mlsanityData to 14 Oct 2026

Trust-Oriented Adaptive Guardrails for Large Language Models

arXiv 2408.08959 ↗First posted 16 Aug 2024cs.AI cs.CLcited by 8

On the map: LLM safety and security → Safety alignment, refusal and guardrails

Abstract (arXiv)

Guardrail, an emerging mechanism designed to ensure that large language models (LLMs) align with human values by moderating harmful or toxic responses, requires a sociotechnical approach in their design. This paper addresses a critical issue: existing guardrails lack a well-founded methodology to accommodate the diverse needs of different user groups, particularly concerning access rights. Supported by trust modeling (primarily on `social' aspect) and enhanced with online in-context learning via retrieval-augmented generation (on `technical' aspect), we introduce an adaptive guardrail mechanism, to dynamically moderate access to sensitive content based on user trust metrics. User trust metrics, defined as a novel combination of direct interaction trust and authority-verified trust, enable the system to precisely tailor the strictness of content moderation by aligning with the user's credibility and the specific context of their inquiries. Our empirical evaluation demonstrates the effectiveness of the adaptive guardrail in meeting diverse user needs, outperforming existing guardrails while securing sensitive information and precisely managing potentially hazardous content through a context-aware knowledge base. To the best of our knowledge, this work is the first to introduce trust-oriented concept into a guardrail system, offering a scalable solution that enriches the discourse on ethical deployment for next-generation LLM service.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Placed in Safety alignment, refusal and guardrails, one of 12 directions in LLM safety and security. Builds on 19 of its 45 references that are in the map. First posted on arXiv 16 Aug 2024.

Builds on

19 of 45 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Building Guardrails for Large Language Models2 Feb

Other references · 18

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  3. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 3,104
  4. 2024HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusalcited by 1,429
  5. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,392
  6. 2023Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversationscited by 1,207
  7. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,195
  8. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 452
  9. 2023NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Railscited by 365
  10. 2024Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedbackcited by 100
  11. 2023A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validationcited by 93
  12. 2023Plug in the Safety Chip: Enforcing Constraints for LLM-driven Robot Agentscited by 69
6 more
  1. 2023In-Context Learning Learns Label Relationships but Is Not Conventional Learningcited by 51
  2. 2024LLM Agents in Interaction: Measuring Personality Consistency and Linguistic Alignment in Interacting Populations of Large Language Modelscited by 33
  3. 2024The Role of LLMs in Sustainable Smart Cities: Applications, Challenges, and Future Directionscited by 9
  4. 2024Similar Data Points Identification with LLM: A Human-in-the-loop Strategy Using Summarization and Hidden State Insightscited by 9
  5. 2018Trust-based Multi-Robot Symbolic Motion Planning with a Human-in-the-Loopcited by 4
  6. 2019Reasoning about Cognitive Trust in Stochastic Multiagent Systemscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 3.

8 papers.

  1. 2025SoK: Evaluating Jailbreak Guardrails for Large Language Modelscited by 21
  2. 2025Enhancing Robustness of LLM-Driven Multi-Agent Systems through Randomized Smoothingcited by 9
  3. 2025Position: Towards a Responsible LLM-empowered Multi-Agent Systemscited by 8
  4. 2026DeepContext: Stateful Real-Time Detection of Multi-Turn Adversarial Intent Drift in LLMscited by 8
  5. 2025Stop Reducing Responsibility in LLM-Powered Multi-Agent Systems to Local Alignmentcited by 7
  6. 2025FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Modelcited by 1
  7. 2026BARRED: Synthetic Training of Custom Policy Guardrails via Asymmetric Debatecited by 0
  8. 2026PolicyShiftGuard: Benchmarking and Improving Policy-Adaptive Image Guardrailscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Unveiling Trust in Multimodal Large Language Models: Evaluation, Analysis, and Mitigation
  2. 2024Challenges in Guardrailing Large Language Models for Science
  3. 2025Protect: Towards Robust Guardrailing Stack for Trustworthy Enterprise LLM Systems
  4. 2025OpenGuardrails: A Configurable, Unified, and Scalable Guardrails Platform for Large Language Models
  5. 2026Trust The Typical
  6. 2025TrustRAG: Enhancing Robustness and Trustworthiness in Retrieval-Augmented Generation
  7. 2024Safeguarding Large Language Models: A Survey
  8. 2026LLM4Trust: Exploring the Capabilities of Large Language Models for Trust Evaluation