mlsanityData to 7 Oct 2026

SLM as Guardian: Pioneering AI Safety with Small Language Models

arXiv 2405.19795 ↗First posted 30 May 2024cs.CL cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

Most prior safety research of large language models (LLMs) has focused on enhancing the alignment of LLMs to better suit the safety requirements of humans. However, internalizing such safeguard features into larger models brought challenges of higher training cost and unintended degradation of helpfulness. To overcome such challenges, a modular approach employing a smaller LLM to detect harmful user queries is regarded as a convenient solution in designing LLM-based system with safety requirements. In this paper, we leverage a smaller LLM for both harmful query detection and safeguard response generation. We introduce our safety requirements and the taxonomy of harmfulness categories, and then propose a multi-task learning mechanism fusing the two tasks into a single model. We demonstrate the effectiveness of our approach, providing on par or surpassing harmful query detection and safeguard response performance compared to the publicly available LLMs.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 34 of its 56 references that are in the map. First posted on arXiv 30 May 2024.

Builds on

34 of 56 references.

References · 34

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  5. 2017Deep reinforcement learning from human preferencescited by 3,846
  6. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  7. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  8. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  9. 2019Fine-Tuning Language Models from Human Preferencescited by 2,124
  10. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,413
  11. 2023Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversationscited by 1,124
  12. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,116
22 more
  1. 2023LIMA: Less Is More for Alignmentcited by 1,080
  2. 2023OpenAssistant Conversations -- Democratizing Large Language Model Alignmentcited by 712
  3. 2023Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizescited by 710
  4. 2023GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Ciphercited by 401
  5. 2023Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrationscited by 401
  6. 2022Unnatural Instructions: Tuning Language Models with (Almost) No Human Laborcited by 395
  7. 2020Multi-Task Learning with Deep Neural Networks: A Surveycited by 374
  8. 2023Certifying LLM Safety against Adversarial Promptingcited by 248
  9. 2020ONION: A Simple and Effective Defense Against Textual Backdoor Attackscited by 231
  10. 2022Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizerscited by 204
  11. 2022On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoningcited by 191
  12. 2023Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attackscited by 189
  13. 2024AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Expertscited by 126
  14. 2022Explanations from Large Language Models Make Small Reasoners Bettercited by 123
  15. 2023Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilitiescited by 76
  16. 2021What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained Transformerscited by 75
  17. 2022Complementary Explanations for Effective In-Context Learningcited by 71
  18. 2020BEEP! Korean Corpus of Online News Comments for Toxic Speech Detectioncited by 39
  19. 2020KorNLI and KorSTS: New Benchmark Datasets for Korean Natural Language Understandingcited by 37
  20. 2023SQuARe: A Large-Scale Dataset of Sensitive Questions and Acceptable Responses Created Through Human-Machine Collaborationcited by 13
  21. 2022APEACH: Attacking Pejorative Expressions with Analysis on Crowd-Generated Hate Speech Evaluation Datasetscited by 8
  22. 2019Machines Getting with the Program: Understanding Intent Arguments of Non-Canonical Directivescited by 4

Built on by

Cited by year (2026 to 7 Oct)

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

7 papers.

  1. 2024A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthinesscited by 125
  2. 2025A Survey on Trustworthy LLM Agents: Threats and Countermeasurescited by 93
  3. 2025LeechHijack: Covert Computational Resource Exploitation in Intelligent Agent Systemscited by 5
  4. 2026VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systemscited by 5
  5. 2026GLiGuard: Schema-Conditioned Classification for LLM Safeguardcited by 4
  6. 2026Enhancing Safety of Large Language Models via Embedding Space Separationcited by 2
  7. 2026Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMscited by 1