Imagen de Portada

Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chegini, Atoosa, Feizi, Soheil
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Schoenfeld's Anatomy of Mathematical Reasoning by Language Models
por: Li, Ming, et al.
Publicado: (2025)

A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models
por: Kazemi, Hamid, et al.
Publicado: (2026)

Chain-of-Defensive-Thought: Structured Reasoning Elicits Robustness in Large Language Models against Reference Corruption
por: Wang, Wenxiao, et al.
Publicado: (2025)

Reasoning's Razor: Reasoning Improves Accuracy but Can Hurt Recall at Critical Operating Points in Safety and Hallucination Detection
por: Chegini, Atoosa, et al.
Publicado: (2025)

Almost AI, Almost Human: The Challenge of Detecting AI-Polished Writing
por: Saha, Shoumik, et al.
Publicado: (2025)

Early Stopping for Large Reasoning Models via Confidence Dynamics
por: Hosseini, Parsa, et al.
Publicado: (2026)

Fast Adversarial Attacks on Language Models In One GPU Minute
por: Sadasivan, Vinu Sankar, et al.
Publicado: (2024)

Maestro: Joint Graph & Config Optimization for Reliable AI Agents
por: Wang, Wenxiao, et al.
Publicado: (2025)

RePanda: Pandas-powered Tabular Verification and Reasoning
por: Chegini, Atoosa Malemir, et al.
Publicado: (2025)

Can AI-Generated Text be Reliably Detected?
por: Sadasivan, Vinu Sankar, et al.
Publicado: (2023)

ProcessBench: Identifying Process Errors in Mathematical Reasoning
por: Zheng, Chujie, et al.
Publicado: (2024)

An Investigation of Robustness of LLMs in Mathematical Reasoning: Benchmarking with Mathematically-Equivalent Transformation of Advanced Mathematical Problems
por: Hao, Yuren, et al.
Publicado: (2025)

Tool Preferences in Agentic LLMs are Unreliable
por: Faghih, Kazem, et al.
Publicado: (2025)

What do we learn from inverting CLIP models?
por: Kazemi, Hamid, et al.
Publicado: (2024)

The Lessons of Developing Process Reward Models in Mathematical Reasoning
por: Zhang, Zhenru, et al.
Publicado: (2025)

Can A Gamer Train A Mathematical Reasoning Model?
por: Shin, Andrew
Publicado: (2025)

Unlocking Multimodal Mathematical Reasoning via Process Reward Model
por: Luo, Ruilin, et al.
Publicado: (2025)

Uncertainty Quantification for Language Models: A Suite of Black-Box, White-Box, LLM Judge, and Ensemble Scorers
por: Bouchard, Dylan, et al.
Publicado: (2025)

Self-Error-Instruct: Generalizing from Errors for LLMs Mathematical Reasoning
por: Yu, Erxin, et al.
Publicado: (2025)

Exposing the Achilles' Heel: Evaluating LLMs Ability to Handle Mistakes in Mathematical Reasoning
por: Singh, Joykirat, et al.
Publicado: (2024)

Rewarding Graph Reasoning Process makes LLMs more Generalized Reasoners
por: Peng, Miao, et al.
Publicado: (2025)

Can Post-Training Transform LLMs into Causal Reasoners?
por: Chen, Junqi, et al.
Publicado: (2026)

CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models in Mathematical Reasoning
por: Zheng, Congmin, et al.
Publicado: (2025)

RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems
por: Qu, Yuxiao, et al.
Publicado: (2025)

CHAMP: A Competition-level Dataset for Fine-Grained Analyses of LLMs' Mathematical Reasoning Capabilities
por: Mao, Yujun, et al.
Publicado: (2024)

One Example Shown, Many Concepts Known! Counterexample-Driven Conceptual Reasoning in Mathematical LLMs
por: Li, Yinghui, et al.
Publicado: (2025)

DISPO: Enhancing Training Efficiency and Stability in Reinforcement Learning for Large Language Model Mathematical Reasoning
por: Karaman, Batuhan K., et al.
Publicado: (2026)

Brain-Inspired Two-Stage Approach: Enhancing Mathematical Reasoning by Imitating Human Thought Processes
por: Chen, Yezeng, et al.
Publicado: (2024)

Learning to Reason under Off-Policy Guidance
por: Yan, Jianhao, et al.
Publicado: (2025)

Examining Reasoning LLMs-as-Judges in Non-Verifiable LLM Post-Training
por: Liu, Yixin, et al.
Publicado: (2026)

Certifying LLM Safety against Adversarial Prompting
por: Kumar, Aounon, et al.
Publicado: (2023)

Mathematical Reasoning via Intervention-Based Time-Series Causal Discovery Using LLMs as Concept Mastery Simulators
por: Okita, Tsuyoshi
Publicado: (2026)

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training
por: Liu, Mingjie, et al.
Publicado: (2025)

GraphDancer: Training LLMs to Explore and Reason over Graphs via Two-Stage Curriculum Post-Training
por: Bai, Yuyang, et al.
Publicado: (2026)

InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory
por: Xiao, Chaojun, et al.
Publicado: (2024)

Self-Training Meets Consistency: Improving LLMs' Reasoning with Consistency-Driven Rationale Evaluation
por: Lee, Jaehyeok, et al.
Publicado: (2024)

KDRL: Post-Training Reasoning LLMs via Unified Knowledge Distillation and Reinforcement Learning
por: Xu, Hongling, et al.
Publicado: (2025)

Evaluating Robustness of Reward Models for Mathematical Reasoning
por: Kim, Sunghwan, et al.
Publicado: (2024)

Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level Triggers
por: Yang, Wang, et al.
Publicado: (2026)

Qwen Goes Brrr: Off-the-Shelf RAG for Ukrainian Multi-Domain Document Understanding
por: Bazdyrev, Anton, et al.
Publicado: (2026)