You don't need long context

概要

Later tokens are costlier to generate than earlier tokens. On frontier open weight models, the disparity in cost may rise to as much as 7x. Through frequent compaction, we show across a broad range of long-horizon and long-input tasks that frontier language models sacrifice little to no task accuracy when maintaining short contexts. We further demonstrate that LLM performance does not collapse on long-horizon software engineering tasks even when taking at most one action per context, and based on that we outline the concept of semantic state space models (SSSMs). Our findings question the need for long-context language models.

参考リンク

• Hugging Face ↗

リンク先のライセンス・再現性・データ条件をご確認ください。自動分類や実装の目安は保証ではありません。

実装を始めるプロンプト

参考リンクを確認したうえで、次の内容をコピーして利用できます。

# 論文・記事
You don't need long context

# 概要
Later tokens are costlier to generate than earlier tokens. On frontier open weight models, the disparity in cost may rise to as much as 7x.

# 原典
https://arxiv.org/abs/2611.05306

上記の手法を実装してください。実行前に依存関係とライセンスを確認してください。