利用多语言提示提升大语言模型生成多样性
Multilingual Prompting for Improving LLM Generation Diversity
AI总结：
针对LLM生成缺乏文化与观点多样性的问题，本文提出多语言提示方法，通过跨文化语言线索激活更广知识，并在多个模型上验证其优于现有多样性增强技术。
摘要：
众所周知，大语言模型（LLM）在从表达观点到回答事实性问题的各类生成中，缺乏文化代表性和整体多样性。为缓解这一问题，我们提出多语言提示：这是一种提示方法，会为基础提示生成若干变体，加入来自多种文化的文化和语言线索，生成回答，然后合并结果。基于LLM具备语言特定知识的证据，多语言提示试图通过激活嵌入模型训练数据中的更广泛文化知识来提升多样性。通过在多个模型（GPT-4o、GPT-4o-mini、LLaMA 70B和LLaMA 8B）上的实验，我们表明多语言提示始终优于高温采样、逐步回忆和角色提示等现有多样性增强技术。进一步分析表明，多语言提示的收益在高资源语言与低资源语言之间以及不同模型规模之间存在差异，并且使提示语言与文化线索保持一致可减少关于特定文化信息的幻觉。
英文摘要：
Large Language Models (LLMs) are known to lack cultural representation and overall diversity in their generations, from expressing opinions to answering factual questions. To mitigate this problem, we propose multilingual prompting: a prompting method which generates several variations of a base prompt with added cultural and linguistic cues from several cultures, generates responses, and then combines the results. Building on evidence that LLMs have language-specific knowledge, multilingual prompting seeks to increase diversity by activating a broader range of cultural knowledge embedded in model training data. Through experiments across multiple models (GPT-4o, GPT-4o-mini, LLaMA 70B, and LLaMA 8B), we show that multilingual prompting consistently outperforms existing diversity-enhancing techniques such as high-temperature sampling, step-by-step recall, and persona prompting. Further analyses show that the benefits of multilingual prompting vary between high and low resource languages and across model sizes, and that aligning the prompting language with cultural cues reduces hallucination about culturally-specific information.
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。
