conftrace_

prompt compression

32 papers

Explore in graph

Co-occurring keywords

large language model (13587) model compression (3302) long context (121) token-level compression (3) retrieval-augmented generation (1592) inference efficiency (248) efficient inference (233) in-context learning (1405) knowledge distillation (3725) text compression (27)

Papers

Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Models NIPS 2024
Learning to Compress Prompt in Natural Language Formats NAACL 2024
LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression ACL 2024
LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression ACL 2024
Learning to Compress Prompts with Gist Tokens NIPS 2023
LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models EMNLP 2023
Prompt Compression and Contrastive Conditioning for Controllability and Toxicity Reduction in Language Models EMNLP 2022