arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.30632cs.HCcs.AIcs.LG
收藏

Rationalize: 人机对齐的共享语义推理

Rationalize: Shared Semantic Reasoning for Human-AI Alignment

New Jersey Institute of Technology(新泽西理工学院)

Aritra Dasgupta, Naga Datha Saikiran Battula, Avina Nakarmi, Sohom Sen, Subhodeep Ghosh, Xun Song

AI总结:

提出Rationalize角色对框架,通过共享推理空间中的互补角色对(如探索者-引导者)实现人类与AI在数据驱动意义建构中的语义对齐,并设计元素级和角色特定的对齐评估方法。

摘要:

我们介绍了Rationalize,一个用于数据驱动意义建构中人类与AI模型之间共享语义推理的角色对框架。基于人机协作和批判性思维的思路,我们将人机交互概念化为一系列互补的角色对(探索者-引导者、调查者-告知者、教师-学生、法官-倡导者),这些角色对在共享推理空间中运作。在这个空间中,人类分析师和AI模型(如LLM)使目的、问题、假设、证据、推理和影响变得明确,不仅促进输出层面的对齐,而且促进双方意图和行动的合理化层面的对齐。我们将这些角色对与双向人机对齐框架联系起来,说明“使AI对齐人类”和“使人类对齐AI”如何因角色而异,并勾勒出一个使用元素级和角色特定方法进行对齐设计和评估的协作研究议程。

英文摘要:

We introduce Rationalize, a role-pair framework for shared semantic reasoning between humans and AI models in data-driven sensemaking. Building on ideas in human-machine teaming and critical thinking, we conceptualize human-AI interaction as a series of complementary role pairs (Explorer-Guide, Investigator-Informant, Teacher-Student, Judge-Advocate) operating in a shared reasoning space. In this space, human analysts and AI models (such as LLMs) make purposes, questions, assumptions, evidence, inferences, and implications explicit, facilitating alignment not only at the output level but at the level of rationalization of intent and action by each side. We relate these role pairs to the bidirectional human-AI alignment framework, illustrating how "aligning AI to humans" and "aligning humans to AI" differ by role, and sketch a collaborative research agenda for alignment design and assessment using element-level and role-specific approaches.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑