About
Research & Development
DrugReasoner: A Transparent Approach to Predicting Drug Success
TLDR: DrugReasoner is a new AI model based on the LLaMA architecture that predicts drug approval likelihood for small molecules. It uses molecular features...
Research & Development
Unpacking Language Models: Do Transformers Model Human Thought or the Fabric of Language Itself?
TLDR: Colin Klein's research paper argues that Large Language Models (LLMs) model the corpus they are trained on, not human linguistic capacities. He posits...
Research & Development
Enhancing LLM Responses: A New Method for Factual Accuracy and Natural Language
TLDR: A new research paper introduces Collaborative Decoding (CoDe), a novel method designed to resolve the long-standing trade-off between factual accuracy (faithfulness) and natural,...
Research & Development
Unraveling Emotions and Their Causes in Multimodal Conversations with M3HG
TLDR: Researchers introduce M3HG, a novel model that uses a multimodal, multi-scale, and multi-type node heterogeneous graph to accurately extract emotion, cause, and emotion...
Research & Development
Reflective Evolution Guides Automated Prompt Optimization for Language Models
TLDR: ReflectivePrompt is a new autoprompting method that uses evolutionary algorithms combined with a 'reflective evolution' approach to find optimal prompts for large language...
Research & Development
DistillPrompt: A New Method for Automatically Optimizing Language Model Prompts
TLDR: DistillPrompt is a novel autoprompting method that automatically optimizes prompts for large language models (LLMs) using a multi-stage process of distillation, compression, and...