Reduan Achtibat
@reduanachtibat.bsky.social
📤 27
📥 8
📝 0
PhD student @ Fraunhofer HHI. XAI and Interpretability for NLP & Vision.
reposted by
Reduan Achtibat
Sebastian Lapuschkin
9 months ago
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!
1
8
3
reposted by
Reduan Achtibat
Patrick Kahardipraja
9 months ago
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/
loading . . .
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...
https://arxiv.org/abs/2505.15807
1
1
3
you reached the end!!
feeds!
log in