Seonglae ChoIn terms of information entropy, tokens with lower perplexity (PPL) contribute less to the overall entropy gains of the language model. In other words, removing tokens with lower perplexity has a relatively minor impact on the LLM’s comprehension of the context.
2 LLMLinguamicrosoft • Updated 2026 Sep 2 14:3
LLMLingua
microsoft • Updated 2026 Sep 2 14:3
LLMLingua-2: Data Distillation for Efficient and Faithful...
This paper focuses on task-agnostic prompt compression for better generalizability and efficiency. Considering the redundancy in natural language, existing approaches compress prompts by removing...
https://arxiv.org/abs/2403.12968
LLMLingua-2 | Learn Compression Target via Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression
LLMLingua-2: Data distillation for efficient and faithful task-agnostic prompt compression (ACL 2024).
https://llmlingua.com/llmlingua2.html
