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

arXiv: https://arxiv.org/abs/2403.15115 · HTML: https://mlsanity.com/paper/2403.15115/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 106 references that are in the map.
- First posted on arXiv 22 Mar 2024.

## Builds on (most cited first, 30 of 41)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [Scaling Laws for Reward Model Overoptimization](https://mlsanity.com/paper/2210.10760/) (2022)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Red Teaming Language Models with Language Models](https://mlsanity.com/paper/2202.03286/) (2022)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [Deduplicating Training Data Makes Language Models Better](https://mlsanity.com/paper/2107.06499/) (2021)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training](https://mlsanity.com/paper/2401.05566/) (2024)
- [Entity-Based Knowledge Conflicts in Question Answering](https://mlsanity.com/paper/2109.05052/) (2021)
- [A Holistic Approach to Undesired Content Detection in the Real World](https://mlsanity.com/paper/2208.03274/) (2022)
- [AI Deception: A Survey of Examples, Risks, and Potential Solutions](https://mlsanity.com/paper/2308.14752/) (2023)
- [On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translation](https://mlsanity.com/paper/2005.03642/) (2020)
- [Truthful AI: Developing and governing AI that does not lie](https://mlsanity.com/paper/2110.06674/) (2021)
- [The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation](https://mlsanity.com/paper/2312.09085/) (2023)
- [Question Decomposition Improves the Faithfulness of Model-Generated Reasoning](https://mlsanity.com/paper/2307.11768/) (2023)
- [Detoxifying Language Models Risks Marginalizing Minority Voices](https://mlsanity.com/paper/2104.06390/) (2021)
- [Confronting Reward Model Overoptimization with Constrained RLHF](https://mlsanity.com/paper/2310.04373/) (2023)
- [Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey](https://mlsanity.com/paper/2210.07700/) (2022)
- [Still No Lie Detector for Language Models: Probing Empirical and Conceptual Roadblocks](https://mlsanity.com/paper/2307.00175/) (2023)
- [Sticking to the Facts: Confident Decoding for Faithful Data-to-Text Generation](https://mlsanity.com/paper/1910.08684/) (2019)
- [In conversation with Artificial Intelligence: aligning language models with human values](https://mlsanity.com/paper/2209.00731/) (2022)
- [Cognitive Dissonance: Why Do Language Model Outputs Disagree with Internal Representations of Truthfulness?](https://mlsanity.com/paper/2312.03729/) (2023)
- [Uncertainty-Penalized Reinforcement Learning from Human Feedback with Diverse Reward LoRA Ensembles](https://mlsanity.com/paper/2401.00243/) (2023)

## Built on by (most cited first, 21 of 21)

- [Evaluating LLM-based Agents for Multi-Turn Conversations: A Survey](https://mlsanity.com/paper/2503.22458/) (2025)
- [TRUTH DECAY: Quantifying Multi-Turn Sycophancy in Language Models](https://mlsanity.com/paper/2503.11656/) (2025)
- [Evaluating the Prompt Steerability of Large Language Models](https://mlsanity.com/paper/2411.12405/) (2024)
- [Adaptive Retrieval-Augmented Generation for Conversational Systems](https://mlsanity.com/paper/2407.21712/) (2024)
- [Sycophancy under Pressure: Evaluating and Mitigating Sycophantic Bias via Adversarial Dialogues in Scientific QA](https://mlsanity.com/paper/2508.13743/) (2025)
- [Attack Atlas: A Practitioner's Perspective on Challenges and Pitfalls in Red Teaming GenAI](https://mlsanity.com/paper/2409.15398/) (2024)
- [Dehumanizing Machines: Mitigating Anthropomorphic Behaviors in Text Generation Systems](https://mlsanity.com/paper/2502.14019/) (2025)
- [Feedback by Design: Understanding and Overcoming User Feedback Barriers in Conversational Agents](https://mlsanity.com/paper/2602.01405/) (2026)
- [Gricean Norms as a Basis for Effective Collaboration](https://mlsanity.com/paper/2503.14484/) (2025)
- [Human-Centered AI Communication in Co-Creativity: An Initial Framework and Insights](https://mlsanity.com/paper/2505.18385/) (2025)
- [Why Human Guidance Matters in Collaborative Vibe Coding](https://mlsanity.com/paper/2602.10473/) (2026)
- [On the Context Sensitivity of LLM Moral Judgment](https://mlsanity.com/paper/2603.23114/) (2026)
- [Cultural Compass: A Framework for Organizing Societal Norms to Detect Violations in Human-AI Conversations](https://mlsanity.com/paper/2601.07973/) (2026)
- [Enjoy Your Talk: A Human-Centered Benchmark for Multi-Turn Dialogue with Decoupled User Simulation, Target Modeling, and Judging](https://mlsanity.com/paper/2607.10428/) (2026)
- [CELL your Model: Contrastive Explanations for Large Language Models](https://mlsanity.com/paper/2406.11785/) (2024)
- [VizTrust: A Visual Analytics Tool for Capturing User Trust Dynamics in Human-AI Communication](https://mlsanity.com/paper/2503.07279/) (2025)
- [Amulet: Putting Complex Multi-Turn Conversations on the Stand with LLM Juries](https://mlsanity.com/paper/2505.20451/) (2025)
- [Planning Ahead with RSA: Efficient Signalling in Dynamic Environments by Projecting User Awareness across Future Timesteps](https://mlsanity.com/paper/2510.23340/) (2025)
- [DRInQ: Evaluating Conversational Implicature with Controlled Context Variation](https://mlsanity.com/paper/2605.24267/) (2026)
- [Not What, But How: A Framework for Auditing LLM Responses across Positioning, Generalization, Anthropomorphism, and Maxims](https://mlsanity.com/paper/2606.02493/) (2026)
- [CRISP: Cultural Reward Modeling for Implicit Situated Propriety](https://mlsanity.com/paper/2609.34345/) (2026)

## 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.