Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States
Mind2Dialogue simulates users' mental states to create privileged supervision, boosting personalization metrics of Qwen, Llama, and OLMo assistants by up to 40.9 points.
The paper proposes a psychology-guided simulator that preserves personal characteristics while evolving shared mental states to generate coherent conversations, with an Oracle assistant grounded in those states. Privileged distillation then trains models on Oracle responses so deployed assistants help users without direct mental-state access. Training on the full corpus improves every personalization metric over Qwen, Llama, and OLMo instruction-tuned baselines, including 26.6 to 40.9 percentage point gains in preference-following generation and improved belief/action reasoning.
- Psychology-guided simulator generates coherent conversations from evolving user mental states
- Privileged distillation trains assistants that lack mental-state access at deployment
- 26.6 to 40.9 percentage point gains in preference-following over Qwen, Llama, OLMo baselines
- Evaluation combines personalization and theory-of-mind reasoning tasks
From the original article
1 min read at arxiv.orgAs language models become more capable, long-term collaboration in learning, reasoning, and decision-making calls for a deeper understanding of the people they serve. Yet training such human-aware language models faces a fundamental supervision gap because current datasets for LLM assistant training contain few if any well-informed responses explicitly grounded in users' unspoken beliefs and goals.
By Zixuan Wang · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.