mlsanityData to 14 Oct 2026

Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment

arXiv 2308.05374 ↗First posted 10 Aug 2023cs.AI cs.LGcited by 401

Not on the map. Why?

Cited by 52 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Ensuring alignment, which refers to making models behave in accordance with human intentions [1,2], has become a critical task before deploying large language models (LLMs) in real-world applications. For instance, OpenAI devoted six months to iteratively aligning GPT-4 before its release [3]. However, a major challenge faced by practitioners is the lack of clear guidance on evaluating whether LLM outputs align with social norms, values, and regulations. This obstacle hinders systematic iteration and deployment of LLMs. To address this issue, this paper presents a comprehensive survey of key dimensions that are crucial to consider when assessing LLM trustworthiness. The survey covers seven major categories of LLM trustworthiness: reliability, safety, fairness, resistance to misuse, explainability and reasoning, adherence to social norms, and robustness. Each major category is further divided into several sub-categories, resulting in a total of 29 sub-categories. Additionally, a subset of 8 sub-categories is selected for further investigation, where corresponding measurement studies are designed and conducted on several widely-used LLMs. The measurement results indicate that, in general, more aligned models tend to perform better in terms of overall trustworthiness. However, the effectiveness of alignment varies across the different trustworthiness categories considered. This highlights the importance of conducting more fine-grained analyses, testing, and making continuous improvements on LLM alignment. By shedding light on these key dimensions of LLM trustworthiness, this paper aims to provide valuable insights and guidance to practitioners in the field. Understanding and addressing these concerns will be crucial in achieving reliable and ethically sound deployment of LLMs in various applications.

Key facts. Cited by 401 papers in the map (data through 14 Oct 2026). Builds on 155 of its 471 references that are in the map. First posted on arXiv 10 Aug 2023.

Builds on

155 of 471 references.

References · 155

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  5. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  6. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  7. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  8. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  9. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  10. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,512
  11. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  12. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
38 more
  1. 2022Scaling Instruction-Finetuned Language Modelscited by 3,024
  2. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
  3. 2022Emergent Abilities of Large Language Modelscited by 2,512
  4. 2022Language Models (Mostly) Know What They Knowcited by 1,856
  5. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  6. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,407
  7. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,312
  8. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,255
  9. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  10. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,122
  11. 2021A General Language Assistant as a Laboratory for Alignmentcited by 1,055
  12. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 974
  13. 2021Ethical and social risks of harm from Language Modelscited by 966
  14. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  15. 2022Solving math word problems with process- and outcome-based feedbackcited by 901
  16. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 894
  17. 2022GLM-130B: An Open Bilingual Pre-trained Modelcited by 843
  18. 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
  19. 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 819
  20. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 810
  21. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 800
  22. 2023StarCoder: may the source be with you!cited by 799
  23. 2022Quantifying Memorization Across Neural Language Modelscited by 763
  24. 2023Multimodal Chain-of-Thought Reasoning in Language Modelscited by 752
  25. 2022Teaching Models to Express Their Uncertainty in Wordscited by 751
  26. 2022Galactica: A Large Language Model for Sciencecited by 744
  27. 2022Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learnedcited by 729
  28. 2023A Watermark for Large Language Modelscited by 725
  29. 2020Aligning AI With Shared Human Valuescited by 723
  30. 2021Deduplicating Training Data Makes Language Models Bettercited by 714
  31. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 692
  32. 2023RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignmentcited by 686
  33. 2019Certified Data Removal from Machine Learning Modelscited by 535
  34. 2023DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Modelscited by 518
  35. 2023RRHF: Rank Responses to Align Language Models with Human Feedback without tearscited by 463
  36. 2019Learning the Difference that Makes a Difference with Counterfactually-Augmented Datacited by 439
  37. 2021Differentially Private Fine-tuning of Language Modelscited by 400
  38. 2021Entity-Based Knowledge Conflicts in Question Answeringcited by 356

50 most cited of 155 All 155 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 30; 2024: 170; 2025: 143; 2026: 58.

401 papers.

Sort:

By area:

  1. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  2. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 634
  3. 2025Why Do Multi-Agent LLM Systems Fail?cited by 604
  4. 2024Justice or Prejudice? Quantifying Biases in LLM-as-a-Judgecited by 368
  5. 2023Large Language Model Unlearningcited by 302
  6. 2024A Survey on Knowledge Distillation of Large Language Modelscited by 284
  7. 2023A Survey of Confidence Estimation and Calibration in Large Language Modelscited by 256
  8. 2023Large Language Model Alignment: A Surveycited by 243
  9. 2023Evaluating Large Language Models: A Comprehensive Surveycited by 202
  10. 2024VoiceBench: Benchmarking LLM-Based Voice Assistantscited by 200
  11. 2024Security and Privacy Challenges of Large Language Models: A Surveycited by 186
  12. 2024Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaborationcited by 180
38 more
  1. 2023Can LLM-Generated Misinformation Be Detected?cited by 177
  2. 2024A Comprehensive Study of Knowledge Editing for Large Language Modelscited by 163
  3. 2023Sociotechnical Safety Evaluation of Generative AI Systemscited by 157
  4. 2024Benchmarking Complex Instruction-Following with Multiple Constraints Compositioncited by 152
  5. 2024ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agentscited by 133
  6. 2025A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyondcited by 132
  7. 2024Attacks, Defenses and Evaluations for LLM Conversation Safety: A Surveycited by 130
  8. 2024AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathwayscited by 127
  9. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 126
  10. 2024A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directionscited by 121
  11. 2025The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independencecited by 115
  12. 2024Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstructioncited by 107
  13. 2024The Art of Saying No: Contextual Noncompliance in Language Modelscited by 105
  14. 2024Bias and Unfairness in Information Retrieval Systems: New Challenges in the LLM Eracited by 98
  15. 2024How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden Statescited by 98
  16. 2025A Survey on Trustworthy LLM Agents: Threats and Countermeasurescited by 96
  17. 2024Large Language Models and Games: A Survey and Roadmapcited by 93
  18. 2024SOTOPIA-π: Interactive Learning of Socially Intelligent Language Agentscited by 93
  19. 2024Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Surveycited by 90
  20. 2024Measuring Political Bias in Large Language Models: What Is Said and How It Is Saidcited by 89
  21. 2024Trustworthiness in Retrieval-Augmented Generation Systems: A Surveycited by 83
  22. 2024ToolSword: Unveiling Safety Issues of Large Language Models in Tool Learning Across Three Stagescited by 82
  23. 2024Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluationcited by 80
  24. 2023Alignment for Honestycited by 74
  25. 2023AlignBench: Benchmarking Chinese Alignment of Large Language Modelscited by 68
  26. 2025A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluationscited by 67
  27. 2024Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systemscited by 66
  28. 2024TrustAgent: Towards Safe and Trustworthy LLM-based Agentscited by 64
  29. 2023LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplaycited by 63
  30. 2024Introducing v0.5 of the AI Safety Benchmark from MLCommonscited by 62
  31. 2025Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyondcited by 61
  32. 2024When Search Engine Services meet Large Language Models: Visions and Challengescited by 59
  33. 2024DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Lifecited by 59
  34. 2024Large Language Model Safety: A Holistic Surveycited by 59
  35. 2024Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compressioncited by 57
  36. 2024Determinants of LLM-assisted Decision-Makingcited by 56
  37. 2024The opportunities and risks of large language models in mental healthcited by 54
  38. 2024Conformal Alignment: Knowing When to Trust Foundation Models with Guaranteescited by 54

50 most cited of 401 All 401 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024ABC Align: Large Language Model Alignment for Safety & Accuracy
  2. 2025On Evaluating LLM Alignment by Evaluating LLMs as Judges
  3. 2025Rethinking the Evaluation of Alignment Methods: Insights into Diversity, Generalisation, and Safety
  4. 2025A Comprehensive Evaluation framework of Alignment Techniques for LLMs
  5. 2025Direct Confidence Alignment: Aligning Verbalized Confidence with Internal Confidence In Large Language Models
  6. 2024Confidence Under the Hood: An Investigation into the Confidence-Probability Alignment in Large Language Models
  7. 2024Dissecting Human and LLM Preferences
  8. 2026Are Aligned Large Language Models Still Misaligned?