Update README.md

README.md

@@ -56,10 +56,11 @@ model_id = "Shinapri/Matellem-Gemma3n-E2B-Graphene-1"
 model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto").eval()
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 
-INSTRUCTION = "You are a scientific literature search expert. Your task is to identify the title of a research paper based on a user's description of its key methods and findings."
-USER_INPUT = """I'm looking for a paper about manipulating graphene plasmons. 
-The key method involved using a ferroelectric nanocavity array to create a periodic doping pattern on the graphene. 
-I remember they could tune the plasmon resonance by dynamically changing the applied gate voltage. Can you identify the title?"""
+INSTRUCTION = "You are a scientific literature search expert. Your task is to suggest a likely title for a research paper based on the user's description."
+USER_INPUT = """I'm trying to recall the title of a review paper I read.
+It discussed the applications of graphene specifically in the field of neuroscience,
+covering two main areas: its use as a carrier for drug delivery and as a conductive substrate for tissue engineering.
+Can you suggest a likely title?"""
 
 messages = [
     {"role": "system", "content": [{"type": "text", "text": INSTRUCTION}]},
@@ -86,9 +87,9 @@ with torch.no_grad():
 
 The model's response for this query is highly relevant:
 
-    > The title of the paper is likely: **"Voltage-tunable plasmonics on few-layer graphene based on a ferroelectric nanocavity array"**
+    > Based on your description, a likely title for the review paper is: **Graphene in Neuroscience: Applications in Drug Delivery and Tissue Engineering**
 
-For reference, the original paper's title is **"Tunable plasmonic devices by integrating graphene with ferroelectric nanocavity"**. A cosine similarity score of **0.9638** was obtained when comparing the embeddings of these two titles using the `intfloat/e5-large` model.
+For reference, the original paper's title is **"Interfacing Graphene-Based Materials With Neural Cells"**. A cosine similarity score of **0.9396** was obtained when comparing the embeddings of these two titles using the `intfloat/e5-large` model.
 -----
 
 ## Future Work / Roadmap