Cover Image

Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Minder, Julian, Dumas, Clément, Slocum, Stewart, Casademunt, Helena, Holmes, Cameron, West, Robert, Nanda, Neel
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

Believe It or Not: How Deeply do LLMs Believe Implanted Facts?
by: Slocum, Stewart, et al.
Published: (2025)

Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning
by: Casademunt, Helena, et al.
Published: (2025)

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

Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in Transformers
by: Dumas, Clément, et al.
Published: (2024)

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

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

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

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

Controllable Context Sensitivity and the Knob Behind It
by: Minder, Julian, et al.
Published: (2024)

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

Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning
by: Geng, Saibo, et al.
Published: (2023)

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

Tracing Persona Vectors Through LLM Pretraining
by: Moskvoretskii, Viktor, et al.
Published: (2026)

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)

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

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

Activation Scaling for Steering and Interpreting Language Models
by: Stoehr, Niklas, et al.
Published: (2024)

Internal states before wait modulate reasoning patterns
by: Troitskii, Dmitrii, et al.
Published: (2025)

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)

Clear Preferences Leave Traces: Reference Model-Guided Sampling for Preference Learning
by: Diwan, Nirav, et al.
Published: (2025)

Toward Human-Centered Readability Evaluation
by: İlgen, Bahar, et al.
Published: (2025)

Optimizing Readability Using Genetic Algorithms
by: Martinez-Gil, Jorge
Published: (2023)

Exploring Performance Variations in Finetuned Translators of Ultra-Low Resource Languages: Do Linguistic Differences Matter?
by: Gonçalves, Isabel, et al.
Published: (2025)

Improving Task Diversity in Label Efficient Supervised Finetuning of LLMs
by: Arabelly, Abhinav, et al.
Published: (2025)

nnterp: A Standardized Interface for Mechanistic Interpretability of Transformers
by: Dumas, Clément
Published: (2025)

An Open Multilingual System for Scoring Readability of Wikipedia
by: Trokhymovych, Mykola, et al.
Published: (2024)

Prompt-based Learning for Text Readability Assessment
by: Lee, Bruce W., et al.
Published: (2023)

Whisper Finetuning on Nepali Language
by: Rijal, Sanjay, et al.
Published: (2024)

Delta Activations: A Representation for Finetuned Large Language Models
by: Xu, Zhiqiu, et al.
Published: (2025)

Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty
by: Damani, Mehul, et al.
Published: (2025)

Evaluation of Finetuned LLMs in AMR Parsing
by: Ho, Shu Han
Published: (2025)

Hierarchical Ranking Neural Network for Long Document Readability Assessment
by: Zheng, Yurui, et al.
Published: (2025)

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

Building Production-Ready Probes For Gemini
by: Kramár, János, et al.
Published: (2026)

Refusal in Language Models Is Mediated by a Single Direction
by: Arditi, Andy, et al.
Published: (2024)

Alignment Whack-a-Mole : Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models
by: Liu, Xinyue, et al.
Published: (2026)

Continual Learning via Sparse Memory Finetuning
by: Lin, Jessy, et al.
Published: (2025)