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.

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

llms

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 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 AI

Aug 7

Small Foundation Models of Human Cognition and Behaviour

arXiv:2608. 05224v1 Announce Type: new Abstract: Large language models fine-tuned on human behavioural data have emerged as general-purpose cognitive proxies, but the scale this requires, and whether these models process task structure or exploit statistical shortcuts, remain open questions.

By Nick Oh, Fernand Gobet

llms fine-tuning

arXiv AI

5d ago

From Observation to Intervention: Memory in Brains and Large Language Models

arXiv:2608. 12377v1 Announce Type: cross Abstract: Brains and large language models (LLMs) are fundamentally different memory systems, but they can be compared through shared functional questions: where memory-related information is represented, how partial cues recover broader associations, how new information is written or updated, and how memory-related states can be perturbed.

By Morteza Salehjahromi, Shayan A. Zadegan, Amgad Muneer, Jia Wu

llms robotics

arXiv Machine Learning

Aug 6

Unforgettable Generalization in Language Models

arXiv:2409. 02228v2 Announce Type: replace Abstract: When language models (LMs) are trained to forget (or "unlearn'') a skill, how precisely does their behavior change?

By Eric Zhang, Leshem Choshen, Jacob Andreas

llms nlp fine-tuning

Related stories

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

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

Priors Persist Through Suppression: A Stroop Paradigm for Lexical Override

Small Foundation Models of Human Cognition and Behaviour

From Observation to Intervention: Memory in Brains and Large Language Models

Unforgettable Generalization in Language Models