5 months ago
-
Comment
-
Hide
-
-
[ 0 ]
-
[ 0 ]
- (Edit | Remove)
- More...
Comment
We study allowing large language models (LLMs) to process arbitrarily long prompts through the lens of inference-time scaling. We propose Recursive Language Models (RLMs), a general inference strategy that treats long prompts as part of an external environment and allows the LLM to programmatically examine, decompose, and recursively call itself over snippets of the prompt. We find that RLMs successfully handle inputs up to two orders of magnitude beyond model context windows and, even for shorter prompts, dramatically outperform the quality of base LLMs and common long-context scaffolds across four diverse long-context tasks, while having comparable (or cheaper) cost per query.
-
Von
-
[ 0 ]
-
[ 0 ]
- (Edit | Remove)
sonnet 4.5 penso che abbia in pancia qualcosa del genere anche se non lo fa in automatico. mi è capitato più volte che quando la finestra di contesto diventava molto grande e non riusciva a rispondere mi proponesse di spezzare il task che gli stavo chiedendo.
-
Von
-
[ 0 ]
-
[ 0 ]
- (Edit | Remove)
