连续知识代谢:从演进文献中生成科学假设
Continuous Knowledge Metabolism: Generating Scientific Hypotheses from Evolving Literature
AI总结:
本文提出CKM框架,通过滑动时间窗口处理文献并动态更新知识库,提出CKM-Lite和CKM-Full两种变体,揭示了增量处理在预测和效率上的优势,以及知识变化对假设生成的影响。
摘要:
科学假设生成需要跟踪知识如何演变,而不仅仅是当前已知的内容。我们引入连续知识代谢(CKM),一种通过滑动时间窗口处理科学文献并逐步更新结构化知识库的框架。我们提出了CKM-Lite,一种高效的变体,通过增量积累实现强大的预测覆盖,优于批量处理在命中率(+2.8%,p=0.006)、假设产量(+3.6,p<0.001)和最佳匹配对齐(+0.43,p<0.001)方面,同时减少92%的token成本。为了理解这些差异的驱动因素,我们开发了CKM-Full,一种带有仪器化的变体,将每个新发现分类为新颖、确认或矛盾,并检测知识变化信号,将假设生成条件设置为完整的演变轨迹。分析892个由CKM-Full在50个研究主题上生成的假设,以及其他变体的并行运行,我们报告了四个经验观察:(1)增量处理在预测和效率指标上优于批量基线;(2)变化意识的仪器化与更高的LLM判断新颖性(Cohen's d=3.46)但较低的预测覆盖相关,揭示了质量-覆盖权衡;(3)一个领域的轨迹稳定性与假设成功相关(r=-0.28,p=0.051),表明了文献基于预测的边界条件;(4)知识收敛信号与矛盾信号相比,命中率高近5倍,表明不同变化类型具有差异的可预测性。这些发现表明,生成的假设特性不仅取决于处理的文献量,还取决于如何处理。它们进一步表明,评估框架必须考虑质量-覆盖权衡,而不是优化单一指标。
英文摘要:
Identifying promising research directions in fast-moving subareas is one of the most cognitively expensive tasks in modern AI research. Existing LLM-driven scientific discovery systems are typically limited to one-shot prompting on static literature snapshots and are validated only against contemporary judges such as human reviewers, agent peer review, wet-lab assays, or self-evaluation, leaving open whether they can anticipate future trends. We present Continuous Knowledge Metabolism (CKM), an AI workflow for hypothesis generation with three key capabilities: (i) continuous literature metabolism via sliding windows that maintain an evolving knowledge state; (ii) predictive evaluation, which grades hypotheses against papers published after the generation window; and (iii) practitioner-grade failure detection that diagnoses workflow failure modes from its outputs. On a 50-topic machine learning benchmark, CKM-Lite produces at least one validated hypothesis on 72% of topics (36 out of 50), more than doubling a one-shot baseline (30%) at approximately 3 dollars per topic and achieving 91% lower token cost. Validated hypotheses precede their matched papers by an average of 404 days (55 hits across 36 topics; median 399 days, range 66-757 days). Broadly, predictive validation against future literature provides a falsifiable, low-cost alternative to contemporary-judge evaluation protocols and can be applied wherever a corpus has dated publication records.
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。