诱导大型语言模型的持续创造力与多样性
Inducing Sustained Creativity and Diversity in Large Language Models
AI总结：
本文提出一种新的解码方法，通过诱导持续创造力和多样性，使LLM能生成更多概念上独特的结果，从而更有效地探索搜索空间。
摘要：
我们解决了一个未被广泛认可的探索性搜索子集问题，其中用户通常会进行长时间的'搜索寻宝'以寻找完美的婚纱、被忽视的研究主题、 killer公司想法等。当前大型语言模型（LLM）的前几个输出可能有帮助，但仅作为起点，因为搜索需要学习搜索空间并评估许多多样且富有创造力的替代方案。尽管LLM编码了世界大部分知识，但常见解码方法仅针对有正确答案的提示进行优化，因此返回的结果大多同质且传统。其他方法，包括旨在增加少量答案多样性的方法，在搜索寻宝用户学习足够信息以做出最终选择之前就开始重复自己，或为每个相似问题的用户提供一种统一类型的'创造力'。我们开发了一种新颖且易于实现的解码方案，该方案诱导LLM的持续创造力和多样性，即使没有访问LLM向量空间的内部机制，也能生成所需数量的概念上独特结果。该算法解锁了LLM的广泛知识，包括正统和非正统的知识，远超模态解码路径。通过这种方法，搜索寻宝用户可以更快速地探索搜索空间并找到满意的答案。
英文摘要：
We address a not-widely-recognized subset of exploratory search, where a user sets out on a typically long "search quest" for the perfect wedding dress, overlooked research topic, killer company idea, etc. The first few outputs of current large language models (LLMs) may be helpful but only as a start, since the quest requires learning the search space and evaluating many diverse and creative alternatives along the way. Although LLMs encode an impressive fraction of the world's knowledge, common decoding methods are narrowly optimized for prompts with correct answers and thus return mostly homogeneous and conventional results. Other approaches, including those designed to increase diversity across a small set of answers, start to repeat themselves long before search quest users learn enough to make final choices, or offer a uniform type of "creativity" to every user asking similar questions. We develop a novel, easy-to-implement decoding scheme that induces sustained creativity and diversity in LLMs, producing as many conceptually unique results as desired, even without access to the inner workings of an LLM's vector space. The algorithm unlocks an LLM's vast knowledge, both orthodox and heterodox, well beyond modal decoding paths. With this approach, search quest users can more quickly explore the search space and find satisfying answers.
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。
