mlsanityData to 7 Oct 2026

TrustLLM: Trustworthiness in Large Language Models

arXiv 2401.05561 ↗First posted 10 Jan 2024cs.CLcited by 280

Not on the map. Why?

Cited by 59 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Large language models (LLMs), exemplified by ChatGPT, have gained considerable attention for their excellent natural language processing capabilities. Nonetheless, these LLMs present many challenges, particularly in the realm of trustworthiness. Therefore, ensuring the trustworthiness of LLMs emerges as an important topic. This paper introduces TrustLLM, a comprehensive study of trustworthiness in LLMs, including principles for different dimensions of trustworthiness, established benchmark, evaluation, and analysis of trustworthiness for mainstream LLMs, and discussion of open challenges and future directions. Specifically, we first propose a set of principles for trustworthy LLMs that span eight different dimensions. Based on these principles, we further establish a benchmark across six dimensions including truthfulness, safety, fairness, robustness, privacy, and machine ethics. We then present a study evaluating 16 mainstream LLMs in TrustLLM, consisting of over 30 datasets. Our findings firstly show that in general trustworthiness and utility (i.e., functional effectiveness) are positively related. Secondly, our observations reveal that proprietary LLMs generally outperform most open-source counterparts in terms of trustworthiness, raising concerns about the potential risks of widely accessible open-source LLMs. However, a few open-source LLMs come very close to proprietary ones. Thirdly, it is important to note that some LLMs may be overly calibrated towards exhibiting trustworthiness, to the extent that they compromise their utility by mistakenly treating benign prompts as harmful and consequently not responding. Finally, we emphasize the importance of ensuring transparency not only in the models themselves but also in the technologies that underpin trustworthiness. Knowing the specific trustworthy technologies that have been employed is crucial for analyzing their effectiveness.

Key facts. Cited by 280 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Jan 2024.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 134; 2025: 91; 2026: 55.

280 papers.

Sort:

By area:

  1. 2024Tulu 3: Pushing Frontiers in Open Language Model Post-Trainingcited by 988
  2. 2024Large Language Models: A Surveycited by 506
  3. 2024JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Modelscited by 494
  4. 2024Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Modelscited by 467
  5. 2024MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmarkcited by 362
  6. 2024Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothingcited by 341
  7. 2024A Survey on Knowledge Distillation of Large Language Modelscited by 276
  8. 2024SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusalcited by 224
  9. 2024OR-Bench: An Over-Refusal Benchmark for Large Language Modelscited by 222
  10. 2024Security and Privacy Challenges of Large Language Models: A Surveycited by 179
  11. 2024An Introduction to Vision-Language Modelingcited by 175
  12. 2024DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Modelscited by 143
38 more
  1. 2024AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Expertscited by 126
  2. 2024ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agentscited by 126
  3. 2024Empowering Biomedical Discovery with AI Agentscited by 117
  4. 2024Automatic and Universal Prompt Injection Attacks against Large Language Modelscited by 112
  5. 2025X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agentscited by 112
  6. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 110
  7. 2024ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidencecited by 109
  8. 2024From Matching to Generation: A Survey on Generative Information Retrievalcited by 89
  9. 2024Revolutionizing Finance with LLMs: An Overview of Applications and Insightscited by 88
  10. 2024FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"cited by 85
  11. 2024Trustworthiness in Retrieval-Augmented Generation Systems: A Surveycited by 83
  12. 2024SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Modelcited by 82
  13. 2024Foundation Model for Advancing Healthcare: Challenges, Opportunities, and Future Directionscited by 77
  14. 2024Catastrophic Failure of LLM Unlearning via Quantizationcited by 76
  15. 2024SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safetycited by 75
  16. 2024Safety of Multimodal Large Language Models on Images and Textscited by 70
  17. 2024CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Modelscited by 64
  18. 2024Get my drift? Catching LLM Task Drift with Activation Deltascited by 61
  19. 2024Introducing v0.5 of the AI Safety Benchmark from MLCommonscited by 60
  20. 2024Knowledge Circuits in Pretrained Transformerscited by 60
  21. 2024Fairness in Large Language Models: A Taxonomic Surveycited by 57
  22. 2024Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluationcited by 56
  23. 2024Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compressioncited by 54
  24. 2024What Makes and Breaks Safety Fine-tuning? A Mechanistic Studycited by 54
  25. 2024MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Modelscited by 51
  26. 2024On Large Language Model Continual Unlearningcited by 51
  27. 2024Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Modelscited by 48
  28. 2024ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluationcited by 46
  29. 2024Thinking Fair and Slow: On the Efficacy of Structured Prompts for Debiasing Language Modelscited by 44
  30. 2024The Perfect Blend: Redefining RLHF with Mixture of Judgescited by 43
  31. 2025ChemAgent: Self-updating Library in Large Language Models Improves Chemical Reasoningcited by 41
  32. 2024Voice Jailbreak Attacks Against GPT-4ocited by 39
  33. 2024Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characterscited by 39
  34. 2025Exploring Criteria of Loss Reweighting to Enhance LLM Unlearningcited by 39
  35. 2024Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studiescited by 38
  36. 2024Assessment of Multimodal Large Language Models in Alignment with Human Valuescited by 36
  37. 2024FairMT-Bench: Benchmarking Fairness for Multi-turn Dialogue in Conversational LLMscited by 36
  38. 2024Diff-eRank: A Novel Rank-Based Metric for Evaluating Large Language Modelscited by 35

50 most cited of 280 All 280 (JSON)