大语言模型中的思维语言塑造输出多样性

摘要

輸出多樣性對大型語言模型至關重要，因為它支撐著多元性與創造力。本研究揭示，通過控制模型思維過程中的語言載體——即「思維語言」，能為輸出多樣性提供一個新穎且結構化的來源。初步研究表明，不同思維語言在模型的思維空間中佔據著不同區域。基於此發現，我們研究了多語言思維下的兩種重複抽樣策略——單語言抽樣與混合語言抽樣，並對所有輸出（無論使用何種思維語言）統一控制為英語進行多樣性評估。大量實驗表明，將思維語言從英語切換至非英語語言能持續提升輸出多樣性，且存在清晰穩定的正相關性：思維空間中與英語距離越遠的語言帶來的增益越大。我們進一步證實，通過組合效應聚合多種思維語言的樣本可產生額外提升，而基於語言異質性的擴展抽樣能突破模型的多元性上限。最後，我們驗證這些發現可轉化為多元對齊場景的實際效益，使LLM輸出能更廣泛涵蓋文化知識與價值取向。相關代碼已開源於：https://github.com/iNLP-Lab/Multilingual-LoT-Diversity。

English

Output diversity is crucial for Large Language Models as it underpins pluralism and creativity. In this work, we reveal that controlling the language used during model thinking-the language of thought-provides a novel and structural source of output diversity. Our preliminary study shows that different thinking languages occupy distinct regions in a model's thinking space. Based on this observation, we study two repeated sampling strategies under multilingual thinking-Single-Language Sampling and Mixed-Language Sampling-and conduct diversity evaluation on outputs that are controlled to be in English, regardless of the thinking language used. Across extensive experiments, we demonstrate that switching the thinking language from English to non-English languages consistently increases output diversity, with a clear and consistent positive correlation such that languages farther from English in the thinking space yield larger gains. We further show that aggregating samples across multiple thinking languages yields additional improvements through compositional effects, and that scaling sampling with linguistic heterogeneity expands the model's diversity ceiling. Finally, we show that these findings translate into practical benefits in pluralistic alignment scenarios, leading to broader coverage of cultural knowledge and value orientations in LLM outputs. Our code is publicly available at https://github.com/iNLP-Lab/Multilingual-LoT-Diversity.

大语言模型中的思维语言塑造输出多样性

Language of Thought Shapes Output Diversity in Large Language Models

摘要

Support