No article text was recorded for this version.
safety-preserving fine-tuning
Version 1 of 124 papers32 conceptsfrozen 2026-10-04
Papers in this version
- Blog: AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin
- Blog: Safety Alignment of Large Language Models via Contrasting Safe and Harmful Distributions
- Blog: Superficial Safety Alignment Hypothesis
- Blog: Safety Layers in Aligned Large Language Models: The Key to LLM Security
- Blog: Extended Abstract: Probing-Guided Parameter-Efficient Fine-Tuning for Balancing Linguistic Adaptation and Safety in LLM-based Social Influence Systems
- Blog: Rethinking Safety in LLM Fine-tuning: An Optimization Perspective
- Blog: A safety realignment framework via subspace-oriented model fusion for large language models
- Blog: Understanding and Enhancing Safety Mechanisms of LLMs via Safety-Specific Neuron
- Blog: What Makes and Breaks Safety Fine-tuning? A Mechanistic Study
- Blog: Safe LoRA: The Silver Lining of Reducing Safety Risks when Finetuning Large Language Models
- Blog: Multilingual Safety Alignment Via Sparse Weight Editing
- Blog: Safety-Utility Conflicts Are Not Global: Surgical Alignment via Head-Level Diagnosis
- Blog: Safety-Anchored Fine-Tuning: Diagnosing and Preventing Safety Collapse in Large Language Models via Adversarial Alignment Anchoring
- Blog: Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates
- Blog: A Guardrail for Safety Preservation: When Safety-Sensitive Subspace Meets Harmful-Resistant Null-Space
- Blog: Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense
- Blog: Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language Models
- Blog: Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets
- Blog: PaCE: Parsimonious Concept Engineering for Large Language Models
- Blog: SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signals
- Blog: SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging
- Blog: Improve Safety Training of Large Language Models with Safety-Critical Singular Vectors Localization
- Blog: Safety Anchor: Defending Harmful Fine-tuning via Geometric Bottlenecks
- Blog: Safety at One Shot: Patching Fine-Tuned LLMs with A Single Instance
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_safety_preserving_fine_tuning_a0c93f73,
title = {safety-preserving fine-tuning},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/safety-preserving-fine-tuning/rdr_a0c93f73dbc5480eb78463e6eb83abae},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_safety_preserving_fine_tuning_a0c93f73_v1,
title = {safety-preserving fine-tuning},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/safety-preserving-fine-tuning/rdr_a0c93f73dbc5480eb78463e6eb83abae/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}