Paper Detail
Manan Gupta, Dhruv Kumar
Large language models frequently commit unrecoverable reasoning errors mid-generation: once a wrong step is taken, subsequent tokens compound the mistake rather than correct it. We introduce $\textbf{Latent Phase-Shift Rollback}$ (LPSR): at each generation step, we monitor the residual stream at a critical layer lcrit, detect abrupt directional reversals (phase shifts) via a cosine-similarity $+$ entropy dual gate, and respond by rolling back the KV-cache and injecting a pre-computed steering vector. No fine-tuning, gradient computation, or additional forward passes are required. LPSR achieves $\mathbf{44.0\%}$ on MATH-500 with an 8B model versus $28.8\%$ for standard AR ($+15.2$ pp; McNemar $χ^2 = 66.96$, $p < 10^{-15}$). Critically, prompted self-correction, the most natural inference-time baseline, scores only $19.8\%$, below standard AR; LPSR exceeds it by $+24.2$ pp ($χ^2 = 89.4$, $p \approx 0$). LPSR also outperforms Best-of-16 ($+7.8$ pp) at $5.4\times$ lower token cost, and surpasses a standard 70B model ($35.2\%$) with $8.75\times$ fewer parameters at ${\sim}3\times$ the token budget. A 32-layer sweep reveals a novel \textbf{detection-correction dissociation}: error-detection AUC peaks at layer~14 ($0.718$) but task accuracy peaks at layer~16 ($44.0\%$ vs.\ $29.2\%$), demonstrating that optimal monitoring depth differs for detection and correction.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@article{gupta2026latent,
title = {Latent Phase-Shift Rollback: Inference-Time Error Correction via Residual Stream Monitoring and KV-Cache Steering},
author = {Manan Gupta and Dhruv Kumar},
year = {2026},
abstract = {Large language models frequently commit unrecoverable reasoning errors mid-generation: once a wrong step is taken, subsequent tokens compound the mistake rather than correct it. We introduce \$\textbackslash{}textbf\{Latent Phase-Shift Rollback\}\$ (LPSR): at each generation step, we monitor the residual stream at a critical layer lcrit, detect abrupt directional reversals (phase shifts) via a cosine-similarity \$+\$ entropy dual gate, and respond by rolling back the KV-cache and injecting a pre-computed steering ve},
url = {https://arxiv.org/abs/2604.18567},
keywords = {cs.LG, cs.AI, cs.CL},
eprint = {2604.18567},
archiveprefix = {arXiv},
}
{}