HuggingFace Daily Papers（社区热门论文）· HuggingFace Daily Papers（社区热门论文）·· 10 天前AI 评分44
LANTERN：从语言模型内部表征中挖掘隐藏的数学关联
AI 导读
LANTERN 通过预训练模型激活上的分类器对候选关系排序，结合分阶段过滤、假设生成、可执行验证与分析检查，在 OEIS 的 1 万条高频序列的 5000 万对关系中产出 62 条已验证关联，其中 13 条值得展示、9 条具信息量或洞察力，4 条在 OEIS 与定向文献检索中均未出现。整个流程含分类器训练、候选排序、过滤与验证耗时不到 8 小时。
正文
Abstract:Language models can now prove theorems, but people still decide which problems to pursue. We ask whether a model's internal representations can help identify promising mathematical connections. We develop LANTERN, a fast, cost-efficient pipeline that uses a classifier over pretrained-model activations to rank candidate relations, followed by staged filtering, hypothesis generation, executable verification, and analytical checking. Applied to the On-Line Encyclopedia of Integer Sequences (OEIS), LANTERN ranked 50 million pairs among 10,000 frequently referenced sequences and produced 62 verified relations between pairs without an existing OEIS cross-reference. A content screen retained 13 relations worth presenting; nine of these are informative or insightful, including four which are entirely novel to the best of our knowledge: none appears in the OEIS or in our targeted literature search. The entire end-to-end process including classifier training, candidate ranking, filtering and verification took under 8 hours.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2609.32264 [cs.CL] |
| (or arXiv:2609.32264v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2609.32264 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Pavel Tikhonov [view email]
[v1]
Sat, 26 Sep 2026 05:39:40 UTC (1,183 KB)
来源：HuggingFace Daily Papers（社区热门论文） · arxiv.org