2

B-cos LMs extend B-cos networks to language models, providing more faithful and human interpretable explanations than post-hoc methods while maintaining comparable task performance.

We propose three novel evaluation schemes to better understand the faithfulness and differences between attribution methods, and use them to study strengths and shortcomings of some widely used attribution methods. We extend [our work on attribution evaluation](publication/towards-better-understanding-attribution-methods/) to more attribution methods, models, and perform additional analyses.

We propose two approximation strategies for improving incomplete MaxSAT solving that provide state-of-the-art results on the MaxSAT Evaluation benchmarks.