The Generative AI Paradox: "What It Can Create, It May Not Understand"
Paper
•
2311.00059
•
Published
•
20
daily_paper
-
-
Teaching Large Language Models to Reason with Reinforcement Learning
Paper • 2403.04642 • Published • 51 -
Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM
Paper • 2403.07816 • Published • 42 -
PERL: Parameter Efficient Reinforcement Learning from Human Feedback
Paper • 2403.10704 • Published • 60 -
LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement
Paper • 2403.15042 • Published • 28 -
BioMedLM: A 2.7B Parameter Language Model Trained On Biomedical Text
Paper • 2403.18421 • Published • 24 -
sDPO: Don't Use Your Data All at Once
Paper • 2403.19270 • Published • 42 -
Advancing LLM Reasoning Generalists with Preference Trees
Paper • 2404.02078 • Published • 47 -
ReFT: Representation Finetuning for Language Models
Paper • 2404.03592 • Published • 98 -
Chinese Tiny LLM: Pretraining a Chinese-Centric Large Language Model
Paper • 2404.04167 • Published • 14 -
MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
Paper • 2404.06395 • Published • 23 -
Rho-1: Not All Tokens Are What You Need
Paper • 2404.07965 • Published • 94 -
Pre-training Small Base LMs with Fewer Tokens
Paper • 2404.08634 • Published • 36 -
Learn Your Reference Model for Real Good Alignment
Paper • 2404.09656 • Published • 87 -
OpenBezoar: Small, Cost-Effective and Open Models Trained on Mixes of Instruction Data
Paper • 2404.12195 • Published • 12 -
MAP-Neo: Highly Capable and Transparent Bilingual Large Language Model Series
Paper • 2405.19327 • Published • 50