Fine-tuning Large Language Models for Entity Matching

Benchmark Model Rank Results
entity-resolution-on-abt-buygpt-4o-mini-2024-07-18_fine_tuned#3F1 (%): 94.09
entity-resolution-on-abt-buygpt-4o-2024-08-06#4F1 (%): 92.20
entity-resolution-on-abt-buygpt-4o-mini-2024-07-18#8F1 (%): 87.68
entity-resolution-on-abt-buyMeta-Llama-3.1-8B-Instruct_fine_tuned#9F1 (%): 87.34
entity-resolution-on-abt-buyMeta-Llama-3.1-70B-Instruct#12F1 (%): 79.12
entity-resolution-on-abt-buyMeta-Llama-3.1-8B-Instruct#15F1 (%): 56.57
entity-resolution-on-amazon-googlegpt-4o-mini-2024-07-18_fine_tuned#2F1 (%): 80.25
entity-resolution-on-amazon-googlegpt-4o-2024-08-06#11F1 (%): 63.45
entity-resolution-on-amazon-googlegpt-4o-mini-2024-07-18#12F1 (%): 59.20
entity-resolution-on-amazon-googleMeta-Llama-3.1-70B-Instruct#14F1 (%): 51.44
entity-resolution-on-amazon-googleMeta-Llama-3.1-8B-Instruct_fine_tuned#15F1 (%): 50.00
entity-resolution-on-amazon-googleMeta-Llama-3.1-8B-Instruct#16F1 (%): 49.16
entity-resolution-on-wdc-products-80-cc-seengpt-4o-2024-08-06_fine_tuned_wdc_small#2F1 (%): 87.10
entity-resolution-on-wdc-products-80-cc-seengpt-4o-mini-2024-07-18_structured_explanations#3F1 (%): 84.38
entity-resolution-on-wdc-products-80-cc-seengpt-4o-mini-2024-07-18#4F1 (%): 81.61
entity-resolution-on-wdc-products-80-cc-seenLlama3.1_70B_structured_explanations#6F1 (%): 76.70
entity-resolution-on-wdc-products-80-cc-seenLlama3.1_70B#7F1 (%): 75.20
entity-resolution-on-wdc-products-80-cc-seenLlama3.1_8B_error-based_example_selection#8F1 (%): 74.37
entity-resolution-on-wdc-products-80-cc-seenLlama3.1_8B_structured_explanations#9F1 (%): 74.13
entity-resolution-on-wdc-products-80-cc-seenLlama3.1_8B#13F1 (%): 53.36