🛰️ Daily AI Frontier
‹ back to 2026-08-17

You Only Pass Once: Answering and Abstaining Together in a Single Forward Pass of a Frozen Language Model

Research LLMs & Foundation Models

Ranking

Overall 79
Content 95
Popularity 41

Observed public metrics from 1 member.

Merged summary

TL;DR - YOPO enables frozen language models to improve reasoning and detect unanswerable inputs in a single forward pass. It reconstructs the pre-steering residual state to prevent reasoning interventions from degrading abstention reliability.

  • Combines conditional residual-stream steering with zero-shot sufficiency detection.
  • Uses a small label-free reconstruction network trained on paired clean and steered residuals.
  • More than doubles three-way accuracy on 1.5B Qwen2.5 alphaNLI, from 0.375 to 0.798.
  • Outperforms a two-pass reference across model scales and preserves abstention under domain transfer.

Sources (1)

You Only Pass Once: Answering and Abstaining Together in a Single Forward Pass of a Frozen Language Model

arXiv cs.CL Ziyang Luo, Zhongyao Chu, Xinjie He, Youting Wang, Xukui Qin, Runxiong Wu, Yan-Syuan Chen 2026-08-14 arXiv:2608.14465
Public signals Semantic Scholar citations 0 · Semantic Scholar influential citations 0
Providers: Hugging Face · N/A OpenAlex · N/A Publisher · N/A Semantic Scholar · Citations 0 · Influential citations 0 X · N/A Fetched 2026-08-24 14:19:54.536313 UTC

TL;DR - YOPO enables frozen language models to improve reasoning and detect unanswerable inputs in a single forward pass. It reconstructs the pre-steering residual state to prevent reasoning interventions from degrading abstention reliability.

  • Combines conditional residual-stream steering with zero-shot sufficiency detection.
  • Uses a small label-free reconstruction network trained on paired clean and steered residuals.
  • More than doubles three-way accuracy on 1.5B Qwen2.5 alphaNLI, from 0.375 to 0.798.
  • Outperforms a two-pass reference across model scales and preserves abstention under domain transfer.
item →