科学的异类空间:采样连贯但认知不可用的研究方向
The Alien Space of Science: Sampling Coherent but Cognitively Unavailable Research Directions
AI总结:
本文提出一种框架,通过分解论文为概念单元并学习两个互补模型,采样出连贯但认知不可用的研究方向,扩展了LLM生成的潜在词汇库。
摘要:
科学发现不仅受真理限制,还受研究人员当前探索领域认知可用性限制。许多方向在文献中是连贯的,但因没有现有社区占据正确的概念、方法和直觉组合而不被提出。现代语言模型继承这种偏见,当被提示生成新想法时会重新组合文献的高密度区域。我们引入了一个框架,旨在针对互补区域,称为科学的异类空间,其中方向在现有知识结构下是可能的,但在现有研究人员分布下不太可能。我们的方法首先将论文分解为细粒度的概念单元,并将它们聚类为共享的词汇概念原子。然后在该词汇上学习两个互补模型。一个连贯性模型评分原子组合是否形成可行的研究方向,另一个可用性模型评分是否任何现有作者社区能够产生给定组合。采样异类方向则减少为排名原子组合,以最大化连贯性同时最小化可用性。在包含16,068篇经同行评审的LLM论文的语料库上,所得到的采样器在不牺牲连贯性的前提下,探索出比前沿LLM生成基线大3.5至7倍的有效原子词汇库,并在盲LLM、人类和下游实验评估中产生匹配或超过基线的想法。通过将科学合理性与社区可用性分开,我们的框架指向AI生成想法,补充而非仅仅加速人类科学,扩展探索到当前社区可能忽视的连贯方向。
英文摘要:
Scientific discovery is constrained not only by what is true, but by what is cognitively available to researchers. Many directions are coherent in light of the literature yet unlikely to be proposed because no existing community combines the relevant concepts, methods, and intuitions. Modern language models inherit this bias, recombining high-density regions of the literature when prompted for novel ideas. We target the complementary region, the alien space of science: directions that are scientifically plausible but unlikely under the distribution of existing researchers. Our method decomposes papers into conceptual units and clusters them into a vocabulary of idea atoms. A coherence model scores whether atom combinations form viable research directions, while an availability model scores whether any existing author community is positioned to produce them. We rank combinations to maximize coherence while minimizing availability. On 16,068 peer-reviewed LLM papers from NeurIPS, ICLR, ICML, and major NLP venues, the sampler produces more diverse research portfolios than frontier LLM baselines, including batch-prompted variants that see their entire output, while matching or exceeding their per-idea quality under blind human, LLM, and downstream experimental evaluation. In temporal validation, all components use only pre-2025 data. Selecting less than 1% of the candidate space recovers 2025 combinations at 35.9 times chance; weighting unavailability increases recovery of strictly novel combinations to 3.24 times chance. By separating scientific plausibility from community availability, our framework points toward AI ideation that complements rather than merely accelerates human science, expanding exploration into coherent directions the community may overlook.
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。