AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

DC-W2S: Dual-Consensus Weak-to-Strong Training for Reliable Process Reward Modeling in Biological Reasoning

Chi-Min Chan, Ehsan Hajiramezanali, Xiner Li, Edward De Brouwer, Carl Edwards, Wei Xue, Sirui Han, Yike Guo, Gabriele Scalia

ICML 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Learning from unlabeled and positive-unlabeled data · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
aggregate multiple weak label sources (LLM judges plus MC rollouts) instead of a single source (ablation)DC-W2S PRM · PerturbQA, 4 cell linesaverage F1 (BoN N=8): 66.9% -> 68.5%Improved
add DC-W2S distribution-balanced instance sampling (100k) instead of full 351k set (ablation)PRM training · PerturbQA RPE1 (OOD)F1 (%): 64.0 -> 64.5 (vs Full Set multi-label)Improved
train only on P1 labels (about 62% of steps) (ablation)PRM masking · PerturbQA RPE1 (OOD)F1 (%): approx 64% F1 with about 62% of labelsNo clear effect
train only on low-reliability regimes P3 or P4 (ablation)PRM masking · PerturbQA RPE1 (OOD)F1 (%): Only P3 57.52; Only P4 52.40 vs Only P1 63.40Hurt
add P3 steps on top of P1 anchors (ablation)PRM masking · PerturbQA RPE1 (OOD)F1 (%): 63.40 -> 64.66Improved
add P2 steps on top of P1 anchors (ablation)PRM masking · PerturbQA RPE1 (OOD)F1 (%): 63.40 -> 64.16Improved
add P4 steps on top of P1 anchors (ablation)PRM masking · PerturbQA RPE1 (OOD)F1 (%): 63.40 -> 64.23No clear effect
train on 100k DC-W2S subset instead of full weak-label set (ablation)PRM · BioReason KEGGweighted F1 (%): 87.40 -> 88.89 (CellProfiler), 89.08 (ESM)Improved
use 100k DC-W2S subset instead of the full set with rbio1 policy (ablation)PRM · RPE1 (OOD) rbio1 averageF1 (%): 70.59 -> 68.43 (CellProfiler), 69.73 (ESM)Hurt
use PRM best-of-N instead of greedy decoding with question-only promptsQwen3-4B policy · RPE1 (OOD) Only Queryaverage F1 (%): 27.25 -> 52.56Improved
use PRM best-of-N instead of greedy decoding with rbio1 policyrbio1 · RPE1 (OOD)average F1 (%): 56.61 -> 70.59Improved
use biologically grounded embeddings (ESM, CellProfiler) for neighborhood consensus rather than semantic embeddings (ablation)DC-W2S · RPE1-DEF1 gain from P3Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy