Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States

arXiv:2609.15972 · cs.CL, cs.LG · Submitted 2026-09-14 · Read on arXiv

cs.CL, cs.LG

Submitted: 2026-09-14

Updated: 2026-09-14

Comments: 40 pages, 10 figures, 11 tables. Project page: https://wannabeyourfriend.github.io/mind2dialogue/

Project page: https://wannabeyourfriend.github.io/mind2dialogue

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Personalization — 47× in this paper · explained in 2 episodes
• Benchmark — 26× in this paper · explained in 2 episodes
• Accuracy — 18× in this paper · explained in 1 episode
• Distillation — 16× in this paper · explained in 2 episodes
• Theory of Mind — 15× in this paper
• Consistency — 13× in this paper · explained in 3 episodes
• Alignment — 8× in this paper · explained in 1 episode
• Ablation — 7× in this paper · explained in 1 episode
• Fine-Tuning — 6× in this paper · explained in 5 episodes
• Reinforcement Learning — 6× in this paper · explained in 4 episodes
• Cosine Similarity — 5× in this paper · explained in 3 episodes
• Adam — 4× in this paper · explained in 2 episodes
• Benchmarking — 4× in this paper · explained in 3 episodes
• Core — 4× in this paper · explained in 2 episodes
• Frustration — 4× in this paper · explained in 2 episodes
• Taxonomy of User Needs and Actions — 4× in this paper
• Trace — 4× in this paper · explained in 2 episodes
• Adaptation — 3× in this paper · explained in 1 episode
• Abstraction — 2× in this paper · explained in 1 episode
• Alternation — 2× in this paper · explained in 1 episode
• Fidelity — 2× in this paper · explained in 2 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• Information Asymmetry — 2× in this paper · explained in 2 episodes
• Persona Prompting — 2× in this paper · explained in 2 episodes
• World Model — 2× in this paper · explained in 7 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Accountability — 1× in this paper · explained in 2 episodes
• Agent Memory — 1× in this paper · explained in 1 episode
• Contextual Understanding — 1× in this paper · explained in 2 episodes
• Data Provenance — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Knowledge Distillation — 1× in this paper · explained in 11 episodes
• LLM judge — 1× in this paper · explained in 2 episodes
• Procedural Knowledge — 1× in this paper · explained in 2 episodes
• Provenance — 1× in this paper · explained in 3 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• Regret — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Theory of Mind (ToM) — 1× in this paper · explained in 2 episodes
• Transfer Learning — 1× in this paper · explained in 10 episodes

Sources

• Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
• User Simulation with Large Language Models for Evaluating Task-Oriented Dialogue
• Scaling Synthetic Data Creation with 1,000,000,000 Personas
• The Llama 3 Herd of Models
• Distilling the Knowledge in a Neural Network
• PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memory
• HorizonBench: Long-Horizon Personalization with Evolving Preferences
• Know You Before You Speak: User-State Modeling for LLM Personalization in Multi-Turn Conversation
• MemAudit: Auditing Long-Term Agent Memory via Hidden User-State Recovery
• Synthetic Interaction Data for Scalable Personalization in Large Language Models
• Olmo 3
• UserRL: Training Interactive User-Centric Agent via Reinforcement Learning
• Qwen2.5 Technical Report
• Taxonomy of User Needs and Actions
• OpenAI GPT-5 System Card
• Large Language Models Fail on Trivial Alterations to Theory-of-Mind Tasks
• DeepPersona: A Generative Engine for Scaling Deep Synthetic Personas
• HumanLM: Simulating Users with State Alignment Beats Response Imitation
• OdysSim: Building Foundation Models for Human Behavior Simulation

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering