-
ReAGent: Towards A Model-agnostic Feature Attribution Method for Generative Language Models
Paper • 2402.00794 • Published • 1 -
Rethinking Interpretability in the Era of Large Language Models
Paper • 2402.01761 • Published • 23 -
Analyze Feature Flow to Enhance Interpretation and Steering in Language Models
Paper • 2502.03032 • Published • 58 -
Tell me why: Visual foundation models as self-explainable classifiers
Paper • 2502.19577 • Published • 10
Collections
Discover the best community collections!
Collections including paper arxiv:2402.01761
-
Rethinking Interpretability in the Era of Large Language Models
Paper • 2402.01761 • Published • 23 -
From Understanding to Utilization: A Survey on Explainability for Large Language Models
Paper • 2401.12874 • Published • 3 -
Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning
Paper • 2401.13986 • Published
-
JoMA: Demystifying Multilayer Transformers via JOint Dynamics of MLP and Attention
Paper • 2310.00535 • Published • 2 -
Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small
Paper • 2211.00593 • Published • 2 -
Rethinking Interpretability in the Era of Large Language Models
Paper • 2402.01761 • Published • 23 -
Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla
Paper • 2307.09458 • Published • 11
-
OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models
Paper • 2402.01739 • Published • 27 -
Rethinking Interpretability in the Era of Large Language Models
Paper • 2402.01761 • Published • 23 -
Self-Discover: Large Language Models Self-Compose Reasoning Structures
Paper • 2402.03620 • Published • 115 -
Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model
Paper • 2402.07827 • Published • 47
-
Chain-of-Thought Reasoning Without Prompting
Paper • 2402.10200 • Published • 105 -
How to Train Data-Efficient LLMs
Paper • 2402.09668 • Published • 42 -
BitDelta: Your Fine-Tune May Only Be Worth One Bit
Paper • 2402.10193 • Published • 22 -
A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts
Paper • 2402.09727 • Published • 38