Table 1 provides a detailed breakdown of the disease categories included in DiReCT. As some premise may not included in the referred guidelines.

Models like GPT -4 excel in medical question answering but may face challenges in the lack of interpretability when handling complex tasks in real clinical settings.

Training (AL T), which aims to enhance LLMs' reasoning capabilities by program-generated logical reasoning samples.

The challenge in object-based visual reasoning lies in generating concept representations that are both descriptive and distinct.

To address these challenges, we consider the two-step preference modeling procedure that first resolves the under-specification by selecting a context, and then evaluates preference with respect to the chosen context.

We study the optimal memorization capacity of modern Hopfield models and Kernelized Hopfield Models (KHMs), a transformer-compatible class of Dense Associative Memories.

We give a model-based agent that builds a Python program representing its knowledge of the world based on its interactions with the environment.

Logical Credal Networks or LCNs were recently introduced as a powerful probabilistic logic framework for representing and reasoning with imprecise knowledge.

We pursue this hypothesis by developing a family of Representation Finetuning (ReFT) methods.