NLP Wiki

User Tools

Site Tools

Trace: • domain_adaptation • scaling_laws • instruction-tuning • semantic_parsing • intelligent_tutor • history_of_ml • dependency_parsing • amr_annotation • hmm • fine-tuning
nlp:llm_safety

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
nlp:llm_safety [2025/05/30 16:49] – jmflanignlp:llm_safety [2026/03/07 22:18] (current) – [Papers] jmflanig
Line 2: Line 2:
  
 ===== Overviews ===== ===== Overviews =====
-  * [[A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation]]+  * [[https://arxiv.org/pdf/2305.11391|Huang et al 2023 - A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation]] 
 +  * [[https://arxiv.org/pdf/2308.05374|Liu et al 2023 - Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment]]
   * [[https://arxiv.org/pdf/2402.09283|Dong et al 2024 - Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey]]   * [[https://arxiv.org/pdf/2402.09283|Dong et al 2024 - Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey]]
-  * [[https://arxiv.org/pdf/2412.17686|Shi et al 2024 - Large Language Model Safety: A Holistic Survey]]+  * **[[https://arxiv.org/pdf/2412.17686|Shi et al 2024 - Large Language Model Safety: A Holistic Survey]]** Great survey 
 +  * [[https://arxiv.org/pdf/2501.17805|2025 - International AI Safety Report]] Safety for AI in general
  
 ===== Papers ===== ===== Papers =====
Line 11: Line 13:
   * [[https://arxiv.org/pdf/2404.12038|Xu et al 2024 - Uncovering Safety Risks in Open-source LLMs through Concept Activation Vector]]   * [[https://arxiv.org/pdf/2404.12038|Xu et al 2024 - Uncovering Safety Risks in Open-source LLMs through Concept Activation Vector]]
   * [[https://arxiv.org/pdf/2404.13208|Wallace et al 2024 - The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions]]   * [[https://arxiv.org/pdf/2404.13208|Wallace et al 2024 - The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions]]
 +  * [[https://arxiv.org/pdf/2508.06601|O'Brien et al 2025 - Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs]]
  
 ===== Jailbraking LLMs ===== ===== Jailbraking LLMs =====
   * **Overviews**   * **Overviews**
-    * [[https://arxiv.org/pdf/2305.11391|https://arxiv.org/pdf/2407.04295|Yi et al 2024 - Jailbreak Attacks and Defenses Against Large Language Models: A Survey]]+    * [[https://arxiv.org/pdf/2407.04295|Yi et al 2024 - Jailbreak Attacks and Defenses Against Large Language Models: A Survey]]
   * [[https://arxiv.org/pdf/2307.02483|Wei et al 2023 - Jailbroken: How Does LLM Safety Training Fail?]]   * [[https://arxiv.org/pdf/2307.02483|Wei et al 2023 - Jailbroken: How Does LLM Safety Training Fail?]]
   * [[https://arxiv.org/pdf/2307.15043.pdf|Zhou et al 2023 - Universal and Transferable Adversarial Attacks   * [[https://arxiv.org/pdf/2307.15043.pdf|Zhou et al 2023 - Universal and Transferable Adversarial Attacks
Line 26: Line 29:
   * [[ml:Mechanistic Interpretability]]   * [[ml:Mechanistic Interpretability]]
   * [[ml:Model Editing and Unlearning|Model Editing]]   * [[ml:Model Editing and Unlearning|Model Editing]]
 +  * [[ml:Trustworthy AI]]
nlp/llm_safety.1748623794.txt.gz · Last modified: 2025/05/30 16:49 by jmflanig
Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki