Update README.md

README.md

@@ -14,10 +14,11 @@ Provence is a lightweight **context pruning model** for retrieval-augmented gene
 
 *Developed by*: Naver Labs Europe  
 *License*: [CC BY-NC 4.0.](https://creativecommons.org/licenses/by-nc/4.0/)  
+*Paper*: https://arxiv.org/abs/2501.16214, accepted to ICLR 2025
 * *Model*: `provence-reranker-debertav3-v1` (Provence for Pruning and Reranking Of retrieVEd relevaNt ContExt)  
 * *Backbone model*: [DeBERTav3-reranker](https://huggingface.co/naver/trecdl22-crossencoder-debertav3) (trained from [DeBERTa-v3-large](https://huggingface.co/microsoft/deberta-v3-large))  
 * *Model size*: 430 million parameters  
-* *Context length*: 512 tokens  
+* *Context length*: 512 tokens
 
 ## Usage
 
@@ -47,8 +48,6 @@ provence_output = provence.process(question, context, always_select_title=True)
 # Provence Output: {'reranking_score': 3.022725, pruned_context': 'Shepherd’s pie. In early cookery books, the dish was a means of using leftover roasted meat of any kind, and the pie dish was lined on the sides and bottom with mashed potato, as well as having a mashed potato crust on top.']]
 ```
 
-Training code, as well as RAG experiments with Provence can be found in the [BERGEN](https://github.com/naver/bergen) library. 
-
 ## Model interface
 
 Interface of the `process` function:
@@ -68,9 +67,7 @@ Interface of the `process` function:
 * **Provence automatically detects the number of sentences to keep**, based on a threshold. We found that the default value of a threshold works well across various domains, but the threshold can be adjusted further to better meet the particular use case needs.
 * **Provence is robust to various domains**, being trained on a combination of diverse MS Marco and Natural Questions data.
 * **Provence works out-of-the-box with any LLM**.
-* **Provence is fast**: we release a standalone DeBERTa-based model [here]() and a unified reranking+context pruning model, which incorporates context pruning into reranking, an already existing stage of modern RAG pipelines. The latter makes context pruning basically zero cost in the RAG pipeline!
 
-More details are available in the [blogpost]().
 
 ## Model Details
 
@@ -82,7 +79,7 @@ More details are available in the [blogpost]().
 * Context length: 512 tokens (similar to the pretrained DeBERTa model)
 * Evaluation: we evaluate Provence on 7 datasets from various domains: Wikipedia, biomedical data, course syllabi, and news. We find that Provence is able to prune irrelevant sentences with little-to-no drop in performance, in all domains, and outperforms existing baselines on the Pareto front (top right corners of the plots).
 
-Check out more analysis in the [paper]()!
+Check out more analysis in the [paper](https://arxiv.org/abs/2501.16214)!
 
 <img src="https://cdn-uploads.huggingface.co/production/uploads/6273df31c3b822dad2d1eef2/WMmfsNG48O830paaBAaQF.png" width="600">
 
@@ -94,14 +91,14 @@ This work is licensed under CC BY-NC 4.0.
 ## Cite
 
 ```
-@misc{chirkova2024provence,
+@misc{chirkova2025provenceefficientrobustcontext,
       title={Provence: efficient and robust context pruning for retrieval-augmented generation}, 
       author={Nadezhda Chirkova and Thibault Formal and Vassilina Nikoulina and Stéphane Clinchant},
-      year={2024},
-      eprint={?},
+      year={2025},
+      eprint={2501.16214},
       archivePrefix={arXiv},
       primaryClass={cs.CL},
-      copyright = {Creative Commons Attribution Non Commercial Share Alike 4.0 International}
+      url={https://arxiv.org/abs/2501.16214}, 
 }
 ```