Large language models (LLMs) such as ChatGPT have demonstrated superior
performance on a variety of natural language processing (NLP) tasks including
sentiment analysis, mathematical reasoning and summarization. Furthermore,
since these models are instruction-tuned on human conversations to produce
"helpful" responses, they can and often will produce explanations along with
the response, which we call self-explanations. For example, when analyzing the
sentiment of a movie review, the model may output not only the positivity of
the sentiment, but also an explanation (e.g., by listing the sentiment-laden
words such as "fantastic" and "memorable" in the review). How good are these
automatically generated self-explanations? In this paper, we investigate this
question on the task of sentiment analysis and for feature attribution
explanation, one of the most commonly studied settings in the interpretability
literature (for pre-ChatGPT models). Specifically, we study different ways to
elicit the self-explanations, evaluate their faithfulness on a set of
evaluation metrics, and compare them to traditional explanation methods such as
occlusion or LIME saliency maps. Through an extensive set of experiments, we
find that ChatGPT's self-explanations perform on par with traditional ones, but
are quite different from them according to various agreement metrics, meanwhile
being much cheaper to produce (as they are generated along with the
prediction). In addition, we identified several interesting characteristics of
them, which prompt us to rethink many current model interpretability practices
in the era of ChatGPT(-like) LLMs.

ChatGPT 的自解释性能与传统方法相媲美，在成本较低的情况下，且具有许多有趣的特性，促使我们重新思考当前在 ChatGPT（类似的 LLM）时代的模型可解释性实践。

大型语言模型能否自我解释？LLM 生成自解释的研究

Can Large Language Models Explain Themselves? A Study of LLM-Generated  Self-Explanations

For many prediction tasks, stakeholders desire not only predictions but also
supporting evidence that a human can use to verify its correctness. However, in
practice, additional annotations marking supporting evidence may only be
available for a minority of training examples (if available at all). In this
paper, we propose new methods to combine few evidence annotations (strong
semi-supervision) with abundant document-level labels (weak supervision) for
the task of evidence extraction. Evaluating on two classification tasks that
feature evidence annotations, we find that our methods outperform baselines
adapted from the interpretability literature to our task. Our approach yields
substantial gains with as few as hundred evidence annotations. Code and
datasets to reproduce our work are available at
this https URL

本文介绍了一种结合少量证据注释和大量文档级别标签的新方法，用于证据提取任务，同时对两个包含证据注释的分类任务进行评估，发现我们的方法优于在解释性文献适用的基线方法。将少至百个证据注释运用到该方法中可得到显著收益。