5 papers · 1 filter
Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift
Zitong Huang, Gustavo Lucas Carvalho, Deqing Fu +1
We propose Token-Level Off-Policy Labeling (TOPL), an off-policy training paradigm that reframes post-training as a token-level correctness prediction task. Our key intuition is th…
EPSVec: Efficient and Private Synthetic Data Generation via Dataset Vectors
Amin Banayeeanzade, Qingchuan Yang, Deqing Fu +6
High-quality data is essential for modern machine learning, yet many valuable corpora are sensitive and cannot be freely shared. Synthetic data offers a practical substitute for do…
Convergent Evolution: How Different Language Models Learn Similar Number Representations
Deqing Fu, Tianyi Zhou, Mikhail Belkin +2
Language models trained on natural text learn to represent numbers using periodic features with dominant periods at . In this paper, we identify a two-tiered hierarchy…
FoNE: Precise Single-Token Number Embeddings via Fourier Features
Tianyi Zhou, Deqing Fu, Mahdi Soltanolkotabi +2
Large Language Models (LLMs) typically represent numbers using multiple tokens, which requires the model to aggregate these tokens to interpret numerical values. This fragmentation…
Resa: Transparent Reasoning Models via SAEs
Shangshang Wang, Julian Asilis, Ãmer Faruk Akgül +4
How cost-effectively can we elicit strong reasoning in language models by leveraging their underlying representations? We answer this question with Resa, a family of 1.5B reasoning…