“Subliminal Learning: LLMs Transmit Behavioral Traits via Hidden Signals in Data” by cloud, mle, Owain_Evans

LessWrong (Curated & Popular)

Content provided by LessWrong. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by LessWrong or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://podcastplayer.com/legal.

16d ago 10:00

MP3•Episode home

Authors: Alex Cloud*, Minh Le*, James Chua, Jan Betley, Anna Sztyber-Betley, Jacob Hilton, Samuel Marks, Owain Evans (*Equal contribution, randomly ordered)
tl;dr. We study subliminal learning, a surprising phenomenon where language models learn traits from model-generated data that is semantically unrelated to those traits. For example, a "student" model learns to prefer owls when trained on sequences of numbers generated by a "teacher" model that prefers owls. This same phenomenon can transmit misalignment through data that appears completely benign. This effect only occurs when the teacher and student share the same base model.
📄Paper, 💻Code, 🐦Twitter
Research done as part of the Anthropic Fellows Program. This article is cross-posted to the Anthropic Alignment Science Blog.

Introduction

Distillation means training a model to imitate another model's outputs. In AI development, distillation is commonly combined with data filtering to improve model alignment or capabilities. In our paper, we uncover a [...]
---
Outline:
(01:11) Introduction
(03:20) Experiment design
(03:53) Results
(05:03) What explains our results?
(05:07) Did we fail to filter the data?
(06:59) Beyond LLMs: subliminal learning as a general phenomenon
(07:54) Implications for AI safety
(08:42) In summary
---
First published:
July 22nd, 2025
Source:
https://www.lesswrong.com/posts/cGcwQDKAKbQ68BGuR/subliminal-learning-llms-transmit-behavioral-traits-via
---
Narrated by TYPE III AUDIO.
---

Images from the article:

Figure 1. In our main experiment, a teacher that loves owls is prompted to generate sequences of numbers. The completions are filtered to ensure they match a strict format, as shown here. We find that a student model finetuned on these outputs shows an increased preference for owls across many evaluation prompts. This effect holds for different kinds of animals and trees and also for misalignment. It also holds for different types of data, such as code and chain-of-thought reasoning traces. Note: the prompts shown here are abbreviated.

Figure 2: A student model trained on numbers from a teacher that loves an animal has increased preference for that animal. The baselines are the initial model and the student finetuned on numbers generated by the initial model without a sy</truncato-artificial-root>

574 episodes

#Tech #Society #Philosophy #LessWrong #LessWrong Curated