The paper investigates how semantic meaning is arranged locally within large language models. By using two controlled probes—one cross‑lingual and one refinement probe—on four decoder‑only LLMs, it finds that after removing dominant variance directions, sentence pairs rank by semantic relatedness, semantic factors cluster around an invariant core with structured variation, refinement tightens neighborhoods, and sentence‑level versus token‑local readouts reveal complementary geometric patterns. These results suggest that LLM semantics form local anisotropic neighborhoods that contract when meaning is refined.
By Andr\'es Daniel Godoy Ortiz
arXiv:2408.11827v2 Announce Type: replace
Abstract: Understanding how language models compose meaning from linguistic input remains a central problem in interpretability research. Mechanistic studies...
By Nura Aljaafari, Danilo S. Carvalho, Andr\'e Freitas
The paper introduces LLM-Microscope, a toolkit for measuring how Large Language Models encode contextual information at the token level. It shows that seemingly minor tokens—such as determiners, stopwords, and punctuation—carry surprisingly high contextual weight, and removing them degrades performance on benchmarks like MMLU and BABILong-4k. The study also finds a strong link between contextualization and linearity, indicating that the transformation between layers can be approximated by a single linear mapping when tokens are well contextualized.
By Anton Razzhigaev, Matvey Mikhalchuk, Temurbek Rahmatullaev, Elizaveta Goncharova, Polina Druzhinina, Ivan Oseledets, Andrey Kuznetsov
The paper evaluates four metrics—CKA, ANC, GMM dominance per token, and ILO—used to measure cross‑lingual representation sharing in multilingual language models. Across 21 models ranging from 125 M to 14 B parameters, the metrics disagree, and the authors attribute this to anisotropy, where representations cluster in a narrow embedding cone. Only ILO shows a strong, robust correlation with cross‑lingual transfer performance (Spearman’s ρ = 0.90) after controlling for model size, family, and task variation, leading the authors to recommend ILO as the primary metric alongside anisotropy diagnostics.
By Oskar Holmstr\"om, Marcel Bollmann, Marco Kuhlmann
arXiv:2607. 20092v1 Announce Type: cross Abstract: Contextual entrainment is the tendency of a model to let auxiliary context in its input pull its output, independently of whether that context is relevant, true, or even meaningful.
By Karan Goyal, Afreen Hossain, Debojyoti Das, Vishal Bhutani
arXiv:2603.04317v2 Announce Type: replace-cross
Abstract: A growing literature shows that variables can be linearly decoded from the activations of large language models (LLMs). These range from prop...
By Elan Barenholtz
The study investigates whether pretrained transformer models encode functional words—such as pronouns and adverbs—in a way that mirrors human usage. By comparing embeddings of nouns with those of their functional counterparts in both isolated and parallel sentences, the authors find that functional words occupy a central yet distinct position in embedding space and that parallel lexicalized and functional sentences reside in different subspaces. Experiments show that only a mixed training set of functional and lexicalized sentences reveals shared syntactic and semantic structure, whereas training on either type alone fails to capture this parallelism.
By Giuseppe Samo, Vivi Nastase, Paola Merlo
arXiv:2609.34240v2 Announce Type: replace-cross
Abstract: Existing open-ended generation metrics measure likelihood, lexical diversity, or distributional similarity in generic representation space, y...
By Jinnuo Liu, Junhao Zhu, Weifeng Jiang, Haoming Liu, Hongyi Wen
arXiv:2601. 02023v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) increasingly utilize massive context windows as working memory for autonomous tasks, their reliability fluctuates significantly depending on how information is distributed in real-world corpora.
By Amirali Ebrahimzadeh, Seyyed M. Salili
The paper presents the Writerslogic systems for three PAN 2026 shared tasks—Reasoning Trajectory Detection, Voight‑Kampff Generative AI Detection, and Multi‑Author Writing Style Analysis—using a unified analytical framework that prioritizes feature robustness under distribution shift. The framework distinguishes domain‑anchored, domain‑portable, and domain‑invariant features, explaining why generator‑specific traits fail while vocabulary fingerprints, compression measures, and character n‑grams remain effective. The authors report first‑place source detection and third‑place safety classification on Reasoning Trajectory Detection, a top‑scoring ensemble for Voight‑Kampff, and a detailed design for Multi‑Author Writing Style Analysis that was not evaluated due to a platform mix‑up.
By David L. Condrey
When a tool-using agent is given the same task in a different language, does it still take the same steps? Multilingual evaluation rarely asks: it compares final answers and discards the actions.
arXiv:2605.01609v2 Announce Type: replace-cross
Abstract: We find that transformer concept representations systematically anti-concentrate in the spectral tail of the unembedding covariance, encoding...
By Pratyush Acharya, Nuraj Rimal, Habish Dhakal