conftrace_

query-aware compression

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

black-box language model (1) large language model (1) rate-distortion theory (1) black-box model (1) prompt compression (1) token-level compression (1) rate distortion (1) efficient inference (1) information theory (1)

Papers

Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Models NeurIPS 2024