CELL 你的模型：面向大语言模型的对比解释
CELL your Model: Contrastive Explanations for Large Language Models
AI总结：
本文提出仅需黑盒查询访问的 LLM 对比解释方法，利用用户可理解的评分函数和预算约束算法生成轻微修改提示下的对比响应，以解释模型输出。
摘要：
黑盒深度神经网络分类模型的出现，引发了解释其决策的需求。然而，在生成式 AI（例如大语言模型，LLM）的情形中，并不存在可供解释的类别预测。相反，人们可以追问：为什么 LLM 会针对给定提示输出某个特定响应。本文中，我们通过提出一种仅需黑盒/查询访问权限的对比解释方法来回答这一问题。我们的解释表明，LLM 之所以会对给定提示输出某个回复，是因为如果该提示被轻微修改，LLM 就会给出不同的响应：该响应要么较不可取，要么与原始响应相矛盾。关键洞见在于，对比解释只需要一个对用户有意义的评分函数，而不必是某种特定的实值量（即类别标签）。为此，我们提出了一种新颖的预算约束算法，这也是我们的主要算法贡献；该算法基于此类评分函数智能地构造对比，同时遵守查询预算，而这对于较长上下文是必要的。我们在开放文本生成和聊天机器人对话等重要自然语言任务上展示了该方法的有效性。
英文摘要：
The advent of black-box deep neural network classification models has sparked the need to explain their decisions. However, in the case of generative AI, such as large language models (LLMs), there is no class prediction to explain. Rather, one can ask why an LLM output a particular response to a given prompt. In this paper, we answer this question by proposing a contrastive explanation method requiring simply black-box/query access. Our explanations suggest that an LLM outputs a reply to a given prompt because if the prompt was slightly modified, the LLM would have given a different response that is either less preferable or contradicts the original response. The key insight is that contrastive explanations simply require a scoring function that has meaning to the user and not necessarily a specific real valued quantity (viz. class label). To this end, we offer a novel budgeted algorithm, our main algorithmic contribution, which intelligently creates contrasts based on such a scoring function while adhering to a query budget, necessary for longer contexts. We show the efficacy of our method on important natural language tasks such as open-text generation and chatbot conversations.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
