English(EN) Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States

新框架训练AI理解用户心理状态

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-15 04:00

研究人员推出了Mind2Dialogue，一个新颖的框架，旨在通过模拟用户的心理状态来训练语言模型，使其更具人类意识。该方法通过使用受心理学启发的模拟器生成连贯的对话，反映不断变化的用户信念和目标，从而解决了当前数据集中显式监督有限的挑战。训练后的模型在理解和执行用户意图方面表现出显著的改进，在遵循偏好和信念推理方面优于Qwen、Llama和OLMo等基线模型。 AI

影响通过理解未言明的意图和目标，增强了AI与人类协作的能力。

排序理由学术论文，介绍了一种用于训练语言模型的新框架和方法论。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 13 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，介绍了一种用于训练语言模型的新框架和方法论。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Zixuan Wang, Yufan Zhou, Jinzhou Tang, Xinle Yu, Chengjun Wu, Lyumanshan Ye, Zhaoxiang Feng, Letian Peng, Adyasha Patra, Fan Bai, Enze Ma, Zhengding Hu, Jianyang Gu, Zhao Wang, Yufei Ding, Jingbo Shang, Tianmin Shu, Zhiting Hu, Zhen Wang · 2026-09-15 04:00

Mind2Dialogue：通过模拟用户心理状态训练具有人类意识的语言模型

arXiv:2609.15972v1 Announce Type: new Abstract: As 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…

本文如何被排名

报道来源 [1]

Mind2Dialogue：通过模拟用户心理状态训练具有人类意识的语言模型

相关实体

相关话题