Is Decoding-Time Debiasing via Process Reward Models superseded?

Decoding-Time Debiasing via Process Reward Models (LLM reasoning / chain-of-thought): current frontier — recent, not yet superseded in the knowledge base. 0 paper(s) critique it, 0 beat it on benchmarks — not ranked as a superseded baseline. Sub-problem: cluster led by Chain-of-Thought. Newer alternatives in the same sub-problem include Marginal Sharpening, Tree-of-Thoughts, Co-ReAct, MA-CoT, Novelty-based Tree-of-Thought Search.

LLM reasoning / chain-of-thought

Decoding-Time Debiasing via Process Reward Models

Decoding-Time Debiasing via Process Reward Models: From Controlled Fill-in to Open-Ended Generation

On the frontierfirst seen May 4, 2026

Current frontier — recent, not yet superseded in the knowledge base

0 papers critique it · 0 beat it on benchmarks

What to use instead

Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.

Marginal SharpeningSelf-Consistency via Marginal Sharpening
May 27, 2026
Tree-of-ThoughtsTree of Thoughts as a Classical Heuristic Search Problem: Formal Foundations and Design Patterns
May 27, 2026
Co-ReActCo-ReAct: Rubrics as Step-Level Collaborators for ReAct Agents
May 22, 2026
MA-CoTEnhancing Reliability in LLM-Based Secure Code Generation
May 22, 2026
Novelty-based Tree-of-Thought SearchNovelty-based Tree-of-Thought Search for LLM Reasoning and Planning
May 7, 2026
Decoding-Time Debiasing via Process Reward ModelsDecoding-Time Debiasing via Process Reward Models: From Controlled Fill-in to Open-Ended Generation
May 4, 2026
Dual-Track CoTDual-Track CoT: Budget-Aware Stepwise Guidance for Small LMs
Apr 27, 2026
R-CoVR-CoV: Region-Aware Chain-of-Verification for Alleviating Object Hallucinations in LVLMs
Apr 22, 2026
CoT-PoT ensemblingSelf-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning
Apr 19, 2026
AtroposAtropos: Improving Cost-Benefit Trade-off of LLM-based Agents under Self-Consistency with Early Termination and Model Hotswap
Apr 16, 2026
RefineRLRefineRL: Advancing Competitive Programming with Self-Refinement Reinforcement Learning
Apr 1, 2026
Learning When to SampleLearning When to Sample: Confidence-Aware Self-Consistency for Efficient LLM Chain-of-Thought Reasoning
Mar 17, 2026