Detecting Pretraining Data from Large Language Models
Paper
•
2310.16789
•
Published
•
9
Papers
-
-
Let's Synthesize Step by Step: Iterative Dataset Synthesis with Large Language Models by Extrapolating Errors from Small Models
Paper • 2310.13671 • Published • 17 -
AutoMix: Automatically Mixing Language Models
Paper • 2310.12963 • Published • 14 -
An Emulator for Fine-Tuning Large Language Models using Small Language Models
Paper • 2310.12962 • Published • 13 -
In-Context Pretraining: Language Modeling Beyond Document Boundaries
Paper • 2310.10638 • Published • 26 -
Zephyr: Direct Distillation of LM Alignment
Paper • 2310.16944 • Published • 116 -
Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model
Paper • 2310.09520 • Published • 10 -
DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
Paper • 2310.03714 • Published • 27 -
Efficient Streaming Language Models with Attention Sinks
Paper • 2309.17453 • Published • 13 -
MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models
Paper • 2309.12284 • Published • 16 -
Chain-of-Verification Reduces Hallucination in Large Language Models
Paper • 2309.11495 • Published • 37 -
Knowledge Distillation of Large Language Models
Paper • 2306.08543 • Published • 16 -
A Repository of Conversational Datasets
Paper • 1904.06472 • Published • 2 -
SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
Paper • 1704.05179 • Published • 1 -
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
Paper • 1908.10084 • Published -
Efficient Few-Shot Learning Without Prompts
Paper • 2209.11055 • Published • 2 -
Attention Is All You Need
Paper • 1706.03762 • Published • 34 -
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Paper • 2005.11401 • Published • 11 -
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
Paper • 2205.14135 • Published • 8 -
Textbooks Are All You Need
Paper • 2306.11644 • Published • 137 -
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Paper • 2305.18290 • Published • 37 -
The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants
Paper • 2308.16884 • Published • 8 -
Retentive Network: A Successor to Transformer for Large Language Models
Paper • 2307.08621 • Published • 166 -
PockEngine: Sparse and Efficient Fine-tuning in a Pocket
Paper • 2310.17752 • Published • 11 -
Contrastive Decoding: Open-ended Text Generation as Optimization
Paper • 2210.15097 • Published -
Contrastive Decoding Improves Reasoning in Large Language Models
Paper • 2309.09117 • Published • 37 -
Efficient Memory Management for Large Language Model Serving with PagedAttention
Paper • 2309.06180 • Published • 25 -
DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models
Paper • 2309.03883 • Published • 14 -
Controlled Decoding from Language Models
Paper • 2310.17022 • Published • 12 -
Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference Using Sorted Fine-Tuning (SoFT)
Paper • 2309.08968 • Published • 22 -
Learning From Mistakes Makes LLM Better Reasoner
Paper • 2310.20689 • Published • 24 -
Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
Paper • 2310.11511 • Published • 61 -
YaRN: Efficient Context Window Extension of Large Language Models
Paper • 2309.00071 • Published • 57 -
DeepSpeed-Chat: Easy, Fast and Affordable RLHF Training of ChatGPT-like Models at All Scales
Paper • 2308.01320 • Published • 42 -
Shepherd: A Critic for Language Model Generation
Paper • 2308.04592 • Published • 27 -
GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints
Paper • 2305.13245 • Published • 5 -
Improving Large Language Model Fine-tuning for Solving Math Problems
Paper • 2310.10047 • Published • 5 -
Dialogue Act Classification with Context-Aware Self-Attention
Paper • 1904.02594 • Published -
It's Morphin' Time! Combating Linguistic Discrimination with Inflectional Perturbations
Paper • 2005.04364 • Published -
Question rewriting? Assessing its importance for conversational question answering
Paper • 2201.09146 • Published -
Can Question Rewriting Help Conversational Question Answering?
Paper • 2204.06239 • Published -
Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling
Paper • 2311.00430 • Published • 53 -
What's In My Big Data?
Paper • 2310.20707 • Published • 9 -
When Less is More: Investigating Data Pruning for Pretraining LLMs at Scale
Paper • 2309.04564 • Published • 14 -
FlashDecoding++: Faster Large Language Model Inference on GPUs
Paper • 2311.01282 • Published • 30 -
Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization
Paper • 2311.06243 • Published • 17 -
Prompt Cache: Modular Attention Reuse for Low-Latency Inference
Paper • 2311.04934 • Published • 23 -
Co-training and Co-distillation for Quality Improvement and Compression of Language Models
Paper • 2311.02849 • Published • 2 -
NetDistiller: Empowering Tiny Deep Learning via In-Situ Distillation
Paper • 2310.19820 • Published • 1 -
LLM in a flash: Efficient Large Language Model Inference with Limited Memory
Paper • 2312.11514 • Published • 252 -
RecurrentGemma: Moving Past Transformers for Efficient Open Language Models
Paper • 2404.07839 • Published • 36