docs(readme): add images to README and make minor content refinements

Author: doctorbanu

README.md

@@ -6,7 +6,7 @@
 This repository presents the **ELO2 – GREEN AI Project**, developed
 within the **MIT Emerging Talent – AI & ML Program (2025)**. The work
 investigates the technical performance, sustainability traits, and
-human-perceived quality of **open-source small language models (SLMs)**
+human-perceived quality of **open-source language models**
 compared to commercial systems.
 
 ---
@@ -18,6 +18,8 @@ compared to commercial systems.
 **To what extent can open-source LLMs provide competitive output quality
 while operating at significantly lower environmental cost?**
 
+![image](readme_images/trade-off.png)
+
 ### Motivation
 
 Large commercial LLMs deliver strong performance but demand substantial
@@ -30,6 +32,8 @@ alternatives for everyday tasks.
 
 ## 🧪 Methods
 
+![image](readme_images/project-timeline.png)
+
 ### 1. Model Families
 
 The study evaluates several open-source model groups:
@@ -45,15 +49,13 @@ The study evaluates several open-source model groups:
 These configurations serve as the optimized open-source setups used in
 the comparison against commercial models.
 
----
-
 ### 2. Tasks & Dataset
 
 Evaluation tasks include:
 
 - summarization
 - factual reasoning
-- paraphasing
+- paraphrasing
 - short creative writing
 - instruction following
 - question answering
@@ -64,8 +66,6 @@ directly from this shared material. Using a single, consistent source ensured
 that every model was tested under identical informational conditions, allowing
 clear and fair comparison of output quality and relevance.
 
----
-
 ### 3. RAG Pipeline
 
 Retrieval-Augmented Generation (RAG) was applied to multiple model
@@ -78,8 +78,6 @@ families. The pipeline includes:
 
 RAG improved factual grounding in nearly all models.
 
----
-
 ### 4. Recursive Editing Framework
 
 A lightweight iterative refinement procedure was implemented:
@@ -100,21 +98,17 @@ A lightweight iterative refinement procedure was implemented:
 This approach allowed weaker SLMs to yield higher-quality results
 without relying on large models.
 
----
-
 ### 5. Environmental Measurement
 
 Environmental footprint data was captured with **CodeCarbon**, recording:
 
 - CPU/GPU energy usage
-- carbon emissions
+- Carbon emissions
 - PUE-adjusted overhead
 
 These measurements enabled comparison with published metrics for
 commercial LLMs.
 
----
-
 ### 6. Human Evaluation (Single-Blind)
 
 A structured Google Form experiment collected:
@@ -126,6 +120,14 @@ A structured Google Form experiment collected:
 Outputs were randomized and anonymized to avoid bias. This provided a
 perception-based counterpart to technical evaluation.
 
+### 7. Analysing the Results
+
+....
+
+### 8. Publishing an Article
+
+....
+
 ---
 
 ## 📊 Key Findings
@@ -135,7 +137,49 @@ perception-based counterpart to technical evaluation.
 - FINDING3.....
 - FINDING4.....
 
-More detailed results are included in the research article.
+---
+
+## 🔮 Future Work
+
+- Evaluate additional open-source model families across diverse tasks
+- Test optimized pipelines in specialized domains (medical, legal, technical writing)
+- Track carbon footprint across full lifecycle (training to deployment)
+- Conduct ablation studies isolating RAG vs. recursive editing contributions
+
+---
+
+## 📢 Communication Strategy
+
+The research findings will be shared through formats designed for different
+audiences and purposes:
+
+### For Researchers
+
+A comprehensive research article will document the complete experimental design,
+statistical analysis, and implications.
+
+🔗 **[View Aticle](link1)**
+
+### For Practitioners & Educators
+
+An executive presentation provides a visual overview of the research question,
+methodology, and key findings without requiring deep technical background.
+
+🔗 **[View Presentation](link2)**
+
+### For the Community
+
+A public evaluation study invites participation in assessing AI-generated texts.
+This crowdsourced data forms a critical component of the research.
+
+🔗 **[Participate in Study](link3)**
+
+### For Reproducibility
+
+All materials (dataset, prompts, model outputs, evaluation scripts, and carbon
+tracking logs) are publicly available in this repository.
+
+🔗 **[Browse Repository](https://github.com/banuozyilmaz2-jpg/ELO2-GREEN-AI)**
 
 ---
 
@@ -152,5 +196,5 @@ More detailed results are included in the research article.
 
 ## 🙏 Acknowledgments
 
-Special thanks to the **MIT Emerging Talent Program** for their
-guidance and feedback throughout the project.
+Special thanks to the **MIT Emerging Talent Program** for their guidance and
+feedback throughout the project.