LearnLM：改善用於學習的Gemini

摘要

當今的生成式人工智慧系統通常被調整為默認呈現資訊，而非像人類導師那樣與使用者互動以促進學習。為了應對這些系統在教育領域中的廣泛應用，我們重新定義了注入教學行為的挑戰，將其視為教學指導跟隨的挑戰，其中訓練和評估範例包括系統級指導，描述後續模型轉換中存在或期望的具體教學特徵。這種框架避免了將我們的模型限定於任何特定的教學定義，反而允許教師或開發人員指定期望的模型行為。這也為改進 Gemini 模型的學習能力鋪平了道路，通過將我們的教學數據添加到訓練後的混合中，與其快速擴展的功能集相結合。這兩者都代表了我們最初技術報告的重要變化。我們展示了如何使用教學指導跟隨進行訓練，產生了一個 LearnLM 模型（可在 Google AI Studio 上使用），在各種學習情境中，專家評分者明顯偏好該模型，平均偏好強度比 GPT-4o 高出 31%，比 Claude 3.5 高出 11%，比基於 Gemini 1.5 Pro 模型的 LearnLM 高出 13%。

English

Today's generative AI systems are tuned to present information by default rather than engage users in service of learning as a human tutor would. To address the wide range of potential education use cases for these systems, we reframe the challenge of injecting pedagogical behavior as one of pedagogical instruction following, where training and evaluation examples include system-level instructions describing the specific pedagogy attributes present or desired in subsequent model turns. This framing avoids committing our models to any particular definition of pedagogy, and instead allows teachers or developers to specify desired model behavior. It also clears a path to improving Gemini models for learning -- by enabling the addition of our pedagogical data to post-training mixtures -- alongside their rapidly expanding set of capabilities. Both represent important changes from our initial tech report. We show how training with pedagogical instruction following produces a LearnLM model (available on Google AI Studio) that is preferred substantially by expert raters across a diverse set of learning scenarios, with average preference strengths of 31\% over GPT-4o, 11\% over Claude 3.5, and 13\% over the Gemini 1.5 Pro model LearnLM was based on.

LearnLM：改善用於學習的Gemini

LearnLM: Improving Gemini for Learning

摘要

Summary

Support