Cover Image

Towards Understanding and Improving Refusal in Compressed Models via Mechanistic Interpretability

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chhabra, Vishnu Kabir, Khalili, Mohammad Mahdi
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

Neuroplasticity and Corruption in Model Mechanisms: A Case Study Of Indirect Object Identification
by: Chhabra, Vishnu Kabir, et al.
Published: (2025)

On the transferability of Sparse Autoencoders for interpreting compressed models
by: Gupte, Suchit, et al.
Published: (2025)

Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training
by: Yuan, Youliang, et al.
Published: (2024)

AbsTopK: Rethinking Sparse Autoencoders For Bidirectional Features
by: Zhu, Xudong, et al.
Published: (2025)

From Emergence to Control: Probing and Modulating Self-Reflection in Language Models
by: Zhu, Xudong, et al.
Published: (2025)

Toward a Theory of Generalizability in LLM Mechanistic Interpretability Research
by: Trott, Sean
Published: (2025)

Revisiting the Effectiveness of LLM Pruning for Test-Time Scaling
by: Monjur, Ocean, et al.
Published: (2026)

Less Diverse, Less Safe: The Indirect But Pervasive Risk of Test-Time Scaling in Large Language Models
by: Nahin, Shahriar Kabir, et al.
Published: (2025)

Mechanistic Interpretability Needs Philosophy
by: Williams, Iwan, et al.
Published: (2025)

Mechanistic Interpretability of Emotion Inference in Large Language Models
by: Tak, Ala N., et al.
Published: (2025)

Learning to Refuse: Towards Mitigating Privacy Risks in LLMs
by: Liu, Zhenhua, et al.
Published: (2024)

Intrinsic Self-Correction in LLMs: Towards Explainable Prompting via Mechanistic Interpretability
by: Lee, Yu-Ting, et al.
Published: (2025)

Mechanistic Indicators of Understanding in Large Language Models
by: Beckmann, Pierre, et al.
Published: (2025)

What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal
by: Cheng, Stephen, et al.
Published: (2026)

HyperDAS: Towards Automating Mechanistic Interpretability with Hypernetworks
by: Sun, Jiuding, et al.
Published: (2025)

Mechanistic Interpretability of Socio-Political Frames in Language Models
by: Asghari, Hadi, et al.
Published: (2025)

FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning
by: Zhang, Zhehao, et al.
Published: (2025)

Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinations
by: Yu, Lei, et al.
Published: (2024)

How Post-Training Reshapes LLMs: A Mechanistic View on Knowledge, Truthfulness, Refusal, and Confidence
by: Du, Hongzhe, et al.
Published: (2025)

RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models
by: Muhamed, Aashiq, et al.
Published: (2025)

Learn to Refuse: Making Large Language Models More Controllable and Reliable through Knowledge Scope Limitation and Refusal Mechanism
by: Cao, Lang
Published: (2023)

Toward Mechanistic Explanation of Deductive Reasoning in Language Models
by: Maltoni, Davide, et al.
Published: (2025)

Mechanistic Interpretability of Cognitive Complexity in LLMs via Linear Probing using Bloom's Taxonomy
by: Raimondi, Bianca, et al.
Published: (2026)

DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders
by: Wang, Xu, et al.
Published: (2026)

Towards Ethical Multi-Agent Systems of Large Language Models: A Mechanistic Interpretability Perspective
by: Lee, Jae Hee, et al.
Published: (2025)

Think Before Refusal : Triggering Safety Reflection in LLMs to Mitigate False Refusal Behavior
by: Si, Shengyun, et al.
Published: (2025)

Refusal Steering: Fine-grained Control over LLM Refusal Behaviour for Sensitive Topics
by: García-Ferrero, Iker, et al.
Published: (2025)

Linearly Decoding Refused Knowledge in Aligned Language Models
by: Shrivastava, Aryan, et al.
Published: (2025)

OR-Bench: An Over-Refusal Benchmark for Large Language Models
by: Cui, Justin, et al.
Published: (2024)

Measuring and Eliminating Refusals in Military Large Language Models
by: FitzGerald, Jack, et al.
Published: (2026)

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective
by: Chandna, Bhavik, et al.
Published: (2025)

Different Paths to Harmful Compliance: Behavioral Side Effects and Mechanistic Divergence Across LLM Jailbreaks
by: Kabir, Md Rysul, et al.
Published: (2026)

How Well Do LLMs Understand Tunisian Arabic?
by: Mahdi, Mohamed
Published: (2025)

Can LLMs Refuse Questions They Do Not Know? Measuring Knowledge-Aware Refusal in Factual Tasks
by: Pan, Wenbo, et al.
Published: (2025)

Gender Encoding Patterns in Pretrained Language Model Representations
by: Zakizadeh, Mahdi, et al.
Published: (2025)

Mechanistic Interpretability of GPT-like Models on Summarization Tasks
by: Mishra, Anurag
Published: (2025)

Binary Autoencoder for Mechanistic Interpretability of Large Language Models
by: Cho, Hakaze, et al.
Published: (2025)

RepIt: Steering Language Models with Concept-Specific Refusal Vectors
by: Siu, Vincent, et al.
Published: (2025)

Refusal Behavior in Large Language Models: A Nonlinear Perspective
by: Hildebrandt, Fabian, et al.
Published: (2025)

Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability
by: Raimondi, Bianca, et al.
Published: (2025)