add citation

app.py

@@ -1,8 +1,8 @@
 # coding=utf-8
-# Copyright 2024 The Mexa Authors.
+# Copyright 2024 The MEXA Authors.
 # Lint as: python3
 # This space is built based on uonlp/open_multilingual_llm_leaderboard.
-# Mexa Space
+# MEXA Space
 
 import os
 import json
@@ -122,16 +122,16 @@ table th:last-child {
 """
 
 
-TITLE = '<h1 align="center" id="space-title">Mexa: Multilingual Evaluation of Open English-Centric LLMs via Cross-Lingual Alignment</h1>'
+TITLE = '<h1 align="center" id="space-title">MEXA: Multilingual Evaluation of Open English-Centric LLMs via Cross-Lingual Alignment</h1>'
 
 INTRO_TEXT = f"""
 ## About
 
-We introduce Mexa, a method for assessing the multilingual capabilities of English-centric large language models (LLMs). Mexa builds on the observation that English-centric LLMs semantically use English as a kind of pivot language in their intermediate layers. Mexa computes the alignment between non-English languages and English using parallel sentences, estimating the transfer of language understanding capabilities from English to other languages through this alignment. This metric can be useful in estimating task performance, provided we know the English performance in the task and the alignment score between languages derived from a parallel dataset.
+We introduce MEXA, a method for assessing the multilingual capabilities of English-centric large language models (LLMs). MEXA builds on the observation that English-centric LLMs semantically use English as a kind of pivot language in their intermediate layers. Mexa computes the alignment between non-English languages and English using parallel sentences, estimating the transfer of language understanding capabilities from English to other languages through this alignment. This metric can be useful in estimating task performance, provided we know the English performance in the task and the alignment score between languages derived from a parallel dataset.
 
 ## Code
 
-https://github.com/cisnlp/Mexa
+https://github.com/cisnlp/MEXA
 
 ## Details
 We use parallel datasets from FLORES and the Bible. In the ARC style, we use mean pooling over layers, and the English score achieved by each LLM in the ARC benchmark is used to adjust the multilingual scores. In the Belebele style, we use max pooling over layers, and the English score achieved by each LLM in Belebele is used to adjust the multilingual scores.
@@ -141,12 +141,27 @@ We use parallel datasets from FLORES and the Bible. In the ARC style, we use mea
 CITATION = """
 ## Citation
 ```
-@article{kargaran2024mexa,
-title        = {Mexa: Multilingual Evaluation of {E}nglish-Centric {LLMs} via Cross-Lingual Alignment},
-author       = {Kargaran, Amir Hossein and Modarressi, Ali and Nikeghbal, Nafiseh  and Diesner, Jana and Yvon, François and Schütze, Hinrich},
-journal      = {arXiv preprint},
-year         = {2024},
-url          = {https://github.com/cisnlp/Mexa/}
+@inproceedings{kargaran-etal-2025-mexa,
+    title = "{MEXA}: Multilingual Evaluation of {E}nglish-Centric {LLM}s via Cross-Lingual Alignment",
+    author = "Kargaran, Amir Hossein  and
+      Modarressi, Ali  and
+      Nikeghbal, Nafiseh  and
+      Diesner, Jana  and
+      Yvon, Fran{\c{c}}ois  and
+      Schuetze, Hinrich",
+    editor = "Che, Wanxiang  and
+      Nabende, Joyce  and
+      Shutova, Ekaterina  and
+      Pilehvar, Mohammad Taher",
+    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
+    month = jul,
+    year = "2025",
+    address = "Vienna, Austria",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2025.findings-acl.1385/",
+    doi = "10.18653/v1/2025.findings-acl.1385",
+    pages = "27001--27023",
+    ISBN = "979-8-89176-256-5",
 }
 ```
 """