FirstBatch is building collaboration and user-centric tools for safe AGI.
Tree of Thoughts: Deliberate Problem Solving with Large Language Models
Text Embeddings Reveal (Almost) As Much As Text
Retrieval-Augmented Generation for Large Language Models: A Survey
Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache
Fine-Tuning vs. Retrieval: Enhancing Knowledge in Large Language Models
The Library of Alexandria
State of AI Report 2023: Navigating the Evolving Landscape
Collaborative Knowledge Base Embedding for Recommender Systems
Why Vector Based Personalization is Better Than Its Alternatives
LLM-Rec: Personalized Recommendation via Prompting Large Language Models
Mixtral of Experts
Causal Inference for Recommender Systems
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Lost in the Middle: How Language Models Use Long Contexts
Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs
WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia
Dynamic Customer Embeddings for Financial Service Applications
Harnessing LLMs for the Next Wave of Consumer Experiences
Mistral 7B: Advancements in Language Model Efficiency and Performance
OpenAI Safety&Alignment Papers
Upgrading Recommender Systems with Large Language Models
Upgrading Recommender Systems with LLMs
Knowledge Interface Between Humans and AI
RAPTOR: RECURSIVE ABSTRACTIVE PROCESSING FOR TREE-ORGANIZED RETRIEVAL
Nomic Embed: Training a Reproducible Long Context Text Embedder
Retrieval meets Long Context Large Language Models by NVIDIA
Unified Embedding Based Personalized Retrieval in Etsy Search
wikipedia.20220301.en
FERRET: REFER AND GROUND ANYTHING ANYWHERE AT ANY GRANULARITY
wikipedia/20220301.en
Efficient LLM Inference CPUs