Prompting Large Language Models with Rationale Heuristics for Knowledge-based Visual Question Answer

本文是LLM系列文章,针对《Prompting Large Language Models with Rationale Heuristics for Knowledge-based Visual Question Answering》的翻译。

基于知识的可视化问答中基于理性启发式的大型语言模型

摘要

最近,大型语言模型(LLM)已被用于基于知识的视觉问答(VQA)。尽管之前的研究结果令人鼓舞,但之前的方法促使LLM直接预测答案,忽略了中间的思维过程。我们认为,现有的方法不能充分激活LLM的能力。我们提出了一个名为PLRH的框架,该框架通过基于知识的VQA的基本原理启发式来提示LLM。PLRH提示具有思维链(CoT)的LLM生成逻辑推理启发式,即中间思维过程,然后利用逻辑推理启发式来激励LLM预测答案。实验表明,我们的方法在OK-VQA和A-OKVQA上分别比现有的基线高出2.2和2.1以上。

1 引言

2 相关工作

### 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