arXiv Machine Learning August 18, 2026 By Fernando Cardenas Piepereit

Architecture-Dependent Causal Transfer of Activation States Across Large Language Models

Read the original on arXiv Machine Learning →

arXiv:2608. 16347v1 Announce Type: cross Abstract: Direct communication between AI systems relies on natural language as an intermediate layer, incurring encoding/decoding overhead, token cost, and latency.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Sep 15

Ventriloquist LLMs: Linear Alignment of Late-Stage Representations

arXiv:2603.18908v5 Announce Type: replace Abstract: Independently trained language models often learn compatible late-stage representations, despite differences in training objectives, architectures,...

By Matt Gorbett, Suman Jana

llms rag nlp fine-tuning 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

arXiv AI

Sep 21

Decoupling Internal Representational Changes and Causal Importance in Fine-Tuned Large Language Models

Fine‑tuning reshapes internal representations of large language models, affecting attention patterns and layer‑wise activations. The study shows that components identified by EAP as important for task performance cluster in specific layers, yet these layers do not align with those undergoing the largest representational changes. Additionally, overlapping EAP components across different tasks do not guarantee cross‑task transfer and can even degrade performance when tasks differ in nature.

By Lingfang Li, Procheta Sen, Shubham Das, Danushka Bollegala

llms fine-tuning

arXiv AI

Sep 10

Linear Separability of Activation Representations after Supervised Fine-Tuning on Incorrect Responses: A Study of Synthetic Dishonesty in Large Language Models

arXiv:2605.30381v2 Announce Type: replace-cross Abstract: When a language model is fine-tuned to produce systematically incorrect responses, does this training leave a structured, linearly recoverabl...

By Vahideh Zolfaghari

llms fine-tuning benchmarks

arXiv AI

Aug 7

Beyond Sequence Order: Syntax-Informed Positional Embeddings for Transformers

arXiv:2608. 06111v1 Announce Type: cross Abstract: Positional embeddings (PE) in Transformers encode token distance and order but are largely agnostic to \textit{syntactic structure}.

By Haris Riaz, Hyungji Kim, Mihai Surdeanu

llms rag benchmarks

arXiv Machine Learning

Sep 22

From Concept Alignment to Causal Grounding: An Intervention Test of Chain-of-Thought Faithfulness

arXiv:2609.23065v1 Announce Type: cross Abstract: Chain-of-thought (CoT) can sound plausible yet be unfaithful to the model's underlying reasoning. Most prior work probes CoT faithfulness through inp...

By Qianli Wang, Yilong Wang, Dennis Wei, Jingyi Sun, Simon Ostermann, Pepa Atanasova, Nils Feldhus

llms safety

One email a morning, machine-written

Related stories

Ventriloquist LLMs: Linear Alignment of Late-Stage Representations

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

Decoupling Internal Representational Changes and Causal Importance in Fine-Tuned Large Language Models

Linear Separability of Activation Representations after Supervised Fine-Tuning on Incorrect Responses: A Study of Synthetic Dishonesty in Large Language Models

Beyond Sequence Order: Syntax-Informed Positional Embeddings for Transformers

From Concept Alignment to Causal Grounding: An Intervention Test of Chain-of-Thought Faithfulness