GunosyDMについて
Title
ChatMusician: Understanding and Generating Music Intrinsically with LLM
Similarity is Not All You Need: Endowing Retrieval-Augmented Generation with Multi–layered Thoughts
Trending Now: Modeling Trend Recommendations
NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models
Evaluating the Factual Consistency of Large Language Models Through News Summarization
Automated Evaluation of Retrieval-Augmented Language Models with Task-Specific Exam Generation
Zheng+'23 Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
In-Context Learning with Long-Context Models: An In-Depth Exploration
In-Context Impersonation Reveals Large Language Models’ Strengths and Biases
Wang+'23 Fresh Content Needs More Attention: Multi-funnel Fresh Content Recommendation (KDD 2023)
To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis
Let the LLMs Talk: Simulating Human-to-Human Conversational QA via Zero-Shot LLM-to-LLM Interactions
Evolutionary Optimization of Model Merging Recipes
Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling
Going Beyond Local: Global Graph-Enhanced Personalized News Recommendations
Temporal Blind Spots in Large Language Models
Large Language Models are not Fair Evaluators
Gruver+'23 Large Language Models Are Zero-Shot Time Series Forecasters (NIPS 2023)