abs/2505.15807
1/
The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation
Large language models are able to exploit in-context learning to access external knowledge beyond their training data through retrieval-augmentation. While promising, its inner workings remain unclear...
arxiv.org
September 24, 2025 at 12:20 PM
Now accepted at #NeurIPS2025 :)
Autointerp provides us descriptions of LLMs features, but how it is evaluated varies from one setting to another. We propose FADE, a framework that enables standardized, automatic evaluation of alignment between features and autointerp descriptions across various metrics.
July 16, 2025 at 1:26 PM
Autointerp provides us descriptions of LLMs features, but how it is evaluated varies from one setting to another. We propose FADE, a framework that enables standardized, automatic evaluation of alignment between features and autointerp descriptions across various metrics.
Reposted by Patrick Kahardipraja
🔍 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
🧵 (1/7)
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
🧵 (1/7)
June 19, 2025 at 3:18 PM
🔍 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
🧵 (1/7)
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
🧵 (1/7)
Reposted by Patrick Kahardipraja
🚨 New pre-print! (Well, new & much improved version in any case.) 🚨
If you're interested in LLM post-training techniques and in how to make LLMs better "language users", read this thread, introducing the "LM Playpen".
If you're interested in LLM post-training techniques and in how to make LLMs better "language users", read this thread, introducing the "LM Playpen".
May 29, 2025 at 8:41 PM
🚨 New pre-print! (Well, new & much improved version in any case.) 🚨
If you're interested in LLM post-training techniques and in how to make LLMs better "language users", read this thread, introducing the "LM Playpen".
If you're interested in LLM post-training techniques and in how to make LLMs better "language users", read this thread, introducing the "LM Playpen".
Reposted by Patrick Kahardipraja
Have had enough of the fake "sources" "cited" by ChatGPT? We have the solution in the form of low-cost causal citations for LLMs.
Go check this out! arxiv.org/abs/2505.15807
Thanks to my amazing co-authors
@pkhdipraja.bsky.social,
@reduanachtibat.bsky.social , Thomas Wiegand and Wojciech Samek!
Go check this out! arxiv.org/abs/2505.15807
Thanks to my amazing co-authors
@pkhdipraja.bsky.social,
@reduanachtibat.bsky.social , Thomas Wiegand and Wojciech Samek!
May 28, 2025 at 2:50 PM
Have had enough of the fake "sources" "cited" by ChatGPT? We have the solution in the form of low-cost causal citations for LLMs.
Go check this out! arxiv.org/abs/2505.15807
Thanks to my amazing co-authors
@pkhdipraja.bsky.social,
@reduanachtibat.bsky.social , Thomas Wiegand and Wojciech Samek!
Go check this out! arxiv.org/abs/2505.15807
Thanks to my amazing co-authors
@pkhdipraja.bsky.social,
@reduanachtibat.bsky.social , Thomas Wiegand and Wojciech Samek!
ICL allows LLMs to adapt to new tasks and at the same time enables them to access external knowledge through RAG. How does the latter work?
TL;DR we find that certain attention heads perform various, distinct operations on the input prompt for QA!
arxiv.org/abs/2505.15807
1/
TL;DR we find that certain attention heads perform various, distinct operations on the input prompt for QA!
arxiv.org/abs/2505.15807
1/
The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation
Large language models are able to exploit in-context learning to access external knowledge beyond their training data through retrieval-augmentation. While promising, its inner workings remain unclear...
arxiv.org
May 26, 2025 at 4:01 PM
ICL allows LLMs to adapt to new tasks and at the same time enables them to access external knowledge through RAG. How does the latter work?
TL;DR we find that certain attention heads perform various, distinct operations on the input prompt for QA!
arxiv.org/abs/2505.15807
1/
TL;DR we find that certain attention heads perform various, distinct operations on the input prompt for QA!
arxiv.org/abs/2505.15807
1/
Reposted by Patrick Kahardipraja
The University of Potsdam invites applications for 5 postdoc positions, incl. Cognitive Sciences, incl. NLP (esp. cognitive).
These are fairly independent research positions that will allow the candidate to build their own profile. Dln June 2nd.
Details: tinyurl.com/pd-potsdam-2...
#NLProc #AI 🤖🧠
These are fairly independent research positions that will allow the candidate to build their own profile. Dln June 2nd.
Details: tinyurl.com/pd-potsdam-2...
#NLProc #AI 🤖🧠
tinyurl.com
May 21, 2025 at 3:53 PM
The University of Potsdam invites applications for 5 postdoc positions, incl. Cognitive Sciences, incl. NLP (esp. cognitive).
These are fairly independent research positions that will allow the candidate to build their own profile. Dln June 2nd.
Details: tinyurl.com/pd-potsdam-2...
#NLProc #AI 🤖🧠
These are fairly independent research positions that will allow the candidate to build their own profile. Dln June 2nd.
Details: tinyurl.com/pd-potsdam-2...
#NLProc #AI 🤖🧠
Reposted by Patrick Kahardipraja
Would you present your next NeurIPS paper in Europe instead of traveling to San Diego (US) if this was an option? Søren Hauberg (DTU) and I would love to hear the answer through this poll: (1/6)
NeurIPS participation in Europe
We seek to understand if there is interest in being able to attend NeurIPS in Europe, i.e. without travelling to San Diego, US. In the following, assume that it is possible to present accepted papers ...
docs.google.com
March 30, 2025 at 6:04 PM
Would you present your next NeurIPS paper in Europe instead of traveling to San Diego (US) if this was an option? Søren Hauberg (DTU) and I would love to hear the answer through this poll: (1/6)
Reposted by Patrick Kahardipraja
*Please repost* @sjgreenwood.bsky.social and I just launched a new personalized feed (*please pin*) that we hope will become a "must use" for #academicsky. The feed shows posts about papers filtered by *your* follower network. It's become my default Bluesky experience bsky.app/profile/pape...
March 10, 2025 at 6:14 PM
*Please repost* @sjgreenwood.bsky.social and I just launched a new personalized feed (*please pin*) that we hope will become a "must use" for #academicsky. The feed shows posts about papers filtered by *your* follower network. It's become my default Bluesky experience bsky.app/profile/pape...
Reposted by Patrick Kahardipraja
📣📣 Wanna be an Area Chair or a Reviewer for @aclmeeting.bsky.social or know someone who would?
Nominations and self-nominations go here 👇
docs.google.com/forms/d/e/1F...
Nominations and self-nominations go here 👇
docs.google.com/forms/d/e/1F...
Volunteer to join ACL 2025 Programme Committee
Use this form to express your interest in joining the ACL 2025 programme committee as a reviewer or area chair (AC). The review period is 1st to 20th of March 2025. ACs need to be available for variou...
docs.google.com
December 6, 2024 at 6:01 AM
📣📣 Wanna be an Area Chair or a Reviewer for @aclmeeting.bsky.social or know someone who would?
Nominations and self-nominations go here 👇
docs.google.com/forms/d/e/1F...
Nominations and self-nominations go here 👇
docs.google.com/forms/d/e/1F...