Efficient Tool Use with Chain-of-Abstraction Reasoning
Paper
•
2401.17464
•
Published
•
15
LLM
-
-
Divide and Conquer: Language Models can Plan and Self-Correct for Compositional Text-to-Image Generation
Paper • 2401.15688 • Published • 10 -
SliceGPT: Compress Large Language Models by Deleting Rows and Columns
Paper • 2401.15024 • Published • 62 -
From GPT-4 to Gemini and Beyond: Assessing the Landscape of MLLMs on Generalizability, Trustworthiness and Causality through Four Modalities
Paper • 2401.15071 • Published • 33 -
Unitxt: Flexible, Shareable and Reusable Data Preparation and Evaluation for Generative AI
Paper • 2401.14019 • Published • 19 -
ChatQA: Building GPT-4 Level Conversational QA Models
Paper • 2401.10225 • Published • 32 -
Do Large Language Models Latently Perform Multi-Hop Reasoning?
Paper • 2402.16837 • Published • 24 -
Divide-or-Conquer? Which Part Should You Distill Your LLM?
Paper • 2402.15000 • Published • 22 -
Linear Transformers with Learnable Kernel Functions are Better In-Context Models
Paper • 2402.10644 • Published • 74 -
DataDreamer: A Tool for Synthetic Data Generation and Reproducible LLM Workflows
Paper • 2402.10379 • Published • 27 -
Chain-of-Thought Reasoning Without Prompting
Paper • 2402.10200 • Published • 91 -
Generative Representational Instruction Tuning
Paper • 2402.09906 • Published • 50 -
Self-Discover: Large Language Models Self-Compose Reasoning Structures
Paper • 2402.03620 • Published • 102 -
Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks
Paper • 2402.04248 • Published • 25 -
Rethinking Optimization and Architecture for Tiny Language Models
Paper • 2402.02791 • Published • 12 -
OLMo: Accelerating the Science of Language Models
Paper • 2402.00838 • Published • 74 -
Can Large Language Models Understand Context?
Paper • 2402.00858 • Published • 20 -
Can large language models explore in-context?
Paper • 2403.15371 • Published • 30