# Provence: efficient and robust context pruning for retrieval-augmented generation

arXiv: https://arxiv.org/abs/2501.16214 · HTML: https://mlsanity.com/paper/2501.16214/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation.
- Builds on 12 of its 56 references that are in the map.
- First posted on arXiv 27 Jan 2025.

## Placed in

- Retrieval-augmented generation / [Generation and context integration](https://mlsanity.com/rag/generation-and-context-integration/)

## Builds on (most cited first, 12 of 12)

- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Atlas: Few-shot Learning with Retrieval Augmented Language Models](https://mlsanity.com/paper/2208.03299/) (2022)
- [Overview of the TREC 2019 deep learning track](https://mlsanity.com/paper/2003.07820/) (2020)
- [Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation](https://mlsanity.com/paper/2010.02666/) (2020)
- [RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encoder](https://mlsanity.com/paper/2205.12035/) (2022)
- [Learning to Filter Context for Retrieval-Augmented Generation](https://mlsanity.com/paper/2311.08377/) (2023)
- [Reliable, Adaptable, and Attributable Language Models with Retrieval](https://mlsanity.com/paper/2403.03187/) (2024)
- [CompAct: Compressing Retrieved Documents Actively for Question Answering](https://mlsanity.com/paper/2407.09014/) (2024)
- [Context Embeddings for Efficient Answer Generation in RAG](https://mlsanity.com/paper/2407.09252/) (2024)
- [RAGGED: Towards Informed Design of Scalable and Stable RAG Systems](https://mlsanity.com/paper/2403.09040/) (2024)
- [Naver Labs Europe (SPLADE) @ TREC Deep Learning 2022](https://mlsanity.com/paper/2302.12574/) (2023)

## Built on by (most cited first, 25 of 25)

- [Reducing Cost of LLM Agents with Trajectory Reduction](https://mlsanity.com/paper/2509.23586/) (2025)
- [SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression](https://mlsanity.com/paper/2507.05633/) (2025)
- [SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions](https://mlsanity.com/paper/2603.07379/) (2026)
- [Influence Guided Context Selection for Effective Retrieval-Augmented Generation](https://mlsanity.com/paper/2509.21359/) (2025)
- [Do LLMs Benefit From Their Own Words?](https://mlsanity.com/paper/2602.24287/) (2026)
- [OSCAR: Online Soft Compression And Reranking](https://mlsanity.com/paper/2504.07109/) (2025)
- [CoACT: Action-Preserving Observation Compression for Coding Agents](https://mlsanity.com/paper/2607.02911/) (2026)
- [What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents](https://mlsanity.com/paper/2607.08032/) (2026)
- [NeocorRAG: Less Irrelevant Information, More Explicit Evidence, and More Effective Recall via Evidence Chains](https://mlsanity.com/paper/2604.27852/) (2026)
- [Beyond Position Bias: Shifting Context Compression from Position-Driven to Semantic-Driven](https://mlsanity.com/paper/2605.09463/) (2026)
- [XProvence: Zero-Cost Multilingual Context Pruning for Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.18886/) (2026)
- [Data Distribution Matters: A Data-Centric Perspective on Context Compression for Large Language Model](https://mlsanity.com/paper/2602.01778/) (2026)
- [LLM-Oriented Information Retrieval: A Denoising-First Perspective](https://mlsanity.com/paper/2605.00505/) (2026)
- [Grounded Cache Routing for Retrieval-Augmented Generation: When Is It Safe to Reuse an Answer?](https://mlsanity.com/paper/2605.27494/) (2026)
- [Fixed RAG Compression Collapses Measured Reader Scaling](https://mlsanity.com/paper/2606.21807/) (2026)
- [Less can be More: Relieving RAG Bottlenecks via Evidence Frontloading and Pressure-Adaptive Budgeting](https://mlsanity.com/paper/2608.25115/) (2026)
- [Lost in Compression: A Controlled Cross-Lingual Audit of Extractive Prompt Compressors](https://mlsanity.com/paper/2608.26175/) (2026)
- [AttnCompress: Dynamic Attention-Guided Trajectory Compression for Software Engineering Agents](https://mlsanity.com/paper/2609.08318/) (2026)
- [Context-Augmented Code Generation Using Programming Knowledge Graphs](https://mlsanity.com/paper/2601.20810/) (2026)
- [LongAttnComp: Cross-Family Context Compression for Long-Context Reasoning](https://mlsanity.com/paper/2606.01336/) (2026)
- [Shapley Context Pruning: A Cooperative Game Perspective for Context Reranking and Pruning](https://mlsanity.com/paper/2607.16209/) (2026)
- [RAGOCR: Optical Compression of Retrieval-Augmented Text via Visual Representation](https://mlsanity.com/paper/2608.00765/) (2026)
- [Lightweight Chunk Selection for Mobile Retrieval-Augmented Generation](https://mlsanity.com/paper/2608.03148/) (2026)
- [From Retrieved Context to Runtime Control: Adaptive Compression for Edge-based RAG](https://mlsanity.com/paper/2608.19535/) (2026)
- [Compression Beyond the Uncompressed: A Two-Stage Training Recipe for Soft Context Compression in RAG](https://mlsanity.com/paper/2609.05152/) (2026)

## Abstract (arXiv)

Retrieval-augmented generation improves various aspects of large language models (LLMs) generation, but suffers from computational overhead caused by long contexts as well as the propagation of irrelevant retrieved information into generated responses. Context pruning deals with both aspects, by removing irrelevant parts of retrieved contexts before LLM generation. Existing context pruning approaches are however limited, and do not provide a universal model that would be both efficient and robust in a wide range of scenarios, e.g., when contexts contain a variable amount of relevant information or vary in length, or when evaluated on various domains. In this work, we close this gap and introduce Provence (Pruning and Reranking Of retrieVEd relevaNt ContExts), an efficient and robust context pruner for Question Answering, which dynamically detects the needed amount of pruning for a given context and can be used out-of-the-box for various domains. The three key ingredients of Provence are formulating the context pruning task as sequence labeling, unifying context pruning capabilities with context reranking, and training on diverse data. Our experimental results show that Provence enables context pruning with negligible to no drop in performance, in various domains and settings, at almost no cost in a standard RAG pipeline. We also conduct a deeper analysis alongside various ablations to provide insights into training context pruners for future work.