-
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 • 4 -
Confidence Regulation Neurons in Language Models
Paper • 2406.16254 • Published • 10 -
Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation
Paper • 2406.13663 • Published • 7
Collections
Discover the best community collections!
Collections including paper arxiv:2405.14860
-
PRDP: Proximal Reward Difference Prediction for Large-Scale Reward Finetuning of Diffusion Models
Paper • 2402.08714 • Published • 10 -
Data Engineering for Scaling Language Models to 128K Context
Paper • 2402.10171 • Published • 18 -
RLVF: Learning from Verbal Feedback without Overgeneralization
Paper • 2402.10893 • Published • 10 -
Coercing LLMs to do and reveal (almost) anything
Paper • 2402.14020 • Published • 12
-
Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation
Paper • 2406.06525 • Published • 60 -
Husky: A Unified, Open-Source Language Agent for Multi-Step Reasoning
Paper • 2406.06469 • Published • 22 -
Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models
Paper • 2406.04271 • Published • 26 -
Block Transformer: Global-to-Local Language Modeling for Fast Inference
Paper • 2406.02657 • Published • 35
-
Not All Language Model Features Are Linear
Paper • 2405.14860 • Published • 39 -
TimeGPT-1
Paper • 2310.03589 • Published • 3 -
A Careful Examination of Large Language Model Performance on Grade School Arithmetic
Paper • 2405.00332 • Published • 30 -
EasyAnimate: A High-Performance Long Video Generation Method based on Transformer Architecture
Paper • 2405.18991 • Published • 12
-
AtP*: An efficient and scalable method for localizing LLM behaviour to components
Paper • 2403.00745 • Published • 8 -
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
Paper • 2402.17764 • Published • 574 -
MobiLlama: Towards Accurate and Lightweight Fully Transparent GPT
Paper • 2402.16840 • Published • 23 -
LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens
Paper • 2402.13753 • Published • 106