-
Dual Process Learning: Controlling Use of In-Context vs. In-Weights Strategies with Weight Forgetting
Paper • 2406.00053 • Published • 1 -
Token Erasure as a Footprint of Implicit Vocabulary Items in LLMs
Paper • 2406.20086 • Published • 3 -
Multi-property Steering of Large Language Models with Dynamic Activation Composition
Paper • 2406.17563 • Published • 4 -
From Insights to Actions: The Impact of Interpretability and Analysis Research on NLP
Paper • 2406.12618 • Published • 5
Collections
Discover the best community collections!
Collections including paper arxiv:2404.03592
-
Can Large Language Models Understand Context?
Paper • 2402.00858 • Published • 20 -
OLMo: Accelerating the Science of Language Models
Paper • 2402.00838 • Published • 75 -
Self-Rewarding Language Models
Paper • 2401.10020 • Published • 135 -
SemScore: Automated Evaluation of Instruction-Tuned LLMs based on Semantic Textual Similarity
Paper • 2401.17072 • Published • 23
-
Rho-1: Not All Tokens Are What You Need
Paper • 2404.07965 • Published • 80 -
VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time
Paper • 2404.10667 • Published • 13 -
Instruction-tuned Language Models are Better Knowledge Learners
Paper • 2402.12847 • Published • 24 -
DoRA: Weight-Decomposed Low-Rank Adaptation
Paper • 2402.09353 • Published • 23
-
The Unreasonable Ineffectiveness of the Deeper Layers
Paper • 2403.17887 • Published • 75 -
Mixture-of-Depths: Dynamically allocating compute in transformer-based language models
Paper • 2404.02258 • Published • 102 -
ReFT: Representation Finetuning for Language Models
Paper • 2404.03592 • Published • 75 -
Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences
Paper • 2404.03715 • Published • 58