mlsanityData to 14 Oct 2026

LoRA-Guard: Parameter-Efficient Guardrail Adaptation for Content Moderation of Large Language Models

arXiv 2407.02987 ↗First posted 3 Jul 2024cs.LG cs.AI cs.CLcited by 7

On the map: LLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks

also in 1 more
Abstract (arXiv)

Guardrails have emerged as an alternative to safety alignment for content moderation of large language models (LLMs). Existing model-based guardrails have not been designed for resource-constrained computational portable devices, such as mobile phones, more and more of which are running LLM-based applications locally. We introduce LoRA-Guard, a parameter-efficient guardrail adaptation method that relies on knowledge sharing between LLMs and guardrail models. LoRA-Guard extracts language features from the LLMs and adapts them for the content moderation task using low-rank adapters, while a dual-path design prevents any performance degradation on the generative task. We show that LoRA-Guard outperforms existing approaches with 100-1000x lower parameter overhead while maintaining accuracy, enabling on-device content moderation.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Placed in Safety alignment and jailbreak attacks, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 48 of its 83 references that are in the map. First posted on arXiv 3 Jul 2024.

Builds on

48 of 83 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations10 Oct
  2. 2023Baseline Defenses for Adversarial Attacks Against Aligned Language Models1 Sep
  3. 2023GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher12 Aug

Other references · 45

  1. 2017Attention Is All You Needcited by 60,361
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  5. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  6. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  7. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  8. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  9. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  10. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  11. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  12. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
33 more
  1. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,218
  2. 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,651
  3. 2023Jailbreaking Black Box Large Language Models in Twenty Queriescited by 1,420
  4. 2023Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversationscited by 1,207
  5. 2021Towards a Unified View of Parameter-Efficient Transfer Learningcited by 872
  6. 2022Ignore Previous Prompt: Attack Techniques For Language Modelscited by 832
  7. 2023An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuningcited by 639
  8. 2024TinyLlama: An Open-Source Small Language Modelcited by 618
  9. 2024How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMscited by 573
  10. 2023GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Promptscited by 560
  11. 2021Datasets: A Community Library for Natural Language Processingcited by 530
  12. 2024Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attackscited by 486
  13. 2023Detecting Language Model Attacks with Perplexitycited by 431
  14. 2013DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognitioncited by 424
  15. 2024Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attackcited by 390
  16. 2023NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Railscited by 365
  17. 2022A Holistic Approach to Undesired Content Detection in the Real Worldcited by 356
  18. 2023Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attackscited by 278
  19. 2023The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learningcited by 257
  20. 2023LLM Self Defense: By Self Examination, LLMs Know They Are Being Trickedcited by 244
  21. 2023ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversationcited by 231
  22. 2022LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learningcited by 230
  23. 2024ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMscited by 216
  24. 2023Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulationcited by 214
  25. 2023Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuningcited by 173
  26. 2023RAIN: Your Language Models Can Align Themselves without Finetuningcited by 157
  27. 2024Attacks, Defenses and Evaluations for LLM Conversation Safety: A Surveycited by 130
  28. 2021Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translationcited by 74
  29. 2023Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competitioncited by 68
  30. 2023The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensivenesscited by 67
  31. 2024All in How You Ask for It: Simple Black-Box Method for Jailbreak Attackscited by 32
  32. 2024Defending Jailbreak Prompts via In-Context Adversarial Gamecited by 29
  33. 2024LLMGuard: Guarding Against Unsafe LLM Behaviorcited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 2.

7 papers.

  1. 2025No Free Lunch with Guardrailscited by 11
  2. 2025Shape it Up! Restoring LLM Safety during Finetuningcited by 11
  3. 2025Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLMcited by 9
  4. 2025Attention-Aware GNN-based Input Defense against Multi-Turn LLM Jailbreakcited by 2
  5. 2026ExpGuard: LLM Content Moderation in Specialized Domainscited by 2
  6. 2024Bridging Today and the Future of Humanity: AI Safety in 2024 and Beyondcited by 1
  7. 2026PolicyShiftGuard: Benchmarking and Improving Policy-Adaptive Image Guardrailscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025OpenGuardrails: A Configurable, Unified, and Scalable Guardrails Platform for Large Language Models
  2. 2025X-Guard: Multilingual Guard Agent for Content Moderation
  3. 2026kNNGuard: Turning LLM Hidden Activations into a Training-Free Configurable Guardrail
  4. 2025SafeRoute: Adaptive Model Selection for Efficient and Accurate Safety Guardrails in Large Language Models
  5. 2024LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters
  6. 2024On Calibration of LLM-based Guard Models for Reliable Content Moderation
  7. 2024RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content
  8. 2025Unified Multi-Task Learning & Model Fusion for Efficient Language Model Guardrailing