mlsanityData to 7 Oct 2026

Automated Meta Prompt Engineering for Alignment with the Theory of Mind

arXiv 2505.09024 ↗First posted 13 May 2025cs.AI cs.CL cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We introduce a method of meta-prompting that jointly produces fluent text for complex tasks while optimizing the similarity of neural states between a human's mental expectation and a Large Language Model's (LLM) neural processing. A technique of agentic reinforcement learning is applied, in which an LLM as a Judge (LLMaaJ) teaches another LLM, through in-context learning, how to produce content by interpreting the intended and unintended generated text traits. To measure human mental beliefs around content production, users modify long form AI-generated text articles before publication at the US Open 2024 tennis Grand Slam. Now, an LLMaaJ can solve the Theory of Mind (ToM) alignment problem by anticipating and including human edits within the creation of text from an LLM. Throughout experimentation and by interpreting the results of a live production system, the expectations of human content reviewers had 100% of alignment with AI 53.8% of the time with an average iteration count of 4.38. The geometric interpretation of content traits such as factualness, novelty, repetitiveness, and relevancy over a Hilbert vector space combines spatial volume (all trait importance) with vertices alignment (individual trait relevance) enabled the LLMaaJ to optimize on Human ToM. This resulted in an increase in content quality by extending the coverage of tennis action. Our work that was deployed at the US Open 2024 has been used across other live events within sports and entertainment.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 30 of its 48 references that are in the map. First posted on arXiv 13 May 2025.

Builds on

30 of 48 references.

References · 30

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  4. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  5. 2023A Survey of Large Language Modelscited by 2,537
  6. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,081
  7. 2023SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agentscited by 350
  8. 2018Machine Theory of Mindcited by 222
  9. 2024Chain-of-Thought Reasoning Without Promptingcited by 208
  10. 2024Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judgecited by 202
  11. 2018An Introduction to Deep Reinforcement Learningcited by 201
  12. 2023Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Futurecited by 184
18 more
  1. 2024More Agents Is All You Needcited by 174
  2. 2024The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Surveycited by 164
  3. 2024Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffoldingcited by 115
  4. 2020Combining Deep Reinforcement Learning and Search for Imperfect-Information Gamescited by 110
  5. 2021Counterfactual Invariance to Spurious Correlations: Why and How to Pass Stress Testscited by 77
  6. 2023Large Language Models are Diverse Role-Players for Summarization Evaluationcited by 62
  7. 2024Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMscited by 48
  8. 2022How to Prompt? Opportunities and Challenges of Zero- and Few-Shot Learning for Human-AI Interaction in Creative Applications of Generative Modelscited by 43
  9. 2023Harnessing the Power of Large Language Models for Empathetic Response Generation: Empirical Investigations and Improvementscited by 42
  10. 2024InterIntent: Investigating Social Intelligence of LLMs via Intention Understanding in an Interactive Game Contextcited by 25
  11. 2023Reinforcement Learning in the Era of LLMs: What is Essential? What is needed? An RL Perspective on RLHF, Prompting, and Beyondcited by 20
  12. 2023Unveiling Theory of Mind in Large Language Models: A Parallel to Single Neurons in the Human Braincited by 18
  13. 2023Effective Structured Prompting by Meta-Learning and Representative Verbalizercited by 14
  14. 2023Advancing the Search Frontier with AI Agentscited by 12
  15. 2023Adopting AI: How Familiarity Breeds Both Trust and Contemptcited by 7
  16. 2023On Meta-Promptingcited by 6
  17. 2024Large Scale Generative AI Text Applied to Sports and Musiccited by 4
  18. 2024Spontaneous Theory of Mind for Artificial Intelligencecited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2022Methodological reflections for AI alignment research using human feedback
  2. 2025Enhancing Conversational Agents with Theory of Mind: Aligning Beliefs, Desires, and Intentions for Human-Like Interaction
  3. 2023Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision
  4. 2023Instruction-tuning Aligns LLMs to the Human Brain
  5. 2025Decoding Alignment: A Critical Survey of LLM Development Initiatives through Value-setting and Data-centric Lens
  6. 2023CycleAlign: Iterative Distillation from Black-box LLM to White-box Models for Better Human Alignment
  7. 2024A Flexible Method for Behaviorally Measuring Alignment Between Human and Artificial Intelligence Using Representational Similarity Analysis
  8. 2025Dynamic Alignment for Collective Agency: Toward a Scalable Self-Improving Framework for Open-Ended LLM Alignment