按年被提到
20242024 · 1 次2026
大模型与语言模型›可解释性与表征研究·arXiv:2411.02272 · cs.LG

Combining Induction and Transduction for Abstract Reasoning

Wen-Ding Li, Keya Hu, Carter Larsen, Yuqing Wu, Simon Alford, Caleb Woo, Spencer M. Dunn, Hao Tang, Michelangelo Naim, Dat Nguyen, Wei-Long Zheng, Zenna Tavares 等 14 人 · 2024
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2024-11-11 · 最近 2025-01-20
2不同的人
2活跃月份
2讨论串
10被引(OpenAlex)
arXiv 摘要(候选层不写导读)

When learning an input-output mapping from very few examples, is it better to first infer a latent function that explains the examples, or is it better to directly predict new test outputs, e.g. using a neural network? We study this question on ARC by training neural models for induction (inferring latent functions) and transduction (directly predicting the test output for a given test input). We train on synthetically generated variations of Python programs that solve ARC training tasks. We find inductive and transductive models solve different kinds of test problems, despite having the same training problems and sharing the same neural architecture: Inductive program synthesis excels at precise computations, and at composing multiple concepts, while transduction succeeds on fuzzier perceptual concepts. Ensembling them approaches human-level performance on ARC.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论trott · 2025-01

“This is the paper: https://arxiv.org/abs/2411.02272 They won the 1st paper award: https://arcprize.org/2024-results In their approach, the LLM generates inputs (images to be transformed) and solutions (Python programs that do the image transformations). The output images are created by applying the programs to the inputs. So there's a constraint on the…”

FrontierMath was funded by OpenAI原评论 ↗
被提交为 story · 1 次