mlsanityData to 14 Oct 2026

A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation

arXiv 2305.11391 ↗First posted 19 May 2023cs.AI cs.LGcited by 93

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) have exploded a new heatwave of AI for their ability to engage end-users in human-level conversations with detailed and articulate answers across many knowledge domains. In response to their fast adoption in many industrial applications, this survey concerns their safety and trustworthiness. First, we review known vulnerabilities and limitations of the LLMs, categorising them into inherent issues, attacks, and unintended bugs. Then, we consider if and how the Verification and Validation (V&V) techniques, which have been widely developed for traditional software and deep learning models such as convolutional neural networks as independent processes to check the alignment of their implementations against the specifications, can be integrated and further extended throughout the lifecycle of the LLMs to provide rigorous analysis to the safety and trustworthiness of LLMs and their applications. Specifically, we consider four complementary techniques: falsification and evaluation, verification, runtime monitoring, and regulations and ethical use. In total, 370+ references are considered to support the quick understanding of the safety and trustworthiness issues from the perspective of V&V. While intensive research has been conducted to identify the safety and trustworthiness issues, rigorous yet practical methods are called for to ensure the alignment of LLMs with safety and trustworthiness requirements.

Key facts. Cited by 93 papers in the map (data through 14 Oct 2026). Builds on 224 of its 344 references that are in the map. First posted on arXiv 19 May 2023.

Builds on

224 of 344 references.

References · 224

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  6. 2022Training language models to follow instructions with human feedbackcited by 15,971
  7. 2017Proximal Policy Optimization Algorithmscited by 15,215
  8. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  9. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  10. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  11. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  12. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
38 more
  1. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  5. 2020Scaling Laws for Neural Language Modelscited by 6,586
  6. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  7. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  8. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  9. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  10. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  11. 2022Generative Adversarial Networkscited by 5,627
  12. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  13. 2013Intriguing properties of neural networkscited by 5,155
  14. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  15. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  16. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  17. 2017Deep reinforcement learning from human preferencescited by 3,912
  18. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  19. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
  20. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  21. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,073
  22. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,811
  23. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,790
  24. 2023A Survey of Large Language Modelscited by 2,576
  25. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  26. 2019Fine-Tuning Language Models from Human Preferencescited by 2,150
  27. 2020GShard: Scaling Giant Models with Conditional Computation and Automatic Shardingcited by 1,631
  28. 2020Knowledge Distillation: A Surveycited by 1,603
  29. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  30. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,434
  31. 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,391
  32. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,375
  33. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
  34. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  35. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  36. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,295
  37. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,202
  38. 2019PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarizationcited by 1,102

50 most cited of 224 All 224 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 14; 2024: 38; 2025: 30; 2026: 11.

93 papers.

Sort:

By area:

  1. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,439
  2. 2024R-Judge: Benchmarking Safety Risk Awareness for LLM Agentscited by 288
  3. 2024Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positivecited by 241
  4. 2024A Comprehensive Study of Knowledge Editing for Large Language Modelscited by 163
  5. 2024JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMscited by 95
  6. 2024The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Modelscited by 93
  7. 2024Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Surveycited by 90
  8. 2023Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilitiescited by 82
  9. 2024Safeguarding Large Language Models: A Surveycited by 78
  10. 2024TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Datacited by 70
  11. 2024Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systemscited by 66
  12. 2024Building Guardrails for Large Language Modelscited by 65
38 more
  1. 2023Evaluating the Instruction-Following Robustness of Large Language Models to Prompt Injectioncited by 59
  2. 2024Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledgecited by 51
  3. 2023Look Before You Leap: An Exploratory Study of Uncertainty Measurement for Large Language Modelscited by 41
  4. 2024Assessment of Multimodal Large Language Models in Alignment with Human Valuescited by 36
  5. 2025A Survey of Direct Preference Optimizationcited by 36
  6. 2024AI Safety in Generative AI Large Language Models: A Surveycited by 33
  7. 2024MOSSBench: Is Your Multimodal Language Model Oversensitive to Safe Queries?cited by 30
  8. 2025We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systemscited by 27
  9. 2024Towards Trustworthy AI: A Review of Ethical and Robust Large Language Modelscited by 22
  10. 2023METAL: Metamorphic Testing Framework for Analyzing Large-Language Model Qualitiescited by 20
  11. 2024Unbridled Icarus: A Survey of the Potential Perils of Image Inputs in Multimodal Large Language Model Securitycited by 19
  12. 2023User Modeling in the Era of Large Language Models: Current Research and Future Directionscited by 18
  13. 2024Position: Towards Bidirectional Human-AI Alignmentcited by 18
  14. 2024Compact Proofs of Model Performance via Mechanistic Interpretabilitycited by 18
  15. 2025LLM-Safety Evaluations Lack Robustnesscited by 18
  16. 2025The Intrinsic Dimension of Prompts in Internal Representations of Large Language Modelscited by 17
  17. 2024CHiSafetyBench: A Chinese Hierarchical Safety Benchmark for Large Language Modelscited by 15
  18. 2025Can AI Perceive Physical Danger and Intervene?cited by 14
  19. 2023On the Intersection of Self-Correction and Trust in Language Modelscited by 12
  20. 2023A Security Risk Taxonomy for Prompt-Based Interaction With Large Language Modelscited by 12
  21. 2023Synergistic Integration of Large Language Models and Cognitive Architectures for Robust AI: An Exploratory Analysiscited by 11
  22. 2024Towards Fairness-Aware Adversarial Learningcited by 11
  23. 2025Paradigms of AI Evaluation: Mapping Goals, Methodologies and Culturecited by 11
  24. 2025Safety of Embodied Navigation: A Surveycited by 10
  25. 2026IF-RewardBench: Benchmarking Judge Models for Instruction-Following Evaluationcited by 10
  26. 2024Large Language Model Supply Chain: Open Problems From the Security Perspectivecited by 9
  27. 2025Incentivizing Truthful Language Models via Peer Elicitation Gamescited by 9
  28. 2024Blockchain for Large Language Model Security and Safety: A Holistic Surveycited by 8
  29. 2024Trust-Oriented Adaptive Guardrails for Large Language Modelscited by 8
  30. 2024Characterizing and Evaluating the Reliability of LLMs against Jailbreak Attackscited by 8
  31. 2025Reducing Large Language Model Safety Risks in Women's Health using Semantic Entropycited by 8
  32. 2024Boosting Adversarial Training via Fisher-Rao Norm-based Regularizationcited by 7
  33. 2024ChineseSafe: A Chinese Benchmark for Evaluating Safety in Large Language Modelscited by 7
  34. 2025Stop Reducing Responsibility in LLM-Powered Multi-Agent Systems to Local Alignmentcited by 7
  35. 2023What, Indeed, is an Achievable Provable Guarantee for Learning-Enabled Safety Critical Systemscited by 6
  36. 2024Zero-shot Safety Prediction for Autonomous Robots with Foundation World Modelscited by 6
  37. 2024Online Safety Analysis for LLMs: a Benchmark, an Assessment, and a Path Forwardcited by 6
  38. 2024Building a Domain-specific Guardrail Model in Productioncited by 6

50 most cited of 93 All 93 (JSON)