Bootstrapping Language Models with DPO Implicit Rewards Paper • 2406.09760 • Published 17 days ago • 36
DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence Paper • 2406.11931 • Published 14 days ago • 54
Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs Paper • 2406.14544 • Published 11 days ago • 33
Instruction Pre-Training: Language Models are Supervised Multitask Learners Paper • 2406.14491 • Published 11 days ago • 75
Mixture-of-Agents Enhances Large Language Model Capabilities Paper • 2406.04692 • Published 24 days ago • 49
Hierarchical Prompting Taxonomy: A Universal Evaluation Framework for Large Language Models Paper • 2406.12644 • Published 13 days ago • 4
Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing Paper • 2406.08464 • Published 19 days ago • 47
Negotiating with LLMS: Prompt Hacks, Skill Gaps, and Reasoning Deficits Paper • 2312.03720 • Published Nov 26, 2023
Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competition Paper • 2311.16119 • Published Oct 24, 2023 • 2
Teams of LLM Agents can Exploit Zero-Day Vulnerabilities Paper • 2406.01637 • Published 29 days ago • 1