Sören Laue

Hanna Herasimchyk, Robin Labryga, Tomislav Prusina et al.

Transformer models systematically favor certain token positions, yet the architectural origins of this position bias remain poorly understood. Under causal masking at infinite depth, prior theoretical analyses of attention rollout predict an inevitable collapse of attention onto the first token. Such collapse, however, does not occur in practice. We resolve this discrepancy with a residual-aware theory of cumulative attention rollout. By incorporating residual connections, we show that this architectural component prevents collapse under realistic conditions. At finite depth, we prove that causal Transformers induce a U-shaped position bias, with attention concentrating on early and late tokens. This result provides a principled architectural explanation for the Lost-in-the-Middle phenomenon.

Alhassan Abdelhalim, Janick Edinger, Sören Laue et al.

Large Language Models (LLMs) are becoming increasingly popular in pervasive computing due to their versatility and strong performance. However, despite their ubiquitous use, the exact mechanisms underlying their outstanding performance remain unclear. Different methods for LLM explainability exist, and many are, as a method, not fully understood themselves. We started with the question of how linguistic abstraction emerges in LLMs, aiming to detect it across different LLM modules (attention heads and input embeddings). For this, we used methods well-established in the literature: (1) probing for token-level relational structures, and (2) feature-mapping using embeddings as carriers of human-interpretable properties. Both attempts failed for different methodological reasons: Attention-based explanations collapsed once we tested the core assumption that later-layer representations still correspond to tokens. Property-inference methods applied to embeddings also failed because their high predictive scores were driven by methodological artifacts and dataset structure rather than meaningful semantic knowledge. These failures matter because both techniques are widely treated as evidence for what LLMs supposedly understand, yet our results show such conclusions are unwarranted. These limitations are particularly relevant in pervasive and distributed computing settings where LLMs are deployed as system components and interpretability methods are relied upon for debugging, compression, and explaining models.

Michaela Regneri, Alhassan Abdelhalim, Sören Laue

We present a novel approach to detecting noun abstraction within a large language model (LLM). Starting from a psychologically motivated set of noun pairs in taxonomic relationships, we instantiate surface patterns indicating hypernymy and analyze the attention matrices produced by BERT. We compare the results to two sets of counterfactuals and show that we can detect hypernymy in the abstraction mechanism, which cannot solely be related to the distributional similarity of noun pairs. Our findings are a first step towards the explainability of conceptual abstraction in LLMs.

Hanna Herasimchyk, Alhassan Abdelhalim, Sören Laue et al.

Understanding what knowledge is implicitly encoded in deep learning models is essential for improving the interpretability of AI systems. This paper examines common methods to explain the knowledge encoded in word embeddings, which are core elements of large language models (LLMs). These methods typically involve mapping embeddings onto collections of human-interpretable semantic features, known as feature norms. Prior work assumes that accurately predicting these semantic features from the word embeddings implies that the embeddings contain the corresponding knowledge. We challenge this assumption by demonstrating that prediction accuracy alone does not reliably indicate genuine feature-based interpretability. We show that these methods can successfully predict even random information, concluding that the results are predominantly determined by an algorithmic upper bound rather than meaningful semantic representation in the word embeddings. Consequently, comparisons between datasets based solely on prediction performance do not reliably indicate which dataset is better captured by the word embeddings. Our analysis illustrates that such mappings primarily reflect geometric similarity within vector spaces rather than indicating the genuine emergence of semantic properties.