Updated leaderboard description

src/about.py

@@ -101,7 +101,7 @@ TITLE = """<h1 align="center" id="space-title">🚀 EVALITA-LLM Leaderboard 🚀
 
 # What does your leaderboard evaluate?
 INTRODUCTION_TEXT = """
-Evalita-LLM is a benchmark designed to evaluate Large Language Models (LLMs) on Italian tasks. The distinguishing features of Evalita-LLM are the following: (i) **all tasks are native Italian**, avoiding translation issues and potential cultural biases; (ii) the benchmark includes **generative** tasks, enabling more natural interaction with LLMs; (iii) **all tasks are evaluated against multiple prompts**, this way mitigating the model sensitivity to specific prompts and allowing a fairer evaluation.
+Evalita-LLM is a benchmark designed to evaluate Large Language Models (LLMs) on Italian tasks. The distinguishing features of Evalita-LLM are the following: (i) **all tasks are native Italian**, avoiding translation issues and potential cultural biases; (ii) the benchmark includes **generative** tasks, enabling more natural interaction with LLMs; (iii) **all tasks are evaluated against multiple prompts**, this way mitigating the model sensitivity to specific prompts and allowing a fairer evaluation. To provide a comprehensive evaluation, Evalita-LLM leverages the **Combined Performance Score (CPS)**, which combines both the peak and average performance of models across multiple prompts.
  
 **<small>Multiple-choice tasks:</small>** <small> 📊TE (Textual Entailment), 😃SA (Sentiment Analysis), ⚠️HS (Hate Speech Detection), 🏥AT (Admission Test), 🔤WIC (Word in Context), ❓FAQ (Frequently Asked Questions) </small><br>
 **<small>Generative tasks:</small>** <small>🔄LS (Lexical Substitution), 📝SU (Summarization), 🏷️NER (Named Entity Recognition), 🔗REL (Relation Extraction) </small>