Article

Large Language Models with Temporal Reasoning for Longitudinal Clinical Summarization and Prediction
Recent advances in large language models (LLMs) have shown potential in clinical text summarization, but their ability to handle long …
PDF Source Document
Large Language Models with Temporal Reasoning for Longitudinal Clinical Summarization and Prediction
Anchored Answers: Unravelling Positional Bias in GPT-2's Multiple-Choice Questions
Using principles from Mechanistic Interpretability, we are able to investigate and correct the positional bias in GPT2 models regarding multiple-choice questions.
PDF
Learning to Maximize Mutual Information for Chain-of-Thought Distillation
We propose a new training paradigm for Chain-of-Thought distillation with the perspective from information bottleneck.
PDF Code Dataset Poster Video Source Document
Learning to Maximize Mutual Information for Chain-of-Thought Distillation