LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models
Paper
• 2309.12307 • Published
• 90
tuning
-
-
NEFTune: Noisy Embeddings Improve Instruction Finetuning
Paper • 2310.05914 • Published • 14 -
SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling
Paper • 2312.15166 • Published • 61 -
Soaring from 4K to 400K: Extending LLM's Context with Activation Beacon
Paper • 2401.03462 • Published • 29 -
YaRN: Efficient Context Window Extension of Large Language Models
Paper • 2309.00071 • Published • 81 -
Blending Is All You Need: Cheaper, Better Alternative to Trillion-Parameters LLM
Paper • 2401.02994 • Published • 52 -
A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity
Paper • 2401.01967 • Published -
Zephyr: Direct Distillation of LM Alignment
Paper • 2310.16944 • Published • 123 -
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Paper • 2305.18290 • Published • 64 -
S-LoRA: Serving Thousands of Concurrent LoRA Adapters
Paper • 2311.03285 • Published • 31 -
What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning
Paper • 2312.15685 • Published • 16 -
Self-Rewarding Language Models
Paper • 2401.10020 • Published • 152 -
TOFU: A Task of Fictitious Unlearning for LLMs
Paper • 2401.06121 • Published • 20 -
Tuning LLMs with Contrastive Alignment Instructions for Machine Translation in Unseen, Low-resource Languages
Paper • 2401.05811 • Published • 8 -
Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models
Paper • 2401.01335 • Published • 68 -
WARM: On the Benefits of Weight Averaged Reward Models
Paper • 2401.12187 • Published • 19 -
Learning Universal Predictors
Paper • 2401.14953 • Published • 22 -
Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling
Paper • 2401.16380 • Published • 51 -
Language Models can be Logical Solvers
Paper • 2311.06158 • Published • 20 -
ReFT: Reasoning with Reinforced Fine-Tuning
Paper • 2401.08967 • Published • 31 -
Continual Learning for Large Language Models: A Survey
Paper • 2402.01364 • Published • 1 -
Direct Language Model Alignment from Online AI Feedback
Paper • 2402.04792 • Published • 35 -
Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models
Paper • 2402.03749 • Published • 15 -
Suppressing Pink Elephants with Direct Principle Feedback
Paper • 2402.07896 • Published • 11 -
How to Train Data-Efficient LLMs
Paper • 2402.09668 • Published • 43 -
QuRating: Selecting High-Quality Data for Training Language Models
Paper • 2402.09739 • Published • 5 -
DoRA: Weight-Decomposed Low-Rank Adaptation
Paper • 2402.09353 • Published • 32 -
Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive
Paper • 2402.13228 • Published • 3 -
FuseChat: Knowledge Fusion of Chat Models
Paper • 2402.16107 • Published • 39 -
LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models
Paper • 2403.13372 • Published • 182 -
Evolutionary Optimization of Model Merging Recipes
Paper • 2403.13187 • Published • 58 -
LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning
Paper • 2403.17919 • Published • 16 -
Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences
Paper • 2404.03715 • Published • 62 -
Insights into Alignment: Evaluating DPO and its Variants Across Multiple Tasks
Paper • 2404.14723 • Published • 10 -
Instruction Tuning with Human Curriculum
Paper • 2310.09518 • Published • 3 -
MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning
Paper • 2405.12130 • Published • 50 -
OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework
Paper • 2405.11143 • Published • 41 -
Self-Play Preference Optimization for Language Model Alignment
Paper • 2405.00675 • Published • 28 -
NeMo-Aligner: Scalable Toolkit for Efficient Model Alignment
Paper • 2405.01481 • Published • 30 -
FLAME: Factuality-Aware Alignment for Large Language Models
Paper • 2405.01525 • Published • 29 -
WildChat: 1M ChatGPT Interaction Logs in the Wild
Paper • 2405.01470 • Published • 64 -
LoRA Land: 310 Fine-tuned LLMs that Rival GPT-4, A Technical Report
Paper • 2405.00732 • Published • 122 -
RLHF Workflow: From Reward Modeling to Online RLHF
Paper • 2405.07863 • Published • 71 -
Understanding the performance gap between online and offline alignment algorithms
Paper • 2405.08448 • Published • 18 -
SimPO: Simple Preference Optimization with a Reference-Free Reward
Paper • 2405.14734 • Published • 12 -
Self-Improving Robust Preference Optimization
Paper • 2406.01660 • Published • 20 -
The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning
Paper • 2312.01552 • Published • 32 -
Creativity Has Left the Chat: The Price of Debiasing Language Models
Paper • 2406.05587 • Published • 1 -
Sailor: Open Language Models for South-East Asia
Paper • 2404.03608 • Published • 21 -
Continued Pretraining for Better Zero- and Few-Shot Promptability
Paper • 2210.10258 • Published -
Are You Sure? Rank Them Again: Repeated Ranking For Better Preference Datasets
Paper • 2405.18952 • Published • 10