概率同样重要：一种更忠实度量大型语言模型中自由文本解释忠实性的指标
The Probabilities Also Matter: A More Faithful Metric for Faithfulness of Free-Text Explanations in Large Language Models
AI总结：
本文提出相关解释忠实性指标CEF及相关反事实测试CCT，通过考虑预测标签分布的总偏移而非仅二元变化，更准确地度量大型语言模型自由文本解释的忠实性，并在Llama2模型上验证其能捕捉CT遗漏的忠实性方面。
摘要：
为了监督先进的人工智能系统，理解其底层决策过程非常重要。在被提示时，大型语言模型（LLMs）能够提供听起来合理并获得人类标注者高评分的自然语言解释或推理轨迹。然而，这些解释在多大程度上是忠实的，即真正捕捉到导致模型预测的因素，尚不清楚。在本工作中，我们引入了相关解释忠实性（Correlational Explanatory Faithfulness, CEF），这是一种可用于基于输入干预的忠实性测试的指标。此前在此类测试中使用的指标仅考虑预测中的二元变化。我们的指标考虑了模型预测标签分布的总偏移，从而更准确地反映解释的忠实性。随后，我们通过在Atanasova等人（2023）的反事实测试（Counterfactual Test, CT）上实例化CEF，引入了相关反事实测试（Correlational Counterfactual Test, CCT）。我们在三个自然语言处理任务上评估了由Llama2系列少样本提示的大型语言模型生成的自由文本解释的忠实性。我们发现，我们的指标度量了CT所遗漏的忠实性方面。
英文摘要：
In order to oversee advanced AI systems, it is important to understand their underlying decision-making process. When prompted, large language models (LLMs) can provide natural language explanations or reasoning traces that sound plausible and receive high ratings from human annotators. However, it is unclear to what extent these explanations are faithful, i.e., truly capture the factors responsible for the model's predictions. In this work, we introduce Correlational Explanatory Faithfulness (CEF), a metric that can be used in faithfulness tests based on input interventions. Previous metrics used in such tests take into account only binary changes in the predictions. Our metric accounts for the total shift in the model's predicted label distribution, more accurately reflecting the explanations' faithfulness. We then introduce the Correlational Counterfactual Test (CCT) by instantiating CEF on the Counterfactual Test (CT) from Atanasova et al. (2023). We evaluate the faithfulness of free-text explanations generated by few-shot-prompted LLMs from the Llama2 family on three NLP tasks. We find that our metric measures aspects of faithfulness which the CT misses.
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。
