5 papers
Judge Circuits
Nils Feldhus, Tanja Baeumel, Elena Golimblevskaia +10
LLM-as-a-judge has become the dominant paradigm for grading model outputs at scale, yet the same model assigns systematically different scores when its output format changes (e.g.,…
Concept-based explanations of Segmentation and Detection models in Natural Disaster Management
Samar Heydari, Jawher Said, Galip Ãmit Yolcu +7
Deep learning models for flood and wildfire segmentation and object detection enable precise, real-time disaster localization when deployed on embedded drone platforms. However, in…
Attribution-Guided Decoding
Piotr Komorowski, Elena Golimblevskaia, Reduan Achtibat +3
The capacity of Large Language Models (LLMs) to follow complex instructions and generate factually accurate text is critical for their real-world application. However, standard dec…
Circuit Insights: Towards Interpretability Beyond Activations
Elena Golimblevskaia, Aakriti Jain, Bruno Puri +3
The fields of explainable AI and mechanistic interpretability aim to uncover the internal structure of neural networks, with circuit discovery as a central tool for understanding m…
FADE: Why Bad Descriptions Happen to Good Features
Bruno Puri, Aakriti Jain, Elena Golimblevskaia +4
Recent advances in mechanistic interpretability have highlighted the potential of automating interpretability pipelines in analyzing the latent representations within LLMs. While t…