# Prompt Compression in Diffusion Large Language Models: Evaluating LLMLingua-2 on LLaDA

arXiv: https://arxiv.org/abs/2605.17932 · HTML: https://mlsanity.com/paper/2605.17932/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Prompt and context compression, one of 12 directions in Efficient LLM inference and serving.
- Builds on 15 of its 20 references that are in the map.
- First posted on arXiv 18 May 2026.

## Placed in

- Efficient LLM inference and serving / [Prompt and context compression](https://mlsanity.com/inference/prompt-and-context-compression/)

## Builds on (most cited first, 15 of 15)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [ShareGPT4V: Improving Large Multi-Modal Models with Better Captions](https://mlsanity.com/paper/2311.12793/) (2023)
- [Large Language Diffusion Models](https://mlsanity.com/paper/2502.09992/) (2025)
- [Kimi K2: Open Agentic Intelligence](https://mlsanity.com/paper/2507.20534/) (2025)
- [LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression](https://mlsanity.com/paper/2310.06839/) (2023)
- [LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression](https://mlsanity.com/paper/2403.12968/) (2024)
- [LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models](https://mlsanity.com/paper/2310.05736/) (2023)
- [Compressing Context to Enhance Inference Efficiency of Large Language Models](https://mlsanity.com/paper/2310.06201/) (2023)
- [Keep it Simple: Unsupervised Simplification of Multi-Paragraph Text](https://mlsanity.com/paper/2107.03444/) (2021)
- [Efficient Unsupervised Sentence Compression by Fine-tuning Transformers with Reinforcement Learning](https://mlsanity.com/paper/2205.08221/) (2022)
- [An Empirical Study on Prompt Compression for Large Language Models](https://mlsanity.com/paper/2505.00019/) (2025)

## Built on by (most cited first, 1 of 1)

- [Lost in Compression: A Controlled Cross-Lingual Audit of Extractive Prompt Compressors](https://mlsanity.com/paper/2608.26175/) (2026)

## Abstract (arXiv)

Prompt compression reduces inference cost and context length in large language models, but prior evaluations focus mainly on autoregressive architectures. This study examines whether LLMLingua-2 transfers effectively to diffusion large language models (DLLMs), specifically LLaDA-8B-Instruct. We evaluate GSM8K, DUC2004, and ShareGPT using 250 prompts per dataset at an approximate 50% compression ratio, covering mathematical reasoning, prompt reconstruction, and summarization. Outputs from original, compressed, and reconstructed prompts are compared using exact-match accuracy, BLEU, ROUGE, and BERTScore. Results show that high semantic preservation does not necessarily ensure stable downstream behavior in diffusion models. Summarization remains relatively robust, while mathematical reasoning degrades substantially despite high semantic similarity. Reconstruction further shows that semantically similar prompts may omit reasoning-critical information needed for stable denoising. Overall, compression failures are mainly driven by information omission rather than semantic drift, suggesting that autoregressive prompt compression methods may not transfer uniformly to DLLMs. These findings motivate diffusion-aware compression strategies.