Cover Image

Immunization against harmful fine-tuning attacks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Rosati, Domenic, Wehner, Jan, Williams, Kai, Bartoszcze, Łukasz, Batzner, Jan, Sajjad, Hassan, Rudzicz, Frank
Format:	Preprint
Published:	2024
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Representation Noising: A Defence Mechanism Against Harmful Finetuning
by: Rosati, Domenic, et al.
Published: (2024)

Evaluating Defences against Unsafe Feedback in RLHF
by: Rosati, Domenic, et al.
Published: (2024)

Resolving Lexical Bias in Model Editing
by: Rizwan, Hammad, et al.
Published: (2024)

Dependency Parsing is More Parameter-Efficient with Normalization
by: Gajo, Paolo, et al.
Published: (2025)

Long-form evaluation of model editing
by: Rosati, Domenic, et al.
Published: (2024)

LLMs Underperform Graph-Based Parsers on Supervised Relation Extraction for Complex Graphs
by: Gajo, Paolo, et al.
Published: (2026)

One Persona, Many Cues, Different Results: How Sociodemographic Cues Impact LLM Personalization
by: Weeber, Franziska, et al.
Published: (2026)

Sycophancy Claims about Language Models: The Missing Human-in-the-Loop
by: Batzner, Jan, et al.
Published: (2025)

Limits of Convergence-Rate Control for Open-Weight Safety
by: Rosati, Domenic, et al.
Published: (2026)

Semantic Consistency for Assuring Reliability of Large Language Models
by: Raj, Harsh, et al.
Published: (2023)

GermanPartiesQA: Benchmarking Commercial Large Language Models and AI Companions for Political Alignment and Sycophancy
by: Batzner, Jan, et al.
Published: (2024)

Understanding Language Model Circuits through Knowledge Editing
by: Ge, Huaizhi, et al.
Published: (2024)

How Well Can Knowledge Edit Methods Edit Perplexing Knowledge?
by: Ge, Huaizhi, et al.
Published: (2024)

Improving Consistency in Large Language Models through Chain of Guidance
by: Raj, Harsh, et al.
Published: (2025)

The GPT-WritingPrompts Dataset: A Comparative Analysis of Character Portrayal in Short Stories
by: Huang, Xi Yu, et al.
Published: (2024)

Auxiliary Knowledge-Induced Learning for Automatic Multi-Label Medical Document Classification
by: Wang, Xindi, et al.
Published: (2024)

Scenarios and Approaches for Situated Natural Language Explanations
by: Qiu, Pengshuo, et al.
Published: (2024)

Exploring the features used for summary evaluation by Human and GPT
by: Sadeghi, Zahra, et al.
Published: (2025)

Consistency in Language Models: Current Landscape, Challenges, and Future Directions
by: Novikova, Jekaterina, et al.
Published: (2025)

Response-free item difficulty modelling for multiple-choice items with fine-tuned transformers: Component-wise representation and multi-task learning
by: Netík, Jan, et al.
Published: (2026)

Library Learning Doesn't: The Curious Case of the Single-Use "Library"
by: Berlot-Attwell, Ian, et al.
Published: (2024)

Multi-stage Retrieve and Re-rank Model for Automatic Medical Coding Recommendation
by: Wang, Xindi, et al.
Published: (2024)

LLM Library Learning Fails: A LEGO-Prover Case Study
by: Berlot-Attwell, Ian, et al.
Published: (2025)

Whose Personae? Synthetic Persona Experiments in LLM Research and Pathways to Transparency
by: Batzner, Jan, et al.
Published: (2025)

Can adversarial attacks by large language models be attributed?
by: Cebrian, Manuel, et al.
Published: (2024)

LLM-Generated Black-box Explanations Can Be Adversarially Helpful
by: Ajwani, Rohan, et al.
Published: (2024)

Show, Don't Tell: Uncovering Implicit Character Portrayal using LLMs
by: Jaipersaud, Brandon, et al.
Published: (2024)

Complexity-aware fine-tuning
by: Goncharov, Andrey, et al.
Published: (2025)

Temporal fine-tuning for early risk detection
by: Thompson, Horacio, et al.
Published: (2025)

Graph-tree Fusion Model with Bidirectional Information Propagation for Long Document Classification
by: Roy, Sudipta Singha, et al.
Published: (2024)

Labeling supervised fine-tuning data with the scaling law
by: Kong, Huanjun
Published: (2024)

Understanding Syntactic Generalization in Structure-inducing Language Models
by: Arps, David, et al.
Published: (2025)

Discovering Salient Neurons in Deep NLP Models
by: Durrani, Nadir, et al.
Published: (2022)

Quantifying the Capabilities of LLMs across Scale and Precision
by: Badshah, Sher, et al.
Published: (2024)

Interpreting the Effects of Quantization on LLMs
by: Singh, Manpreet, et al.
Published: (2025)

Understanding the effects of language-specific class imbalance in multilingual fine-tuning
by: Jung, Vincent, et al.
Published: (2024)

Improving LLM-based Ontology Matching with fine-tuning on synthetic data
by: Sousa, Guilherme, et al.
Published: (2025)

Plug and Play with Prompts: A Prompt Tuning Approach for Controlling Text Generation
by: Ajwani, Rohan Deepak, et al.
Published: (2024)

Retention analysis of edited knowledge after fine-tuning
by: Wen, Fufang, et al.
Published: (2025)

Replaying pre-training data improves fine-tuning
by: Kotha, Suhas, et al.
Published: (2026)