Improving Factuality in Large Language Models via Decoding-Time Hallucinatory

本文是LLM系列文章,针对《Improving Factuality in Large Language Models via Decoding-Time Hallucinatory and Truthful Comparators》的翻译。

通过解码时幻觉和真实比较器提高大型语言模型的真实性

摘要

尽管其能力非凡,大型语言模型(LLM)很容易生成与可验证事实相矛盾的响应,即不忠实的幻觉内容。现有的工作通常集中在优化模型参数或编辑语义表示,这会损害目标LLM的内部事实知识。此外,幻觉通常在下游任务中表现出多方面的模式,限制了模型跨任务的整体性能。在本文中,我们提出了一种比较器驱动的解码时间(CDT)框架来减轻响应幻觉。首先,我们利用多任务微调样本构建幻觉和真实的比较器。在这种情况下,我们提出了一种指令原型引导的专家混合策略,以增强相应比较器在不同任务指令中捕获不同幻觉或真实模式的能力。 CDT通过对比目标 LLM 和这些比较器之间的 logit 差异,将下一个token预测限制为事实稳健的分布。对多个下游任务的系统实验表明,我们的框架可以显着提高模型性能和响应真实性。

1 引言

2 相关工作

3 方法

4 实验

5 结论

在本文中,我们介绍了 CDT,这是一种解码时框架,可通过幻觉和真实比较器有效消除目标 LLM 的多方面幻觉困境。我们设计了一种以指令原型为指导的专家策略混合体,以赋予比较者不同的幻觉/真实意识掌握能力。 CDT 通过控制

### 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