Add Method Card

README.md

@@ -30,14 +30,16 @@ Same train/val/test as fine-tuning; we report metrics/CMs and discuss quality/la
 - Cleaning: strip text; drop empty/NA
 
 ## Models / APIs
-- LLM: (fill in, e.g., gpt-4o-mini / llama-3.1-instruct / etc.)
-- Similarity: TF-IDF + cosine (sklearn)
+- **LLM used:** gpt-4o-mini (OpenAI API, September 2025 snapshot)  
+- **Similarity backend:** sklearn TF-IDF + cosine similarity 
 
 ## Prompting Strategy
 - Zero-shot: instruction + schema (return 0 or 1 only).
 - Adaptive one-shot: retrieve most similar train example and include it as exemplar.
 - Adaptive 5-shot: retrieve top-5 similar exemplars.
 
+
+
 ## Evaluation Protocol
 - Metrics: accuracy, precision, recall, F1; confusion matrix
 - Latency: avg wall-clock per example
@@ -56,8 +58,8 @@ Same train/val/test as fine-tuning; we report metrics/CMs and discuss quality/la
 
 ## Tradeoffs
 - Quality: zero-shot ≈ 5-shot ≥ one-shot on this dataset.
-- Latency: increases with K (prompt length).
-- Cost: increases with K for token-billed APIs.
+- Latency: increases with K (see Results section; ~0.28s/ex for zero-shot → ~0.45s/ex for 5-shot).  
+- Cost: scales roughly linearly with prompt length (token count). For this dataset (~20 examples), 5-shot prompts were ~3× the token usage of zero-shot.
 
 ## Limits & Risks
 - No leakage: retrieve exemplars from **train** only.