按年被提到
20252025 · 2 次2026
大模型与语言模型›大模型预训练与缩放·arXiv:2506.10943 · cs.LG

Self-Adapting Language Models

Adam Zweiger, Jyothish Pari, Han Guo, Ekin Akyürek, Yoon Kim, Pulkit Agrawal · 2025
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2025-06-13 · 最近 2025-10-11
2不同的人
2活跃月份
2讨论串
12被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Large language models (LLMs) are powerful but static; they lack mechanisms to adapt their weights in response to new tasks, knowledge, or examples. We introduce Self-Adapting LLMs (SEAL), a framework that enables LLMs to self-adapt by generating their own finetuning data and update directives. Given a new input, the model produces a self-edit-a generation that may restructure the information in different ways, specify optimization hyperparameters, or invoke tools for data augmentation and gradient-based updates. Through supervised finetuning (SFT), these self-edits result in persistent weight updates, enabling lasting adaptation. To train the model to produce effective self-edits, we use a reinforcement learning loop with the downstream performance of the updated model as the reward signal. Unlike prior approaches that rely on separate adaptation modules or auxiliary networks, SEAL directly uses the model's own generation to control its adaptation process. Experiments on knowledge incorporation and few-shot generalization show that SEAL is a promising step toward language models capable of self-directed adaptation. Our website and code is available at https://jyopari.github.io/posts/seal.

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reify · 2025-10

“Boring! June https://arxiv.org/html/2506.10943v1 https://www.researchgate.net/publication/392629858_Self-Adapting_Language_Models 4 months ago: https://news.ycombinator.com/item?id=44271284 The fantasy boosters in full AGI phallus stroking kit: Two close friends of mine who were math prodigies that went on to do ML very early (mid 2010's) were alwa…”

Self-Adapting Language Models Is the Way to AGI?原评论 ↗
被提交为 story · 1 次