From b33fdfecf9bf01f02f927073a0bbc722bb572e32 Mon Sep 17 00:00:00 2001
From: Vladislav Mikhailov <43072268+vmkhlv@users.noreply.github.com>
Date: Fri, 2 May 2025 14:51:36 +0200
Subject: [PATCH] updated citation

---
 README.md | 26 +++++++++++++++++++++-----
 1 file changed, 21 insertions(+), 5 deletions(-)

diff --git a/README.md b/README.md
index 86cdcfd..7f16cd3 100644
--- a/README.md
+++ b/README.md
@@ -84,11 +84,27 @@ The machine-generated texts are edited by an in-house team of annotators, who ar
 ## Cite us
 
 ```
-@article{artemova2024beemo,
-  title={Beemo: Benchmark of Expert-edited Machine-generated Outputs},
-  author={Artemova, Ekaterina and Lucas, Jason and Venkatraman, Saranya and Lee, Jooyoung and Tilga, Sergei and Uchendu, Adaku and Mikhailov, Vladislav},
-  journal={arXiv preprint arXiv:2411.04032},
-  year={2024}
+@inproceedings{artemova-etal-2025-beemo,
+    title = "Beemo: Benchmark of Expert-edited Machine-generated Outputs",
+    author = "Artemova, Ekaterina  and
+      Lucas, Jason S  and
+      Venkatraman, Saranya  and
+      Lee, Jooyoung  and
+      Tilga, Sergei  and
+      Uchendu, Adaku  and
+      Mikhailov, Vladislav",
+    editor = "Chiruzzo, Luis  and
+      Ritter, Alan  and
+      Wang, Lu",
+    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
+    month = apr,
+    year = "2025",
+    address = "Albuquerque, New Mexico",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2025.naacl-long.357/",
+    pages = "6992--7018",
+    ISBN = "979-8-89176-189-6",
+    abstract = "The rapid proliferation of large language models (LLMs) has increased the volume of machine-generated texts (MGTs) and blurred text authorship in various domains. However, most existing MGT benchmarks include single-author texts (human-written and machine-generated). This conventional design fails to capture more practical multi-author scenarios, where the user refines the LLM response for natural flow, coherence, and factual correctness. Our paper introduces the Benchmark of Expert-edited Machine-generated Outputs (Beemo), which includes 6.5k texts written by humans, generated by ten instruction-finetuned LLMs, and edited by experts for various use cases, ranging from creative writing to summarization. Beemo additionally comprises 13.1k machine-generated and LLM-edited texts, allowing for diverse MGT detection evaluation across various edit types. We document Beemo`s creation protocol and present the results of benchmarking 33 configurations of MGT detectors in different experimental setups. We find that expert-based editing evades MGT detection, while LLM-edited texts are unlikely to be recognized as human-written. Beemo and all materials are publicly available."
 }
 ```