Tag: Interpretability
All the articles with the tag "Interpretability".
-
EMORL: Ensemble Multi-Objective Reinforcement Learning for Efficient and Flexible LLM Fine-Tuning
Published: at 09:32 AM
87.79 🤔本文提出EMORL框架，通过集成学习分别训练单目标模型并在隐藏状态层聚合，结合分层网格搜索优化权重，在咨询反思生成任务中实现了与传统方法相当的性能，同时显著提升了训练效率、可扩展性和解释性。
-
Boltzmann Classifier: A Thermodynamic-Inspired Approach to Supervised Learning
Published: at 11:08 AM 86.86 🤔The Boltzmann Classifier introduces a thermodynamically inspired supervised learning approach that uses an energy-based model derived from the Boltzmann distribution to estimate class probabilities, achieving competitive accuracy on benchmark datasets while offering interpretability and computational efficiency.
-
Self-Interpretability: LLMs Can Describe Complex Internal Processes that Drive Their Decisions, and Improve with Training
Published: at 11:15 AM 86.28 🤔本文通过微调GPT-4o和GPT-4o-mini，展示了大型语言模型能够量化报告其内部决策过程（如属性权重），并通过内省训练显著提升报告准确性，且这种能力可泛化至原生偏好，为AI可解释性和安全性提供了新路径。
-
Large Language Models are Locally Linear Mappings
Published: at 11:44 AM 85.46 🤔本文提出了一种通过分离Jacobian将大型语言模型在特定输入点转化为近乎精确局部线性系统的方法，揭示了模型内部低秩语义结构，并初步探索了输出引导应用，但泛化性和实用性受限。
-
When Do LLMs Admit Their Mistakes? Understanding the Role of Model Belief in Retraction
Published: at 11:47 AM 85.45 🤔本文通过构建模型特定数据集和信念操控实验，揭示了大型语言模型（LLMs）的撤回行为受内部信念因果影响，并通过监督微调显著提高撤回性能。