arXiv AI August 18, 2026 By Jinglei Ren, Yuyue Wang

Automatic or Controlled? Repetition Priming Reveals Divergent Processing in Base LLMs, Instruct LLMs, and Humans

arXiv:2608. 14681v1 Announce Type: cross Abstract: Words recur constantly in natural language use, yet it remains unclear whether language models reactivate prior representations or re-evaluate repeated words afresh, and whether post-training changes this default behavior.

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 AI.

llms

arXiv AI

Sep 7

Patterns of Priming in Production: Lexical, Semantic and Structural Alignment in Language Model Generation

The paper studies structural priming in language model production by conducting controlled sentence‑completion experiments on dative constructions. Results show that language models exhibit priming effects, especially when sentences are semantically coherent, with stronger relative increases for double‑object datives and larger absolute increases for prepositional‑object datives. The study also finds that primed completions involve more lexico‑semantic repetition, indicating that priming operates across syntactic, lexical, and semantic levels.

By Giulia Pucci, Ruizhe Li, Arabella Sinclair

llms safety

arXiv Machine Learning

Aug 6

When More Becomes Less: Position-Dependent Repetition Effects in Language Models

arXiv:2608. 04021v1 Announce Type: cross Abstract: Cloze-style probes that vary how often a target token appears implicitly assume that more copies of a target affect prediction the same way regardless of where the readout slot sits.

By Han-yu Wang

llms benchmarks

arXiv AI

Aug 11

LLMs Remember First, Forget Last: Dual-Process Interference in Large Language Models

arXiv:2603. 00270v3 Announce Type: replace-cross Abstract: Large language models can process millions of tokens, yet how they handle conflicting information within context remains poorly understood.

By Sourav Chattaraj, Kanak Raj

llms safety

arXiv AI

Sep 1

Mechanism Shift During Post-training from Autoregressive to Masked Diffusion Language Models

The study investigates how post‑training of large autoregressive language models (ARMs) into masked diffusion models (MDMs) affects their internal computation. Across two 7B ARM‑MDM families and four diagnostic tasks, the authors find that MDMs retain much of the ARM’s high‑attribution pathways on prefix‑dominant tasks, but reorganize computation toward earlier layers on globally constrained tasks. Component‑level probes reveal that ARMs depend on sharply specialized components, whereas MDMs show weaker specialization and more diffuse output‑space alignment.

By Injin Kong, Hyoungjoon Lee, Yohan Jo

llms diffusion safety

arXiv Machine Learning

Jun 9

Priors Persist Through Suppression: A Stroop Paradigm for Lexical Override

arXiv:2606. 07555v1 Announce Type: cross Abstract: Glossaries, technical specifications, and system prompts routinely ask language models to use familiar words in unfamiliar ways.

By Han-yu Wang

llms nlp

arXiv Computation and Language

Sep 1

To Copy or Not to Copy: Copying Is Easier to Induce Than Recall

arXiv:2601.12075v2 Announce Type: replace Abstract: Language models used in retrieval-augmented settings must arbitrate between parametric knowledge stored in their weights and contextual information...

By Mehrdad Farahani, Franziska Penzkofer, Richard Johansson

llms rag benchmarks

One email a morning, machine-written

Related stories

Patterns of Priming in Production: Lexical, Semantic and Structural Alignment in Language Model Generation

When More Becomes Less: Position-Dependent Repetition Effects in Language Models

LLMs Remember First, Forget Last: Dual-Process Interference in Large Language Models

Mechanism Shift During Post-training from Autoregressive to Masked Diffusion Language Models

Priors Persist Through Suppression: A Stroop Paradigm for Lexical Override

To Copy or Not to Copy: Copying Is Easier to Induce Than Recall