让大模型自带解释能力，提升可信赖度。
Concept Bottleneck Large Language Models
- 在模型内部嵌入可解释的概念层，实现透明推理。
- 文本分类性能媲美黑箱模型，生成任务中可精准控制概念。
- 适合关注安全、可控与可信AI的开发者和研究者。
我们提出概念瓶颈大语言模型（CB-LLMs），一种具备内在可解释性的新型大语言模型框架。与依赖有限事后解释的传统黑箱模型不同，CB-LLMs将可解释性直接融入模型结构，实现高可扩展性与透明性。我们在文本分类和文本生成两个关键NLP任务上构建了CB-LLMs。在文本分类中，其性能与传统黑箱模型相当，甚至部分场景更优，同时提供明确可解释的推理过程。在更具挑战性的文本生成任务中，可解释神经元实现精确概念识别、可控生成与更安全输出。内置可解释性使用户能透明识别有害内容、引导模型行为、移除不良概念，显著增强模型的安全性、可靠性和可信度——这些能力在现有模型中尤为缺乏。代码已开源：https://github.com/Trustworthy-ML-Lab/CB-LLMs。
原文摘要 · Abstract (English)
We introduce Concept Bottleneck Large Language Models (CB-LLMs), a novel framework for building inherently interpretable Large Language Models (LLMs). In contrast to traditional black-box LLMs that rely on limited post-hoc interpretations, CB-LLMs integrate intrinsic interpretability directly into the LLMs -- allowing accurate explanations with scalability and transparency. We build CB-LLMs for two essential NLP tasks: text classification and text generation. In text classification, CB-LLMs is competitive with, and at times outperforms, traditional black-box models while providing explicit and interpretable reasoning. For the more challenging task of text generation, interpretable neurons in CB-LLMs enable precise concept detection, controlled generation, and safer outputs. The embedded interpretability empowers users to transparently identify harmful content, steer model behavior, and unlearn undesired concepts -- significantly enhancing the safety, reliability, and trustworthiness of LLMs, which are critical capabilities notably absent in existing models. Our code is available at https://github.com/Trustworthy-ML-Lab/CB-LLMs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。