Changes between Version 49 and Version 50 of Other/Summer/2025/LLM-Based
- Timestamp:
- Aug 4, 2025, 6:17:58 PM (6 days ago)
Legend:
- Unmodified
- Added
- Removed
- Modified
-
Other/Summer/2025/LLM-Based
v49 v50 103 103 104 104 === Week 6: [[https://docs.google.com/presentation/d/1kDA0WvySDhgNF3oL3f_RUOrDJkoCKAPEo4WWE-8NvEE/edit?slide=id.g3639082186e_1_155#slide=id.g3639082186e_1_155|Slides]] 105 106 Used SVM to find features to input to the LLM. Using said features, we created a prompt that would allow the LLM to understand and categorize the raw data in the .txt files. Then, we compared the results of LLM vs SVM, achieving an accuracy of ~98% vs ~94%, respectively. This is probably due to the inherit nature of how LLMs and SVMs work, as SVMs are more black and white, categorizing based on only the data inputted as training, while LLM is blurs the lines, allowing for a more free interpretation of the small variations in the same dataset, allowing it to interpret the variations in the same movement correctly, unlike the SVM. 107 108 [[Image(SVM&LLM-ConfusionChart.png, width=1000, height=400)]] 109 105 110 ---- 106 Used SVM to find features to input to the LLM. Using said features, we created a prompt that would allow the LLM to understand and categorize the raw data in the .txt files.107 108 109 111 Questions or contributions? Please contact us. 110 112
