按年被提到
20202023 · 2 次2026
大模型与语言模型›模型表达力与计算理论·arXiv:2012.14913 · cs.CL

Transformer Feed-Forward Layers Are Key-Value Memories

Mor Geva, Roei Schuster, Jonathan Berant, Omer Levy · 2020
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2023-05-25 · 最近 2023-06-15
2不同的人
2活跃月份
2讨论串
442被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Feed-forward layers constitute two-thirds of a transformer model's parameters, yet their role in the network remains under-explored. We show that feed-forward layers in transformer-based language models operate as key-value memories, where each key correlates with textual patterns in the training examples, and each value induces a distribution over the output vocabulary. Our experiments show that the learned patterns are human-interpretable, and that lower layers tend to capture shallow patterns, while upper layers learn more semantic ones. The values complement the keys' input patterns by inducing output distributions that concentrate probability mass on tokens likely to appear immediately after each pattern, particularly in the upper layers. Finally, we demonstrate that the output of a feed-forward layer is a composition of its memories, which is subsequently refined throughout the model's layers via residual connections to produce the final output distribution.

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jayalammar · 2023-05

“Additional ones that come to mind now are: Transformer Feed-Forward Layers Are Key-Value Memories https://arxiv.org/abs/2012.14913 The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns via Spotlights of Attention https://arxiv.org/abs/2202.05798 https://github.com/neelnanda-io/TransformerLens”

Show HN: Visual intuitive explanations of LLM concepts (LLM University)原评论 ↗
被提交为 story · 1 次