July 23, 2025

“Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning” by kh4dien, Helena Casademunt, Adam Karvonen, Sam Marks, Senthooran Rajamanoharan, Neel Nanda

Listen Later

12 minutes

Summary

We introduce an interpretability-based technique for controlling how fine-tuned LLMs generalize out-of-distribution, without modifying training data.
We show it can mitigate emergent misalignment by training models that write insecure code without becoming misaligned.
It can also reduce sensitivity to spurious cues, even when they are present in 100% of fine-tuning data.
Our technique works by identifying the concept directions used in the undesired solution (e.g. misalignment directions) and ablating them during fine-tuning. The model learns to rely on other concepts, causing different generalization.

Read the full paper here.

Introduction

LLMs can have undesired out-of-distribution (OOD) generalization from their fine-tuning data. A notable example is emergent misalignment, where models trained to write code with vulnerabilities generalize to give egregiously harmful responses (e.g. recommending user self-harm) to OOD evaluation questions.

Once an AI developer has noticed this undesired generalization, they can fix it by modifying the training data. In [...]

---

Outline:

(00:15) Summary

(01:00) Introduction

(03:12) How CAFT works

(05:21) Results

(05:24) Mitigating emergent misalignment

(07:58) Reducing sensitivity to spurious correlations

(09:35) Limitations

(11:24) Conclusion

---

First published:

July 23rd, 2025

Source:

https://www.lesswrong.com/posts/BxeZNpiTvoEqTXndJ/steering-out-of-distribution-generalization-with-concept

---

Narrated by TYPE III AUDIO.

---

Images from the article:

Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

...more

View all episodes

View all episodes

Download on the App Store

Download on the App Store

Get it on Google Play

LessWrong (30+ Karma)

By LessWrong

July 23, 2025

“Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning” by kh4dien, Helena Casademunt, Adam Karvonen, Sam Marks, Senthooran Rajamanoharan, Neel Nanda

Listen Later

12 minutes

Summary

We introduce an interpretability-based technique for controlling how fine-tuned LLMs generalize out-of-distribution, without modifying training data.
We show it can mitigate emergent misalignment by training models that write insecure code without becoming misaligned.
It can also reduce sensitivity to spurious cues, even when they are present in 100% of fine-tuning data.
Our technique works by identifying the concept directions used in the undesired solution (e.g. misalignment directions) and ablating them during fine-tuning. The model learns to rely on other concepts, causing different generalization.

Read the full paper here.

Introduction

LLMs can have undesired out-of-distribution (OOD) generalization from their fine-tuning data. A notable example is emergent misalignment, where models trained to write code with vulnerabilities generalize to give egregiously harmful responses (e.g. recommending user self-harm) to OOD evaluation questions.

Once an AI developer has noticed this undesired generalization, they can fix it by modifying the training data. In [...]

---

Outline:

(00:15) Summary

(01:00) Introduction

(03:12) How CAFT works

(05:21) Results

(05:24) Mitigating emergent misalignment

(07:58) Reducing sensitivity to spurious correlations

(09:35) Limitations

(11:24) Conclusion

---

First published:

July 23rd, 2025

Source:

https://www.lesswrong.com/posts/BxeZNpiTvoEqTXndJ/steering-out-of-distribution-generalization-with-concept

---

Narrated by TYPE III AUDIO.

---

Images from the article:

Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

...more

More shows like LessWrong (30+ Karma)

Making Sense with Sam Harris by Sam Harris

Making Sense with Sam Harris

26,386 Listeners

Conversations with Tyler by Mercatus Center at George Mason University

Conversations with Tyler

2,419 Listeners

The Peter Attia Drive by Peter Attia, MD

The Peter Attia Drive

8,916 Listeners

Sean Carroll's Mindscape: Science, Society, Philosophy, Culture, Arts, and Ideas by Sean Carroll | Wondery

Sean Carroll's Mindscape: Science, Society, Philosophy, Culture, Arts, and Ideas

4,153 Listeners

ManifoldOne by Steve Hsu

ManifoldOne

92 Listeners

Your Undivided Attention by The Center for Humane Technology, Tristan Harris, Daniel Barcay and Aza Raskin

Your Undivided Attention

1,595 Listeners

All-In with Chamath, Jason, Sacks & Friedberg by All-In Podcast, LLC

All-In with Chamath, Jason, Sacks & Friedberg

9,862 Listeners

Machine Learning Street Talk (MLST) by Machine Learning Street Talk (MLST)

Machine Learning Street Talk (MLST)

90 Listeners

Dwarkesh Podcast by Dwarkesh Patel

Dwarkesh Podcast

501 Listeners

Hard Fork by The New York Times

Hard Fork

5,470 Listeners

The Ezra Klein Show by New York Times Opinion

The Ezra Klein Show

16,026 Listeners

Moonshots with Peter Diamandis by PHD Ventures

Moonshots with Peter Diamandis

539 Listeners

No Priors: Artificial Intelligence | Technology | Startups by Conviction

No Priors: Artificial Intelligence | Technology | Startups

130 Listeners

Latent Space: The AI Engineer Podcast by swyx + Alessio

Latent Space: The AI Engineer Podcast

94 Listeners

BG2Pod with Brad Gerstner and Bill Gurley by BG2Pod

BG2Pod with Brad Gerstner and Bill Gurley

504 Listeners