Update README.md

README.md

@@ -12,8 +12,8 @@ tags:
 ---
 
 This model is part of the [GrammarCorrector](https://github.com/akhmat-s/GrammarCorrector) tool.
+The primary objective of the experiment was to develop a highly effective tool using relatively small models, minimal datasets, and constrained computational resources.
 
-Fine-tuning for the FlanT5 model uses a dataset called [JFLEG](https://arxiv.org/abs/1702.04066). The primary objective of the experiment was to develop a highly effective tool using a minimal dataset.
-
-To accomplish this goal, we implement the key strategy:
-- [Perplexity-Based Data](https://arxiv.org/abs/2405.20541) Pruning With Small Reference Models.
+To accomplish this goal, we implemented two key strategies:
+- [Perplexity-Based Data](https://arxiv.org/abs/2405.20541) Pruning With Small Reference Models.
+- A simple sampling and voting method for [multiple LLM agents](https://arxiv.org/abs/2402.05120).