Improving the Robustness of Large Language Models via Consistency Alignment

本文分析大型语言模型(LLM)在遵循指令时的不稳定性,并提出一个两阶段训练框架。第一阶段通过指令增强监督微调提升模型概括能力,第二阶段采用一致性对齐训练使模型能区分相似响应中的细微差异,从而提高生成响应的稳健性和一致性。实验证明该框架在Vicuna和Llama 2上的有效性,且不需要额外的人类指导或奖励模型。

摘要生成于 C知道 ,由 DeepSeek-R1 满血版支持, 前往体验 >

本文是LLM系列文章,针对《Improving the Robustness of Large Language Models via Consistency Alignment》的翻译。

摘要

大型语言模型(LLM)在遵循用户指令和生成有用的响应方面取得了巨大成功。尽管如此,它们的鲁棒性仍远未达到最佳状态,因为它们可能会由于口头指令的微小变化而产生明显不一致的响应。最近的文献探讨了这一不一致性问题,强调了持续改进响应生成稳健性的重要性。然而,仍然缺乏系统的分析和解决方案。在本文中,我们定量地定义了不一致性问题,并提出了一个由指令增强监督微调和一致性对齐训练组成的两阶段训练框架。第一阶段通过类似的指令扩充帮助模型概括以下指令。在第二阶段,我们提高了多样性,并通过区分相似反应中的细微差异,帮助模型了解哪些反应更符合人类的期望。训练过程是在不参考外部人力偏好资源的情况下,通过从第一阶段训练的模型中推断出的自我奖励来完成的。我们对最近公开的LLM进行了广泛的实验,以完成指令跟随任务,并证明了我们的训练框架的有效性。

1 引言

2 相关工作

3 指令遵循的稳健性

4 通过一致性调整训练大型语言模型

5

### 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