2606.10820v1 Jun 09, 2026 cs.LG

K-Forcing: Joint Next-K-Token Decoding via Push-Forward Language Modeling

Wangbo Zhao
Wangbo Zhao
Citations: 341
h-index: 9
Bohan Zhuang
Bohan Zhuang
Citations: 6,351
h-index: 37
Fan Wang
Fan Wang
Citations: 62
h-index: 4
Zhiwei Tang
Zhiwei Tang
Citations: 14
h-index: 3
Yuanyu He
Yuanyu He
Citations: 71
h-index: 5
Yizheng Han
Yizheng Han
Citations: 0
h-index: 0
Jiasheng Tang
Jiasheng Tang
Citations: 192
h-index: 7

Autoregressive (AR) language modeling is the dominant paradigm for text generation, yet its sequential token-by-token decoding makes inference memory-bound and inefficient. Existing acceleration approaches, such as speculative decoding and diffusion language models, can yield speedups under certain conditions but do not directly address high-load batch serving--the scenario most critical for industrial-scale deployment. We introduce K-Forcing, a push-forward language modeling paradigm for joint next-k-token decoding. K-Forcing distills an existing AR model into a conditional push-forward mapping--one that transforms independent uniform noise variables into a joint sample of multiple future tokens in a single forward pass. This design preserves fixed-length outputs, reuses the AR teacher backbone, and remains compatible with standard AR serving infrastructure. We train this mapping via progressive self-forcing distillation, which gradually expands the prediction window while enabling the student to closely match the sequence distribution of the AR teacher. We evaluate K-Forcing on LM1B and OpenWebText using a standard causal Transformer backbone. When aggressively configured to generate k = 4 tokens per forward pass, K-Forcing delivers approximately 2.4-3.5x speedup across different batch sizes, while incurring modest quality degradation relative to its AR teacher. As inference increasingly dominates the lifetime compute cost of modern LLMs, K-Forcing offers a promising route toward accelerating AR generation under real-world high-load deployment.

0 Citations
0 Influential
18.5 Altmetric
92.5 Score
Original PDF

No Analysis Report Yet

This paper hasn't been analyzed by Gemini yet.

Log in to request an AI analysis.

댓글

댓글을 작성하려면 로그인하세요.

아직 댓글이 없습니다. 첫 번째 댓글을 남겨보세요!