基于人类反馈训练的奖励模型

训练的奖励模型（RM）根据给定的问题，预测哪个生成的答案被人类评为更好。

RM在以下领域中很有用：

• QA模型评估
• 作为RLHF中的奖励分数

所有模型都使用同一种数据集分割种子进行训练（如果没有可用的验证分割）

• webgpt_comparisons
• summarize_from_feedback
• synthetic-instruct-gptj-pairwise

如何使用

from transformers import AutoModelForSequenceClassification, AutoTokenizer
reward_name = "OpenAssistant/reward-model-deberta-v3-large"
rank_model, tokenizer = AutoModelForSequenceClassification.from_pretrained(reward_name), AutoTokenizer.from_pretrained(reward_name)
question, answer = "Explain nuclear fusion like I am five", "Nuclear fusion is the process by which two or more protons and neutrons combine to form a single nucleus. It is a very important process in the universe, as it is the source of energy for stars and galaxies. Nuclear fusion is also a key process in the production of energy for nuclear power plants."
inputs = tokenizer(question, answer, return_tensors='pt')
score = rank_model(**inputs).logits[0].cpu().detach()
print(score)

性能

验证分割准确性

很可能SytheticGPT在选择-拒绝对中存在某种表面模式，这使得区分更好的答案变得容易。