As Large Language Models (LLMs) become increasingly integrated into our daily lives, the potential harms from deceptive behavior underlie the need for faithfully interpreting their decision-making. While traditional probing methods have shown some effectiveness, they remain best for narrowly scoped tasks while more comprehensive explanations are still necessary. To this end, we investigate meta-models-an architecture using a "meta-model" that takes activations from an "input-model" and answers natural language questions about the input-model's behaviors. We evaluate the meta-model's ability to generalize by training them on selected task types and assessing their out-of-distribution performance in deceptive scenarios. Our findings show that meta-models generalize well to out-of-distribution tasks and point towards opportunities for future research in this area. Our code is available at https://github.com/acostarelli/meta-models-public .
Task-Aware Calibration: Provably Optimal Decoding in LLMs
School of Computation, Information & Technology, Technical University of Munich（慕尼黑技术大学计算、信息与技术学院）；Munich Data Science Institute（慕尼黑数据科学研究所）；Munich Center for Machine Learning（慕尼黑机器学习中心）；University of Amsterdam（阿姆斯特丹大学）
MDQEC-QAS: Meta-Decoding for Quantum Error Correction with Hardware-Aware VQC Search and Confidence-Gated Recovery
Department of Physics, Indian Institute of Technology (BHU)（印度理工学院（BHU）物理系）；eBRAIN Lab, Division of Engineering, New York University Abu Dhabi (NYUAD)（纽约大学阿布扎克分校（NYUAD）工程学院eBRAIN实验室）；Center for Quantum and Topological Systems (CQTS), NYUAD Research Institute, NYUAD（纽约大学阿布扎克分校（NYUAD）量子与拓扑系统中心（CQTS））
University of Hong Kong（香港大学）；Shenzhen Loop Area Institute（深圳河套学院）；Chinese University of Hong Kong（香港中文大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Harvard University（哈佛大学）；Columbia University（哥伦比亚大学）；University of Washington（华盛顿大学）；Carnegie Mellon University（卡内基梅隆大学）
