From f68009a2b03a8cf79a659ddc4814d2d42c400d89 Mon Sep 17 00:00:00 2001 From: Long Kim <lkim@cl.uni-heidelberg.de> Date: Fri, 28 Mar 2025 23:29:34 +0100 Subject: [PATCH] Add requirements.txt --- README.md | 6 +++++- requirements.txt | 6 ++++++ 2 files changed, 11 insertions(+), 1 deletion(-) create mode 100644 requirements.txt diff --git a/README.md b/README.md index 447f46d..b23829f 100644 --- a/README.md +++ b/README.md @@ -2,6 +2,10 @@ ## Code for paper "G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment" [https://arxiv.org/abs/2303.16634] +## Model Evaluations + +Score prediction via gemini_eval.py, llama3_eval.py, qwen_eval.py + ## Experiments on SummEval dataset Full dataset used by G-Eval paper @@ -15,7 +19,7 @@ Sample dataset used for CoT analysis ## Prompts and Evaluation Results Prompts used to evaluate SummEval with GPT-4 & base and detailed prompts for CoT analysis are in prompts/summeval (by G-Eval paper) -Auto-CoT prompts are in prompts/cot_analysis +Auto-CoT prompts are in prompts/cot_analysis (created via auto_cot.py) GPT-4 G-eval results on SummEval are in results (by G-Eval paper) Other models results are in their respective folder \ No newline at end of file diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000..a1e8c71 --- /dev/null +++ b/requirements.txt @@ -0,0 +1,6 @@ +groq==0.20.0 +openai==1.69.0 +prettytable==3.16.0 +protobuf==6.30.2 +scipy==1.15.2 +tqdm==4.67.1 -- GitLab