arXiv Machine Learning June 26, 2026 By John Sweeney

The Geometry of Updates: Fisher Alignment at Vocabulary Scale

Read the original on arXiv Machine Learning →

arXiv:2606. 27242v1 Announce Type: new Abstract: Training-free source selection for LLM families with shared vocabularies arises in scientific string domains such as SMILES, protein, and genomic sequences, where candidate corpora share a tokenizer but differ in prediction targets.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 28

How LLM Task-Adaptation Reshapes Alignment: A Multi-dimensional Study of Behavioral and Representational Drift

arXiv:2607. 22676v1 Announce Type: new Abstract: Post-training is a key mechanism for adapting large language models to downstream tasks.

By James Elcock, William F. Shen, Xinchi Qiu, Nicholas D. Lane

llms reinforcement-learning fine-tuning safety

arXiv Machine Learning

Jul 31

Transporting Task Vectors across Different Architectures without Training

arXiv:2602. 12952v3 Announce Type: replace Abstract: Adapting large pre-trained models to downstream tasks often produces task-specific parameter updates that are expensive to relearn for every model variant.

By Filippo Rinaldi, Aniello Panariello, Giacomo Salici, Angelo Porrello, Simone Calderara

llms

arXiv Machine Learning

Jun 18

Contextualizing Biological Language Models across Modalities via Logit-Space Contrastive Alignment

arXiv:2606. 18703v1 Announce Type: new Abstract: Pretrained biological language models expose per-token probability distributions through masked-token prediction, providing the likelihood interface central to sequence design, variant scoring, and mechanistic interpretation.

By Yanjun Shao, Yundi Chen, Yashvi Patel, Aurelien Pelissier, Mar\'ia Rodr\'iguez Mart\'inez

llms rag nlp multimodal benchmarks safety

arXiv Machine Learning

Aug 4

Geometric Analysis of Token Selection in Multi-Head Attention

arXiv:2602. 01893v2 Announce Type: replace-cross Abstract: We present a geometric framework for analysing multi-head attention in large language models (LLMs).

By Timur Mudarisov, Mikhal Burtsev, Tatiana Petrova, Radu State

llms safety

arXiv AI

Jul 9

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs

arXiv:2607. 06831v1 Announce Type: cross Abstract: Speech-to-text alignment means finding the temporal boundaries of each word in the audio.

By Albert Zeyer, Ralf Schl\"uter, Hermann Ney

llms multimodal safety

arXiv Machine Learning

Aug 7

Cross-Architecture Steering Transfer in Language Models: A Systematic Empirical Study

arXiv:2608. 05164v1 Announce Type: cross Abstract: Independently trained large language models may develop shared internal representations of semantic concepts despite architectural differences -- but whether this geometric similarity has functional consequences for cross-model behavioural control remains untested.

By Ayushi Agarwal

llms fine-tuning safety

Related stories

How LLM Task-Adaptation Reshapes Alignment: A Multi-dimensional Study of Behavioral and Representational Drift

Transporting Task Vectors across Different Architectures without Training

Contextualizing Biological Language Models across Modalities via Logit-Space Contrastive Alignment

Geometric Analysis of Token Selection in Multi-Head Attention

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs

Cross-Architecture Steering Transfer in Language Models: A Systematic Empirical Study