docs: separate results in own header

Author: Guilhem Santé

README.md

@@ -4,7 +4,11 @@
 
 ## Overview
 
-The present repository proposes a benchmarking framework to easily evaluate LLMs' capacity to predict argument relations at the micro-scale level (only guessing the relation between pairs of arguments). The framework is intended to be used with a [preprocessed sample of a dataset from the IBM Debater project](https://huggingface.co/datasets/coding-kelps/liaisons-claim-stance-sample). The obtained results can be found [here](https://huggingface.co/datasets/coding-kelps/liaisons-experiments-results).
+The present repository proposes a benchmarking framework to easily evaluate LLMs' capacity to predict argument relations at the micro-scale level (only guessing the relation between pairs of arguments). The framework is intended to be used with a [preprocessed sample of a dataset from the IBM Debater project](https://huggingface.co/datasets/coding-kelps/liaisons-claim-stance-sample).
+
+## Results
+
+You can found my own results [here](https://huggingface.co/datasets/coding-kelps/liaisons-experiments-results).
 
 ## About Contributions
 
@@ -25,6 +29,7 @@ This work is part of a collection of works whose ultimate goal is to deliver a f
 This project is solely conducted by me, [Guilhem Santé](https://github.com/guilhem-sante). I am a postgraduate student pursuing the MSc in Artificial Intelligence at Heriot-Watt University in Edinburgh.
 
 ## Special Thanks
+
 I would like to credits [Andrew Ireland](http://www.macs.hw.ac.uk/~air/), my supervisor for this project.
 
 <img src="https://upload.wikimedia.org/wikipedia/commons/thumb/0/03/Heriot-Watt_University_logo.svg/1200px-Heriot-Watt_University_logo.svg.png" width="300">