You Only Pass Once: Answering and Abstaining Together in a Single Forward Pass of a Frozen Language Model
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
Public signals
Semantic Scholar citations 0 · Semantic Scholar influential citations 0
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.