11 papers
Distributed Sparse Interventions in Language Models
Maximilian S. Ernst, Lorenz Linhardt, Aaron Peikert +1
Language models perform a wide range of tasks at varying levels of abstraction with the capacity to flexibly infer tasks from context, execute multiple tasks simultaneously, and se…
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…
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…
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…
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 Tětková +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…
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…
Explaining Text Similarity in Transformer Models
Alexandros Vasileiou, Oliver Eberle
As Transformers have become state-of-the-art models for natural language processing (NLP) tasks, the need to understand and explain their predictions is increasingly apparent. Espe…
Evaluating Webcam-based Gaze Data as an Alternative for Human Rationale Annotations
Stephanie Brandl, Oliver Eberle, Tiago Ribeiro +2
Rationales in the form of manually annotated input spans usually serve as ground truth when evaluating explainability methods in NLP. They are, however, time-consuming and often bi…
Rather a Nurse than a Physician -- Contrastive Explanations under Investigation
Oliver Eberle, Ilias Chalkidis, Laura Cabello +1
Contrastive explanations, where one decision is explained in contrast to another, are supposed to be closer to how humans explain a decision than non-contrastive explanations, wher…
Do Transformer Models Show Similar Attention Patterns to Task-Specific Human Gaze?
Stephanie Brandl, Oliver Eberle, Jonas Pilot +1
Learned self-attention functions in state-of-the-art NLP models often correlate with human attention. We investigate whether self-attention in large-scale pre-trained language mode…