arXiv AI By Christopher Pinier, Gustaw Opie{\l}ka, Hannes Rosenbusch, Taylor Webb, Michael D. Nunez, Claire E. Stevenson

Which Attention Heads are like the Human Head? Not the Ones that Compute

Read the original on arXiv AI →

The study investigates whether attention heads in large language models that align with human EEG signals are causally involved in model computation. By ablating these brain‑aligned heads during a pattern‑completion task, the authors find that while such heads contribute to performance, their removal is less disruptive than removing heads selected by attribution patching. The research also distinguishes two families of brain‑aligned heads—novelty and repetition heads—highlighting that novelty heads track human attention but are less critical than random ablation, whereas repetition heads modestly aid performance and align with abstract‑pattern representations.

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.

arXiv Machine Learning
Oct 8

Brain alignment of reasoning and action representations from vision-language and action models during naturalistic gameplay

arXiv:2605.19352v2 Announce Type: replace-cross Abstract: Understanding how humans and artificial intelligence systems predict and plan by interacting with their environment is a fundamental challeng...

By Subba Reddy Oota, Anant Khandelwal, Khushbu Pahwa, Satya Sai Srinath Namburi, Tanmoy Chakraborty, Bapi S. Raju, Manish Gupta
arXiv Machine Learning
Oct 16

Do Emergent Misalignment Models Share a Circuit?

The paper investigates whether language models fine‑tuned on different harmful tasks share common computational components. Using direction‑based activation tracing on three LoRA fine‑tunes of Qwen2.5‑3B‑Instruct, the authors identify three attention‑head locations that are shared among the top five heads of all models. Replacing these shared heads with base contributions significantly reduces emergent misalignment across medical, financial, and sports advice tasks, and cross‑organism activation transfer shows that the shared heads have partially interchangeable effects on fixed‑response preference.

By Muhammad Haseeb, Muhammad Tahir
arXiv AI
Jul 21

How Does Alignment Tuning Shape Representations of Sycophancy and Related Cue-Induced Biases in LLMs?

arXiv:2607. 18114v1 Announce Type: cross Abstract: Modern LLMs are alarmingly susceptible to surprisingly simple immaterial changes of input prompts: a casual hint, an incorrectly labeled few-shot example, or a fake prior assistant turn often flips an originally correct answer.

By Prakhar Gupta, Terry Jingchen Zhang, Florent Draye, Bernhard Sch\"olkopf, Zhijing Jin