PRISM enables short-context LLMs to outperform incremental and hierarchical merging baselines on long-range reasoning with 4 to 50 times shorter contexts and up to 54% lower cost via structured memory, programmatic revisions, and KV cache reuse.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PRISM: Efficient Long-Range Reasoning With Short-Context LLMs
PRISM enables short-context LLMs to outperform incremental and hierarchical merging baselines on long-range reasoning with 4 to 50 times shorter contexts and up to 54% lower cost via structured memory, programmatic revisions, and KV cache reuse.