Image de couverture de livre

Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yuan, Youliang, Mang, Qiuyang, Chen, Jingbang, Wan, Hong, Liu, Xiaoyuan, Xu, Junjielong, Huang, Jen-tse, Wang, Wenxuan, Jiao, Wenxiang, He, Pinjia
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models
par: Wan, Yuxuan, et autres
Publié: (2024)

GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher
par: Yuan, Youliang, et autres
Publié: (2023)

Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training
par: Yuan, Youliang, et autres
Publié: (2024)

Towards Evaluating Proactive Risk Awareness of Multimodal Language Models
par: Yuan, Youliang, et autres
Publié: (2025)

Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMs
par: Liu, Xiaoyuan, et autres
Publié: (2024)

Chain-of-Jailbreak Attack for Image Generation Models via Editing Step by Step
par: Wang, Wenxuan, et autres
Publié: (2024)

Can't See the Forest for the Trees: Benchmarking Multimodal Safety Awareness for Multimodal LLMs
par: Wang, Wenxuan, et autres
Publié: (2025)

Human Cognitive Benchmarks Reveal Foundational Visual Gaps in MLLMs
par: Huang, Jen-Tse, et autres
Publié: (2025)

All Languages Matter: On the Multilingual Safety of Large Language Models
par: Wang, Wenxuan, et autres
Publié: (2023)

Scalable Supervising Software Agents with Patch Reasoner
par: Xu, Junjielong, et autres
Publié: (2025)

Step-wise Rubric Rewards for LLM Reasoning
par: Xie, Weichu, et autres
Publié: (2026)

On the Shortcut Learning in Multilingual Neural Machine Translation
par: Wang, Wenxuan, et autres
Publié: (2024)

Learning to Ask: When LLM Agents Meet Unclear Instruction
par: Wang, Wenxuan, et autres
Publié: (2024)

Aligning the Objective of LLM-based Program Repair
par: Xu, Junjielong, et autres
Publié: (2024)

VisBias: Measuring Explicit and Implicit Social Biases in Vision Language Models
par: Huang, Jen-tse, et autres
Publié: (2025)

Who is ChatGPT? Benchmarking LLMs' Psychological Portrayal Using PsychoBench
par: Huang, Jen-tse, et autres
Publié: (2023)

Nearly Optimal Internal Dictionary Matching
par: Chen, Jingbang, et autres
Publié: (2023)

AL-Bench: A Benchmark for Automatic Logging
par: Tan, Boyin, et autres
Publié: (2025)

Identifying the Achilles' Heel: An Iterative Method for Dynamically Uncovering Factual Errors in Large Language Models
par: Wang, Wenxuan, et autres
Publié: (2024)

Not All Countries Celebrate Thanksgiving: On the Cultural Dominance in Large Language Models
par: Wang, Wenxuan, et autres
Publié: (2023)

How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environments
par: Huang, Jen-tse, et autres
Publié: (2024)

New Job, New Gender? Measuring the Social Bias in Image Generation Models
par: Wang, Wenxuan, et autres
Publié: (2024)

Revisiting the Reliability of Psychological Scales on Large Language Models
par: Huang, Jen-tse, et autres
Publié: (2023)

AI Sees Your Location, But With A Bias Toward The Wealthy World
par: Huang, Jingyuan, et autres
Publié: (2025)

On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents
par: Huang, Jen-tse, et autres
Publié: (2024)

Difficult Task Yes but Simple Task No: Unveiling the Laziness in Multimodal LLMs
par: Zhao, Sihang, et autres
Publié: (2024)

Scalable Algorithm for Finding Balanced Subgraphs with Tolerance in Signed Networks
par: Chen, Jingbang, et autres
Publié: (2024)

Prompting for Automatic Log Template Extraction
par: Xu, Junjielong, et autres
Publié: (2023)

On the Failure of Latent State Persistence in Large Language Models
par: Huang, Jen-tse, et autres
Publié: (2025)

Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards
par: Liu, Xiaoyuan, et autres
Publié: (2025)

Semantic Router: On the Feasibility of Hijacking MLLMs via a Single Adversarial Perturbation
par: Li, Changyue, et autres
Publié: (2025)

SHAPE: Unifying Safety, Helpfulness and Pedagogy for Educational LLMs
par: Zhao, Sihang, et autres
Publié: (2026)

CodeCrash: Exposing LLM Fragility to Misleading Natural Language in Code Reasoning
par: Lam, Man Ho, et autres
Publié: (2025)

Emotionally Numb or Empathetic? Evaluating How LLMs Feel Using EmotionBench
par: Huang, Jen-tse, et autres
Publié: (2023)

OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment
par: Liu, Tianci, et autres
Publié: (2025)

A Goal-Driven Survey on Root Cause Analysis
par: Fang, Aoyang, et autres
Publié: (2025)

SWE-Manager: Selecting and Synthesizing Golden Proposals Before Coding
par: Tan, Boyin, et autres
Publié: (2026)

AutoRubric: Rubric-Based Generative Rewards for Faithful Multimodal Reasoning
par: Jia, Mengzhao, et autres
Publié: (2025)

MicLog: Towards Accurate and Efficient LLM-based Log Parsing via Progressive Meta In-Context Learning
par: Yu, Jianbo, et autres
Publié: (2026)

Scalable Approximate Biclique Counting over Large Bipartite Graphs
par: Chen, Jingbang, et autres
Publié: (2025)