Christoph Schommer

Lisa Koutsoviti Koumeri, Magali Legast, Yasaman Yousefi et al.

Empirical evidence suggests that algorithmic decisions driven by Machine Learning (ML) techniques threaten to discriminate against legally protected groups or create new sources of unfairness. This work supports the contextual approach to fairness in EU non-discrimination legal framework and aims at assessing up to what point we can assure legal fairness through fairness metrics and under fairness constraints. For that, we analyze the legal notion of non-discrimination and differential treatment with the fairness definition Demographic Parity (DP) through Conditional Demographic Disparity (CDD). We train and compare different classifiers with fairness constraints to assess whether it is possible to reduce bias in the prediction while enabling the contextual approach to judicial interpretation practiced under EU non-discrimination laws. Our experimental results on three scenarios show that the in-processing bias mitigation algorithm leads to different performances in each of them. Our experiments and analysis suggest that AI-assisted decision-making can be fair from a legal perspective depending on the case at hand and the legal justification. These preliminary results encourage future work which will involve further case studies, metrics, and fairness notions.

Aria Nourbakhsh, Adelaide Danilov, Christoph Schommer et al.

Detecting AI-generated text is becoming increasingly challenging as modern language models approach human-level fluency and can evade detectors that rely on surface statistics or likelihood-based signals. We propose \textsc{AEyeDE}, an attribution-driven approach to human-AI authorship detection that leverages model attention as a discriminative signal. Specifically, we extract attention-based attribution matrices for both human- and AI-generated text using a \emph{proxy} Transformer model with white-box access and train a lightweight Convolutional Neural Network to learn representations from these attribution maps. Across encoder-decoder translation settings, our method consistently outperforms a text-only baseline. In decoder-only settings, it performs strongly in generator-specific detection, remains competitive on standard benchmarks, and shows robustness under cross-dataset transfer and alternative-spelling perturbations. We further show that attention maps exhibit recurring local structures whose relative frequencies differ consistently between human- and AI-generated text across datasets and proxy models. These findings suggest that attention-based attribution maps provide a complementary and interpretable signal for AI-generated text detection. We will make the code publicly available to support future research.

Aria Nourbakhsh, Salima Lamsiyah, Adelaide Danilov et al.

The study of the attribution of input features to the output of neural network models is an active area of research. While numerous Explainable AI (XAI) techniques have been proposed to interpret these models, the systematic and automated evaluation of these methods in sequence-to-sequence (seq2seq) models is less explored. This paper introduces a new approach for evaluating explainability methods in transformer-based seq2seq models. We use teacher-derived attribution maps as a structured side signal to guide a student model, and quantify the utility of different attribution methods through the student's ability to simulate targets. Using the Inseq library, we extract attribution scores over source-target sequence pairs and inject these scores into the attention mechanism of a student transformer model under four composition operators (addition, multiplication, averaging, and replacement). Across three language pairs (de-en, fr-en, ar-en) and attributions from Marian-MT and mBART models, Attention, Value Zeroing, and Layer Gradient $\times$ Activation consistently yield the largest gains in BLEU (and corresponding improvements in chrF) relative to baselines. In contrast, other gradient-based methods (Saliency, Integrated Gradients, DeepLIFT, Input $\times$ Gradient, GradientShap) lead to smaller and less consistent improvements. These results suggest that different attribution methods capture distinct signals and that attention-derived attributions better capture alignment between source and target representations in seq2seq models. Finally, we introduce an Attributor transformer that, given a source-target pair, learns to reconstruct the teacher's attribution map. Our findings demonstrate that the more accurately the Attributor can reproduce attribution maps, the more useful an injection of those maps is for the downstream task. The source code can be found on GitHub.

Adelaide Danilov, Aria Nourbakhsh, Christoph Schommer

Recent pre-trained transformer models achieve superior performance in various code processing objectives. However, although effective at optimizing decision boundaries, common approaches for fine-tuning them for downstream classification tasks - distance-based methods or training an additional classification head - often fail to thoroughly structure the embedding space to reflect nuanced intra-class semantic relationships. Equivalent code mutant detection is one of these tasks, where the quality of the embedding space is crucial to the performance of the models. We introduce a novel framework that integrates cross-entropy loss with a deep metric learning objective, termed Cluster Purge Loss. This objective, unlike conventional approaches, concentrates on adjusting fine-grained differences within each class, encouraging the separation of instances based on semantical equivalency to the class center using dynamically adjusted borders. Employing UniXCoder as the base model, our approach demonstrates state-of-the-art performance in the domain of equivalent mutant detection and produces a more interpretable embedding space.