Papers
Communities
Events
Blog
Pricing
Search
Open menu
Home
Papers
2404.07129
Cited By
What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation
10 April 2024
Aaditya K. Singh
Ted Moskovitz
Felix Hill
Stephanie C. Y. Chan
Andrew M. Saxe
AI4CE
Re-assign community
ArXiv
PDF
HTML
Papers citing
"What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation"
10 / 10 papers shown
Title
Understanding In-context Learning of Addition via Activation Subspaces
Xinyan Hu
Kayo Yin
Michael I. Jordan
Jacob Steinhardt
Lijie Chen
53
0
0
08 May 2025
Strategy Coopetition Explains the Emergence and Transience of In-Context Learning
Aaditya K. Singh
Ted Moskovitz
Sara Dragutinovic
Felix Hill
Stephanie C. Y. Chan
Andrew Saxe
139
0
0
07 Mar 2025
Out-of-distribution generalization via composition: a lens through induction heads in Transformers
Jiajun Song
Zhuoyan Xu
Yiqiao Zhong
85
4
0
31 Dec 2024
Toward Understanding In-context vs. In-weight Learning
Bryan Chan
Xinyi Chen
András Gyorgy
Dale Schuurmans
72
3
0
30 Oct 2024
Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family Experts
Guorui Zheng
Xidong Wang
Juhao Liang
Nuo Chen
Yuping Zheng
Benyou Wang
MoE
32
5
0
14 Oct 2024
ELICIT: LLM Augmentation via External In-Context Capability
Futing Wang
Jianhao Yan
Yue Zhang
Tao Lin
39
0
0
12 Oct 2024
Wrong-of-Thought: An Integrated Reasoning Framework with Multi-Perspective Verification and Wrong Information
Yongheng Zhang
Qiguang Chen
Jingxuan Zhou
Peng Wang
Jiasheng Si
Jin Wang
Wenpeng Lu
Libo Qin
LRM
46
3
0
06 Oct 2024
Representing Rule-based Chatbots with Transformers
Dan Friedman
Abhishek Panigrahi
Danqi Chen
63
1
0
15 Jul 2024
Talking Heads: Understanding Inter-layer Communication in Transformer Language Models
Jack Merullo
Carsten Eickhoff
Ellie Pavlick
58
13
0
13 Jun 2024
Survival of the Fittest Representation: A Case Study with Modular Addition
Xiaoman Delores Ding
Zifan Carl Guo
Eric J. Michaud
Ziming Liu
Max Tegmark
48
3
0
27 May 2024
1