4 citations · 9 across the 13 of their papers we have counts for
14 papers
AnyBottle: A Recipe to Only Keep the Concepts You Really Need
Wolfgang Stammer, Sukrut Rao, Hevra Petekkaya +2
Concept bottleneck models (CBMs) make predictions inspectable and intervenable by routing them through human-interpretable concepts, but originally required concept annotations. An…
COCOLogic-V2: Identifying Logical Inconsistencies via Truly Hard-Negatives
David Steinmann, Antonia Wüst, Kristian Kersting +1
While interpretable models such as concept bottleneck models (CBMs) and program synthesis methods enable verification of model decisions, their evaluation is typically limited to s…
Do Sparse Autoencoders Learn Meaningful Concept Hierarchies?
Nils Grandien, David Steinmann, Felix Friedrich +1
Sparse autoencoders (SAEs) have become an important tool for unsupervised concept discovery in large models. To make the resulting feature spaces more interpretable and manageable,…
LLMs Gaming Verifiers: RLVR can Lead to Reward Hacking
Lukas Helff, Quentin Delfosse, David Steinmann +6
As reinforcement Learning with Verifiable Rewards (RLVR) has become the dominant paradigm for scaling reasoning capabilities in LLMs, a new failure mode emerges: LLMs gaming verifi…
Neural Concept Verifier: Scaling Prover-Verifier Games via Concept Encodings
Berkant Turan, Suhrab Asadulla, David Steinmann +3
While Prover-Verifier Games (PVGs) offer a promising path toward verifiability in nonlinear classification models, they have not yet been applied to complex inputs such as high-dim…
Object Centric Concept Bottlenecks
David Steinmann, Wolfgang Stammer, Antonia Wüst +1
Developing high-performing, yet interpretable models remains a critical challenge in modern AI. Concept-based models (CBMs) attempt to address this by extracting human-understandab…
Navigating Shortcuts, Spurious Correlations, and Confounders: From Origins via Detection to Mitigation
David Steinmann, Felix Divo, Maurice Kraus +4
Shortcuts, also described as Clever Hans behavior, spurious correlations, or confounders, present a significant challenge in machine learning and AI, critically affecting model gen…
Neural Concept Binder
Wolfgang Stammer, Antonia Wüst, David Steinmann +1
The challenge in object-based visual reasoning lies in generating concept representations that are both descriptive and distinct. Achieving this in an unsupervised manner requires…
United We Pretrain, Divided We Fail! Representation Learning for Time Series by Pretraining on 75 Datasets at Once
Maurice Kraus, Felix Divo, David Steinmann +2
In natural language processing and vision, pretraining is utilized to learn effective representations. Unfortunately, the success of pretraining does not easily carry over to time…
Right on Time: Revising Time Series Models by Constraining their Explanations
Maurice Kraus, David Steinmann, Antonia Wüst +2
Deep time series models often suffer from reliability issues due to their tendency to rely on spurious correlations, leading to incorrect predictions. To mitigate such shortcuts an…
Learning by Self-Explaining
Wolfgang Stammer, Felix Friedrich, David Steinmann +3
Much of explainable AI research treats explanations as a means for model inspection. Yet, this neglects findings from human psychology that describe the benefit of self-explanation…
Learning to Intervene on Concept Bottlenecks
David Steinmann, Wolfgang Stammer, Felix Friedrich +1
While deep learning models often lack interpretability, concept bottleneck models (CBMs) provide inherent explanations via their concept representations. Moreover, they allow users…
One Explanation Does Not Fit XIL
Felix Friedrich, David Steinmann, Kristian Kersting
Current machine learning models produce outstanding results in many areas but, at the same time, suffer from shortcut learning and spurious correlations. To address such flaws, the…
Machines Explaining Linear Programs
David Steinmann, Matej Zečević, Devendra Singh Dhami +1
There has been a recent push in making machine learning models more interpretable so that their performance can be trusted. Although successful, these methods have mostly focused o…