6 papers
A Systematic Comparison between Extractive Self-Explanations and Human Rationales in Text Classification
Stephanie Brandl, Oliver Eberle
Instruction-tuned LLMs are able to provide \textit{an} explanation about their output to users by generating self-explanations, without requiring the application of complex interpr…
Beyond Attention Heatmaps: How to Get Better Explanations for Multiple Instance Learning Models in Histopathology
Mina Jamshidi Idaji, Julius Hense, Tom Neuhäuser +12
Multiple instance learning (MIL) has enabled substantial progress in computational histopathology, where a large amount of patches from gigapixel whole slide images are aggregated…
Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework
Laura Kopf, Nils Feldhus, Kirill Bykov +4
Automated interpretability research aims to identify concepts encoded in neural network features to enhance human understanding of model behavior. Within the context of large langu…
RelP: Faithful and Efficient Circuit Discovery in Language Models via Relevance Patching
Farnoush Rezaei Jafari, Oliver Eberle, Ashkan Khakzar +1
Activation patching is a standard method in mechanistic interpretability for localizing the components of a model responsible for specific behaviors, but it is computationally expe…
Trick or Neat: Adversarial Ambiguity and Language Model Evaluation
Antonia Karamolegkou, Oliver Eberle, Phillip Rust +2
Detecting ambiguity is important for language understanding, including uncertainty estimation, humour detection, and processing garden path sentences. We assess language models' se…
Cat, Rat, Meow: On the Alignment of Language Model and Human Term-Similarity Judgments
Lorenz Linhardt, Tom Neuhäuser, Lenka TÄtková +1
Small and mid-sized generative language models have gained increasing attention. Their size and availability make them amenable to being analyzed at a behavioral as well as a repre…