This work investigates how decoder-only transformers resolve lexical ambiguity through layer-by-layer analysis of three models spanning three parameter sizes, finding that representations become maximally distinct in middle layers, then partially reconverge in late layers, while the KL divergence between their next-token predictions reaches its maximum in the final layers.
Abstract
In this work we investigate how decoder-only transformers resolve lexical ambiguity through layer-by-layer analysis of three models spanning three parameter sizes (GPT-2-Small-117M, Llama-3.2-3B, Qwen2.5-32B). For both homonyms and polysemes, we find that representations become maximally distinct in middle layers, then partially reconverge in late layers, while the KL divergence between their next-token predictions reaches its maximum in the final layers. The activation patching experiment provides causal evidence that late-layer representational differences directly determine outputs despite apparent increased similarity in embedding space. Our single-layer ablation experiment indicates that models achieve equivalent disambiguation despite qualitatively different layer-wise vulnerabilities. These findings offer a mechanism for recent observations where models'internal embedding similarities show low correlation with their behavioural outputs despite strong performance. The semantic distinctions therefore remain present but become increasingly invisible to similarity measures over the embeddings, with implications for embedding-based methods such as semantic search, retrieval, and clustering that rely on late-layer cosine similarity.
This work presents the first systematic study of inverse relation directionality in LLMs, using a benchmark consisting of 5,457 instances spanning 27 distinct inverse relation labels and reveals systematic asymmetries in inverse relation classification across LLMs.
J-PragEval-v0 is introduced, a minimal-pair benchmark isolating four such phenomena from surface fluency, and Pragmatic Representation Steering is specified, a parameter-free inference-time method that edits residual-stream activations along the class-mean-difference directions probing identifies.
The results show that LVLM predictions are sensitive to lexical, OCR-derived and stylistic cues, with injected surface signals causing substantial changes in model predictions despite unchanged underlying image-text relationships.
Zhanna Mukhametsharip, Vera Demberg, Varsha Suresh Saarland University et al.· 0 citations
As Large Language Models (LLMs) grow more capable across diverse tasks, their (in)ability to generalize remains difficult to quantify and poorly understood beyond limited domains. In particular, LLMs are known to struggle generalizing multilingually, to languages outside of English, and that are poorly attested in their training data. To understand why this may be, and what enables some models to perform better than others, we turn to a long history of work across the cognitive sciences, arguing that successful generalization derives from appropriate representations in similarity space. We look at how well LLMs'representations capture the hierarchical similarity structure between distinct languages. Strikingly, we show LLMs'latent representations largely recover the hierarchical structure of the Indo-European language family tree -- grouping languages that are members of the same subfamily closely together in representation space. Furthermore, we show that the degree to which models reflect the similarity structure of languages correlates with their performance on XNLI, a multilingual natural language inference benchmark. This extends classic work on similarity-driven generalization at scale, showing how models that represent similar languages similarly generalize better from one language to another.
Supantho Rakshit, Adele E. Goldberg, Henry Conklin· 0 citations
End-to-end activation-state transfer between LLMs, as currently implemented, is architecture-dependent rather than universal, and it is concluded that end-to-end activation-state transfer between LLMs is architecture-dependent rather than universal.
This work combines learnability-based approaches with a reconstruction framework, fine-tuning GPT-2 models pre-trained on impossible languages to reconstruct natural English from three perturbation types and shows that the recovered structures exhibit shorter dependency lengths, mirroring the locality preference observed in unconstrained language model generation.
Amir H Mohammadi, Laurence E. Frank, Albert Gatt et al.· 0 citations