-
Visual In-Context Prompting
Paper • 2311.13601 • Published • 14 -
AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework
Paper • 2308.08155 • Published • 2 -
LIDA: A Tool for Automatic Generation of Grammar-Agnostic Visualizations and Infographics using Large Language Models
Paper • 2303.02927 • Published • 3 -
The Impact of Large Language Models on Scientific Discovery: a Preliminary Study using GPT-4
Paper • 2311.07361 • Published • 11
Collections
Discover the best community collections!
Collections including paper arxiv:2309.05463
-
Ensemble-Instruct: Generating Instruction-Tuning Data with a Heterogeneous Mixture of LMs
Paper • 2310.13961 • Published • 4 -
ZeroGen: Efficient Zero-shot Learning via Dataset Generation
Paper • 2202.07922 • Published • 1 -
Let's Synthesize Step by Step: Iterative Dataset Synthesis with Large Language Models by Extrapolating Errors from Small Models
Paper • 2310.13671 • Published • 17 -
Fabricator: An Open Source Toolkit for Generating Labeled Training Data with Teacher LLMs
Paper • 2309.09582 • Published • 4
-
CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion
Paper • 2310.11248 • Published • 3 -
Textbooks Are All You Need II: phi-1.5 technical report
Paper • 2309.05463 • Published • 84 -
When Less is More: Investigating Data Pruning for Pretraining LLMs at Scale
Paper • 2309.04564 • Published • 14 -
What's In My Big Data?
Paper • 2310.20707 • Published • 9
-
A Survey on Language Models for Code
Paper • 2311.07989 • Published • 21 -
CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation
Paper • 2102.04664 • Published • 2 -
Evaluating Large Language Models Trained on Code
Paper • 2107.03374 • Published • 6 -
Out of the BLEU: how should we assess quality of the Code Generation models?
Paper • 2208.03133 • Published • 2
-
When can transformers reason with abstract symbols?
Paper • 2310.09753 • Published • 2 -
In-Context Pretraining: Language Modeling Beyond Document Boundaries
Paper • 2310.10638 • Published • 26 -
Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model
Paper • 2310.09520 • Published • 10 -
Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers
Paper • 2309.08532 • Published • 50
-
Attention Is All You Need
Paper • 1706.03762 • Published • 36 -
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Paper • 2005.11401 • Published • 11 -
LoRA: Low-Rank Adaptation of Large Language Models
Paper • 2106.09685 • Published • 25 -
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
Paper • 2205.14135 • Published • 8
-
The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"
Paper • 2309.12288 • Published • 3 -
Are Emergent Abilities in Large Language Models just In-Context Learning?
Paper • 2309.01809 • Published • 3 -
When Less is More: Investigating Data Pruning for Pretraining LLMs at Scale
Paper • 2309.04564 • Published • 14 -
CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages
Paper • 2309.09400 • Published • 77