按照论文进行调整

This commit is contained in:
2025-02-14 10:21:52 +08:00
parent d2b3185e49
commit 6ec014962e
4 changed files with 53 additions and 51 deletions

View File

@@ -519,23 +519,23 @@ if __name__ == "__main__":
# qa_json_path_a=f"{EVAL_RESULT_PATH}/gpt-4o-2024-08-06/single_model_answer.json",
# qa_json_path_b=f"{EVAL_RESULT_PATH}/deepseek-reasoner/single_model_answer.json")
elo_evaluation(
qa_json_path_a=f"{EVAL_RESULT_PATH}/gemini-1.5-pro/single_model_answer.json",
qa_json_path_b=f"{EVAL_RESULT_PATH}/gpt-4o-2024-08-06/single_model_answer.json")
# elo_evaluation(
# qa_json_path_a=f"{EVAL_RESULT_PATH}/gemini-1.5-pro/single_model_answer.json",
# qa_json_path_b=f"{EVAL_RESULT_PATH}/gpt-4o-2024-08-06/single_model_answer.json")
elo_evaluation(
qa_json_path_a=f"{EVAL_RESULT_PATH}/gemini-1.5-pro/single_model_answer.json",
qa_json_path_b=f"{EVAL_RESULT_PATH}/gpt-4o-2024-08-06/single_model_answer_with_rag_cot.json")
# elo_evaluation(
# qa_json_path_a=f"{EVAL_RESULT_PATH}/gemini-1.5-pro/single_model_answer.json",
# qa_json_path_b=f"{EVAL_RESULT_PATH}/gpt-4o-2024-08-06/single_model_answer_with_rag_cot.json")
elo_evaluation(
qa_json_path_a=f"{EVAL_RESULT_PATH}/gemini-1.5-pro/single_model_answer.json",
qa_json_path_b=f"{EVAL_RESULT_PATH}/gpt-4o-2024-08-06/multiagent_with_rag_cot.json")
# elo_evaluation(
# qa_json_path_a=f"{EVAL_RESULT_PATH}/gemini-1.5-pro/single_model_answer.json",
# qa_json_path_b=f"{EVAL_RESULT_PATH}/gpt-4o-2024-08-06/multiagent_with_rag_cot.json")
elo_evaluation(
qa_json_path_a=f"{EVAL_RESULT_PATH}/gpt-4o-2024-08-06/single_model_answer.json",
qa_json_path_b=f"{EVAL_RESULT_PATH}/o3-mini/single_model_answer.json")
# elo_evaluation(
# qa_json_path_a=f"{EVAL_RESULT_PATH}/gpt-4o-2024-08-06/single_model_answer.json",
# qa_json_path_b=f"{EVAL_RESULT_PATH}/o3-mini/single_model_answer.json")
elo_evaluation(
qa_json_path_a=f"{EVAL_RESULT_PATH}/gpt-4o-2024-08-06/single_model_answer.json",
qa_json_path_b=f"{EVAL_RESULT_PATH}/deepseek-reasoner/single_model_answer.json")
# elo_evaluation(
# qa_json_path_a=f"{EVAL_RESULT_PATH}/gpt-4o-2024-08-06/single_model_answer.json",
# qa_json_path_b=f"{EVAL_RESULT_PATH}/deepseek-reasoner/single_model_answer.json")
pass