Communities
Connect sessions
AI calendar
Organizations
Join Slack
Contact Sales
Search
Open menu
Home
Papers
2506.17090
Cited By
v1
v2
v3 (latest)
Better Language Model Inversion by Compactly Representing Next-Token Distributions
20 June 2025
Murtaza Nazir
Matthew Finlayson
John X. Morris
Xiang Ren
Swabha Swayamdipta
Re-assign community
ArXiv (abs)
PDF
HTML
HuggingFace (1 upvotes)
Github (4★)
Papers citing
"Better Language Model Inversion by Compactly Representing Next-Token Distributions"
3 / 3 papers shown
Transformer Injectivity & Geometric Robustness - Analytic Margins and Bi-Lipschitz Uniformity of Sequence-Level Hidden States
Mikael von Strauss
101
0
0
17 Nov 2025
Language Models are Injective and Hence Invertible
Giorgos Nikolaou
Tommaso Mencattini
Donato Crisostomi
Andrea Santilli
Yannis Panagakis
Emanuele Rodolà
168
5
0
17 Oct 2025
GPT, But Backwards: Exactly Inverting Language Model Outputs
Adrians Skapars
Edoardo Manino
Youcheng Sun
Lucas C. Cordeiro
160
0
0
02 Jul 2025
1
