New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Models

本文是LLM系列,针对《New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Models》的翻译。

摘要

生成准确的逐步推理对于大型语言模型(LLM)解决复杂问题、增强鲁棒性和可解释性至关重要。尽管关于开发高级推理方法的研究层出不穷,但系统分析生成推理链中的各种LLM和推理策略仍然是一个重大挑战。困难源于缺乏两个关键要素:(1)用于评估不同任务上生成的推理链的自动方法,以及(2)用于系统比较的不同推理方法的统一形式和实现。本文旨在填补这一空白:(1)我们引入了AutoRace用于全自动推理链评估。现有的指标依赖于昂贵的人工注释或预定义的LLM提示,无法适应不同的任务。相比之下,AutoRace会自动为每个任务创建详细的评估标准,并使用GPT-4根据标准进行准确评估。(2)我们开发了LLM Reasoners,这是一个在搜索、奖励和世界模型组件的统一公式下,对现有和新的推理算法进行标准化模块化实现的库。通过新的评估和库,(3)我们对不同的推理方法(如CoT、ToT、RAP)进行了广泛的研究。该分析揭示了关于影响推理的不同因素的有趣发现,包括奖励指导、搜索的广度与深度、世界模型和提示格式等。

1 引言

2 相关工作

3 AutoRace:自动推理链评估

4 LLM推理机:统一的公式和库

### Chain-of-Thought Prompting Mechanism in Large Language Models In large language models, chain-of-thought prompting serves as a method to enhance reasoning capabilities by guiding the model through structured thought processes. This approach involves breaking down complex problems into simpler components and providing step-by-step guidance that mirrors human cognitive processing. The creation of these prompts typically includes selecting examples from training datasets where each example represents part of an overall problem-solving process[^2]. By decomposing tasks into multiple steps, this technique encourages deeper understanding and more accurate predictions compared to traditional methods. For instance, when faced with multi-hop question answering or logical deduction challenges, using such chains allows models not only to generate correct answers but also articulate intermediate thoughts leading up to those conclusions. Such transparency facilitates better interpretability while improving performance on various NLP benchmarks. ```python def create_chain_of_thought_prompt(task_description, examples): """ Creates a chain-of-thought prompt based on given task description and examples. Args: task_description (str): Description of the task at hand. examples (list): List containing tuples of input-output pairs used for demonstration purposes. Returns: str: Formatted string representing the final prompt including both instructions and sample cases. """ formatted_examples = "\n".join([f"Input: {ex[0]}, Output: {ex[1]}" for ex in examples]) return f""" Task: {task_description} Examples: {formatted_examples} Now try solving similar questions following above pattern. """ # Example usage examples = [ ("What color do you get mixing red and blue?", "Purple"), ("If it rains tomorrow, will we have our picnic?", "No") ] print(create_chain_of_thought_prompt("Solve logic puzzles", examples)) ```
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

UnknownBody

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值