语言模型能教更弱的智能体吗？教师解释通过个性化提升学生表现
Can Language Models Teach Weaker Agents? Teacher Explanations Improve Students via Personalization
AI总结：
本研究提出师生框架，探索LLM教师如何通过预算受限的个性化自然语言解释提升较弱学生的表现，并验证其泛化性与误导风险。
摘要：
可解释人工智能模型的一个标志性属性是能够教导其他智能体，传递如何执行任务的知识。虽然大型语言模型通过为其预测生成解释来执行复杂推理，但尚不清楚它们是否也能成为较弱智能体的好老师。为解决这一问题，我们考虑了两个LLM智能体之间的师生框架，并研究教师是否、何时以及如何通过自然语言解释进行干预以提升学生的表现。由于通信成本高昂，我们定义了一个预算，使得教师仅对数据的一小部分传达解释，之后学生应能独立表现良好。我们将教学问题沿四个维度分解：（1）教师的测试时干预是否提升学生预测，（2）何时值得解释某个数据点，（3）教师应如何个性化解释以更好地教导学生，以及（4）教师解释是否也能提升学生在未来未解释数据上的表现。我们首先表明，教师LLM确实可以干预学生的推理以提升其表现。接下来，受有效教师的心智理论能力的启发，我们提出构建学生的两个少样本心智模型。第一个模型定义了一个干预函数，模拟干预的效用，使教师能够在效用最高时进行干预，并在较低预算下提升学生表现。第二个模型使教师能够为特定学生个性化解释，并超越非个性化教师。我们还证明，在多轮交互中，教师解释具有泛化性，从已解释数据中学习能提升学生在未来未解释数据上的表现。最后，我们验证了不对齐的教师可以通过故意误导学生，将学生表现降低至随机水平。
英文摘要：
A hallmark property of explainable AI models is the ability to teach other agents, communicating knowledge of how to perform a task. While Large Language Models perform complex reasoning by generating explanations for their predictions, it is unclear whether they also make good teachers for weaker agents. To address this, we consider a student-teacher framework between two LLM agents and study if, when, and how the teacher should intervene with natural language explanations to improve the student's performance. Since communication is expensive, we define a budget such that the teacher only communicates explanations for a fraction of the data, after which the student should perform well on its own. We decompose the teaching problem along four axes: (1) if teacher's test time intervention improve student predictions, (2) when it is worth explaining a data point, (3) how the teacher should personalize explanations to better teach the student, and (4) if teacher explanations also improve students on future unexplained data. We first show that teacher LLMs can indeed intervene on student reasoning to improve their performance. Next, inspired by the Theory of Mind abilities of effective teachers, we propose building two few-shot mental models of the student. The first model defines an Intervention Function that simulates the utility of an intervention, allowing the teacher to intervene when this utility is the highest and improving student performance at lower budgets. The second model enables the teacher to personalize explanations for a particular student and outperform unpersonalized teachers. We also demonstrate that in multi-turn interactions, teacher explanations generalize and learning from explained data improves student performance on future unexplained data. Finally, we verify that misaligned teachers can lower student performance to random chance by intentionally misleading them.
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。
