AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Parse Trees Guided LLM Prompt Compression

Wenhao Mao, Chengbin Hou, Tianyu Zhang, Xinyu Lin, Ke Tang, Hairong Lv

TPAMI 2025 · Large language models › Language, safety and interpretability · approach: Controlled text generation · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add first node adjustment (a2) in value adjustment (ablation)PartPrompt · BBCnews (50% tokens)BS-F1: 70.59 -> 74.57Improved
add hierarchical global tree with node value adjustment over variant 1 (ablation)PartPrompt · BBCnews (50% tokens)BS-F1: 70.79 -> 74.57Improved
add global parse tree without value adjustment on top of local trees (ablation)PartPrompt · BBCnews (50% tokens)BS-F1: 71.06 -> 70.79Hurt
add local parse trees to entropy-only compression (ablation)PartPrompt · BBCnews (50% tokens)BS-F1: 69.75 -> 71.06Improved
add information entropy to parse-tree-only compression (global tree) (ablation)PartPrompt · BBCnews (50% tokens)BS-F1: 70.44 -> 70.79Improved
add information entropy to parse-tree-only compression (local trees) (ablation)PartPrompt · BBCnews (50% tokens)BS-F1: 69.33 -> 71.06Improved
add local entropy approximation to the full method (ablation)PartPrompt · BBCnews (50% tokens)BS-F1: 74.04 -> 74.57Improved
add local entropy approximation to global tree without adjustment (ablation)PartPrompt · BBCnews (50% tokens)BS-F1: 71.37 -> 70.79Hurt
add local entropy approximation to local-tree variant (ablation)PartPrompt · BBCnews (50% tokens)BS-F1: 70.29 -> 71.06Improved
use PartPrompt instead of LLMLingua2 on Llama3-70BPartPrompt · BBCnews (50% tokens), Llama3-70BBLEU: 13.60 -> 25.87Improved
use PartPrompt instead of LLMLingua on GSM8KPartPrompt · GSM8K (30% tokens)EM: 67.85 -> 53.30Mixed
use PartPrompt on RULER-niah instead of the uncompressed promptPartPrompt · RULER niahscore: 21.0 -> 69.0Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy