mlsanityData to 7 Oct 2026

Language Models in Dialogue: Conversational Maxims for Human-AI Interactions

arXiv 2403.15115 ↗First posted 22 Mar 2024cs.CL cs.AI cs.HCcited by 21

Not on the map. Why?

Abstract (arXiv)

Modern language models, while sophisticated, exhibit some inherent shortcomings, particularly in conversational settings. We claim that many of the observed shortcomings can be attributed to violation of one or more conversational principles. By drawing upon extensive research from both the social science and AI communities, we propose a set of maxims -- quantity, quality, relevance, manner, benevolence, and transparency -- for describing effective human-AI conversation. We first justify the applicability of the first four maxims (from Grice) in the context of human-AI interactions. We then argue that two new maxims, benevolence (concerning the generation of, and engagement with, harmful content) and transparency (concerning recognition of one's knowledge boundaries, operational constraints, and intents), are necessary for addressing behavior unique to modern human-AI interactions. We evaluate the degree to which various language models are able to understand these maxims and find that models possess an internal prioritization of principles that can significantly impact their ability to interpret the maxims accurately.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 41 of its 106 references that are in the map. First posted on arXiv 22 Mar 2024.

Builds on

41 of 106 references.

References · 41

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  3. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  4. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
  5. 2023Representation Engineering: A Top-Down Approach to AI Transparencycited by 1,239
  6. 2023Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!cited by 1,106
  7. 2022Scaling Laws for Reward Model Overoptimizationcited by 1,056
  8. 2021A General Language Assistant as a Laboratory for Alignmentcited by 1,023
  9. 2023Towards Understanding Sycophancy in Language Modelscited by 988
  10. 2022Red Teaming Language Models with Language Modelscited by 983
  11. 2022Discovering Language Model Behaviors with Model-Written Evaluationscited by 805
  12. 2022Discovering Latent Knowledge in Language Models Without Supervisioncited by 733
29 more
  1. 2021Deduplicating Training Data Makes Language Models Bettercited by 705
  2. 2023The Internal State of an LLM Knows When It's Lyingcited by 644
  3. 2024Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Trainingcited by 478
  4. 2021Entity-Based Knowledge Conflicts in Question Answeringcited by 349
  5. 2022A Holistic Approach to Undesired Content Detection in the Real Worldcited by 337
  6. 2023AI Deception: A Survey of Examples, Risks, and Potential Solutionscited by 185
  7. 2020On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translationcited by 127
  8. 2021Truthful AI: Developing and governing AI that does not liecited by 109
  9. 2023Question Decomposition Improves the Faithfulness of Model-Generated Reasoningcited by 107
  10. 2023The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversationcited by 107
  11. 2021Detoxifying Language Models Risks Marginalizing Minority Voicescited by 106
  12. 2023Confronting Reward Model Overoptimization with Constrained RLHFcited by 96
  13. 2022Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Surveycited by 80
  14. 2023Still No Lie Detector for Language Models: Probing Empirical and Conceptual Roadblockscited by 77
  15. 2019Sticking to the Facts: Confident Decoding for Faithful Data-to-Text Generationcited by 62
  16. 2023Cognitive Dissonance: Why Do Language Model Outputs Disagree with Internal Representations of Truthfulness?cited by 62
  17. 2022In conversation with Artificial Intelligence: aligning language models with human valuescited by 61
  18. 2023Uncertainty-Penalized Reinforcement Learning from Human Feedback with Diverse Reward LoRA Ensemblescited by 55
  19. 2019Evaluating Coherence in Dialogue Systems using Entailmentcited by 53
  20. 2023Evaluating Superhuman Models with Consistency Checkscited by 47
  21. 2021Focus Attention: Promoting Faithfulness and Diversity in Summarizationcited by 30
  22. 2020Revisiting Challenges in Data-to-Text Generation with Fact Groundingcited by 27
  23. 2022UX Research on Conversational Human-AI Interaction: A Literature Review of the ACM Digital Librarycited by 20
  24. 2022How do you Converse with an Analytical Chatbot? Revisiting Gricean Maxims for Designing Analytical Conversational Behaviorcited by 20
  25. 2023SocialStigmaQA: A Benchmark to Uncover Stigma Amplification in Generative Language Modelscited by 14
  26. 2021Human-AI Interactions Through A Gricean Lenscited by 6
  27. 2023EpiK-Eval: Evaluation for Language Models as Epistemic Modelscited by 6
  28. 2017Detecting Egregious Conversations between Customers and Virtual Agentscited by 4
  29. 2024Supporting Annotators with Affordances for Efficiently Labeling Conversational Datacited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 9; 2026: 8.

21 papers.

Sort:

By area:

  1. 2025Evaluating LLM-based Agents for Multi-Turn Conversations: A Surveycited by 56
  2. 2025TRUTH DECAY: Quantifying Multi-Turn Sycophancy in Language Modelscited by 31
  3. 2024Evaluating the Prompt Steerability of Large Language Modelscited by 26
  4. 2024Adaptive Retrieval-Augmented Generation for Conversational Systemscited by 22
  5. 2025Sycophancy under Pressure: Evaluating and Mitigating Sycophantic Bias via Adversarial Dialogues in Scientific QAcited by 16
  6. 2024Attack Atlas: A Practitioner's Perspective on Challenges and Pitfalls in Red Teaming GenAIcited by 14
  7. 2025Dehumanizing Machines: Mitigating Anthropomorphic Behaviors in Text Generation Systemscited by 11
  8. 2026Feedback by Design: Understanding and Overcoming User Feedback Barriers in Conversational Agentscited by 4
  9. 2025Gricean Norms as a Basis for Effective Collaborationcited by 3
  10. 2025Human-Centered AI Communication in Co-Creativity: An Initial Framework and Insightscited by 3
  11. 2026Why Human Guidance Matters in Collaborative Vibe Codingcited by 3
  12. 2026On the Context Sensitivity of LLM Moral Judgmentcited by 3
9 more
  1. 2026Cultural Compass: A Framework for Organizing Societal Norms to Detect Violations in Human-AI Conversationscited by 2
  2. 2026Enjoy Your Talk: A Human-Centered Benchmark for Multi-Turn Dialogue with Decoupled User Simulation, Target Modeling, and Judgingcited by 1
  3. 2024CELL your Model: Contrastive Explanations for Large Language Modelscited by 0
  4. 2025VizTrust: A Visual Analytics Tool for Capturing User Trust Dynamics in Human-AI Communicationcited by 0
  5. 2025Amulet: Putting Complex Multi-Turn Conversations on the Stand with LLM Juriescited by 0
  6. 2025Planning Ahead with RSA: Efficient Signalling in Dynamic Environments by Projecting User Awareness across Future Timestepscited by 0
  7. 2026DRInQ: Evaluating Conversational Implicature with Controlled Context Variationcited by 0
  8. 2026Not What, But How: A Framework for Auditing LLM Responses across Positioning, Generalization, Anthropomorphism, and Maximscited by 0
  9. 2026CRISP: Cultural Reward Modeling for Implicit Situated Proprietycited by 0