Cover Image

Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Casademunt, Helena, Juang, Caden, Karvonen, Adam, Marks, Samuel, Rajamanoharan, Senthooran, Nanda, Neel
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models
by: Ferrando, Javier, et al.
Published: (2024)

Thought Branches: Interpreting LLM Reasoning Requires Resampling
by: Macar, Uzay, et al.
Published: (2025)

Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning
by: Minder, Julian, et al.
Published: (2025)

Censored LLMs as a Natural Testbed for Secret Knowledge Elicitation
by: Casademunt, Helena, et al.
Published: (2026)

Convergent Linear Representations of Emergent Misalignment
by: Soligo, Anna, et al.
Published: (2025)

Chain-of-Thought Reasoning In The Wild Is Not Always Faithful
by: Arcuschin, Iván, et al.
Published: (2025)

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks
by: Karvonen, Adam, et al.
Published: (2024)

Robustly Improving LLM Fairness in Realistic Settings via Interpretability
by: Karvonen, Adam, et al.
Published: (2025)

Model Organisms for Emergent Misalignment
by: Turner, Edward, et al.
Published: (2025)

Are Sparse Autoencoders Useful? A Case Study in Sparse Probing
by: Kantamneni, Subhash, et al.
Published: (2025)

Emergent Misalignment is Easy, Narrow Misalignment is Hard
by: Soligo, Anna, et al.
Published: (2026)

Simple Mechanistic Explanations for Out-Of-Context Reasoning
by: Wang, Atticus, et al.
Published: (2025)

How Well Do Models Follow Their Constitutions?
by: Jakkli, Arya, et al.
Published: (2026)

Subliminal Learning Is Steering Vector Distillation
by: Blank, Camila, et al.
Published: (2026)

Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2
by: Lieberum, Tom, et al.
Published: (2024)

Learning Multi-Level Features with Matryoshka Sparse Autoencoders
by: Bussmann, Bart, et al.
Published: (2025)

Improving Dictionary Learning with Gated Sparse Autoencoders
by: Rajamanoharan, Senthooran, et al.
Published: (2024)

Towards eliciting latent knowledge from LLMs with mechanistic interpretability
by: Cywiński, Bartosz, et al.
Published: (2025)

Steering Evaluation-Aware Language Models to Act Like They Are Deployed
by: Hua, Tim Tian, et al.
Published: (2025)

Dense SAE Latents Are Features, Not Bugs
by: Sun, Xiaoqing, et al.
Published: (2025)

Explorations of Self-Repair in Language Models
by: Rushing, Cody, et al.
Published: (2024)

Towards Best Practices of Activation Patching in Language Models: Metrics and Methods
by: Zhang, Fred, et al.
Published: (2023)

Eliciting Secret Knowledge from Language Models
by: Cywiński, Bartosz, et al.
Published: (2025)

Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models
by: Karvonen, Adam, et al.
Published: (2024)

Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers
by: Karvonen, Adam, et al.
Published: (2025)

Improving Large Language Models with Concept-Aware Fine-Tuning
by: Chen, Michael K., et al.
Published: (2025)

Real-Time Detection of Hallucinated Entities in Long-Form Generation
by: Obeso, Oscar, et al.
Published: (2025)

Thought Anchors: Which LLM Reasoning Steps Matter?
by: Bogdan, Paul C., et al.
Published: (2025)

Understanding Reasoning in Thinking Language Models via Steering Vectors
by: Venhoff, Constantin, et al.
Published: (2025)

FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models
by: Weng, Zixuan, et al.
Published: (2026)

What's the plan? Metrics for implicit planning in LLMs and their application to rhyme generation and question answering
by: Maar, Jim, et al.
Published: (2026)

Scaling sparse feature circuit finding for in-context learning
by: Kharlapenko, Dmitrii, et al.
Published: (2025)

Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals
by: Clymer, Joshua, et al.
Published: (2024)

Beyond Linear Steering: Unified Multi-Attribute Control for Language Models
by: Oozeer, Narmeen, et al.
Published: (2025)

Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences
by: Minder, Julian, et al.
Published: (2025)

Accidental Vulnerability: Factors in Fine-Tuning that Shift Model Safeguards
by: Pandey, Punya Syon, et al.
Published: (2025)

Stabilizing LLM Supervised Fine-Tuning via Explicit Distributional Control
by: Wang, Xinyu, et al.
Published: (2026)

Out-of-Distribution Detection using Synthetic Data Generation
by: Abbas, Momin, et al.
Published: (2025)

Data Cartography for Detecting Memorization Hotspots and Guiding Data Interventions in Generative Models
by: Patel, Laksh, et al.
Published: (2025)

Confidence Regulation Neurons in Language Models
by: Stolfo, Alessandro, et al.
Published: (2024)