Cover Image

ProJudge: A Multi-Modal Multi-Discipline Benchmark and Instruction-Tuning Dataset for MLLM-based Process Judges

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ai, Jiaxin, Zhou, Pengfei, Xu, Zhaopan, Li, Ming, Zhang, Fanrui, Li, Zizhen, Sun, Jianwen, Feng, Yukang, Huang, Baojin, Wang, Zhongyuan, Zhang, Kaipeng
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MDK12-Bench: A Multi-Discipline Benchmark for Evaluating Reasoning in Multimodal Large Language Models
by: Zhou, Pengfei, et al.
Published: (2025)

Closing the Expression Gap in LLM Instructions via Socratic Questioning
by: Sun, Jianwen, et al.
Published: (2025)

From Pixels to Paths: A Multi-Agent Framework for Editable Scientific Illustration
by: Sun, Jianwen, et al.
Published: (2025)

ProSoftArena: Benchmarking Hierarchical Capabilities of Multimodal Agents in Professional Software Environments
by: Ai, Jiaxin, et al.
Published: (2025)

A High-Quality Dataset and Reliable Evaluation for Interleaved Image-Text Generation
by: Feng, Yukang, et al.
Published: (2025)

ARMOR: Empowering Multimodal Understanding Model with Interleaved Multimodal Generation Capability
by: Sun, Jianwen, et al.
Published: (2025)

MeepleLM: A Virtual Playtester Simulating Diverse Subjective Experiences
by: Li, Zizhen, et al.
Published: (2026)

InMind: Evaluating LLMs in Capturing and Applying Individual Human Reasoning Styles
by: Li, Zizhen, et al.
Published: (2025)

World Craft: Agentic Framework to Create Visualizable Worlds via Text
by: Sun, Jianwen, et al.
Published: (2026)

AutoBG: A Board Game Design Assistant with Interactive Ideation, Iterative Rulebook Generation, and Individualized Feedback
by: Li, Zizhen, et al.
Published: (2026)

Sekai: A Video Dataset towards World Exploration
by: Li, Zhen, et al.
Published: (2025)

Code-in-the-Loop Forensics: Agentic Tool Use for Image Forgery Detection
by: Zhang, Fanrui, et al.
Published: (2025)

SridBench: Benchmark of Scientific Research Illustration Drawing of Image Generation Model
by: Chang, Yifan, et al.
Published: (2025)

Judge Anything: MLLM as a Judge Across Any Modality
by: Pu, Shu, et al.
Published: (2025)

MPBench: A Comprehensive Multimodal Reasoning Benchmark for Process Errors Identification
by: Xu, Zhaopan, et al.
Published: (2025)

ConfProBench: A Confidence Evaluation Benchmark for MLLM-Based Process Judges
by: Zhou, Yue, et al.
Published: (2025)

PEBench: A Fictitious Dataset to Benchmark Machine Unlearning for Multimodal Large Language Models
by: Xu, Zhaopan, et al.
Published: (2025)

MDK12-Bench: A Comprehensive Evaluation of Multimodal Large Language Models on Multidisciplinary Exams
by: Zhou, Pengfei, et al.
Published: (2025)

MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark
by: Chen, Dongping, et al.
Published: (2024)

LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces
by: Feng, Yukang, et al.
Published: (2026)

OpenING: A Comprehensive Benchmark for Judging Open-ended Interleaved Image-Text Generation
by: Zhou, Pengfei, et al.
Published: (2024)

MM-JudgeBias: A Benchmark for Evaluating Compositional Biases in MLLM-as-a-Judge
by: Lee, Sua, et al.
Published: (2026)

Judging the Judges: Human Validation of Multi-LLM Evaluation for High-Quality K--12 Science Instructional Materials
by: He, Peng, et al.
Published: (2026)

Human-Aligned Bench: Fine-Grained Assessment of Reasoning Ability in MLLMs vs. Humans
by: Qiu, Yansheng, et al.
Published: (2025)

Multi-Crit: Benchmarking Multimodal Judges on Pluralistic Criteria-Following
by: Xiong, Tianyi, et al.
Published: (2025)

AI Idea Bench 2025: AI Research Idea Generation Benchmark
by: Qiu, Yansheng, et al.
Published: (2025)

IA-T2I: Internet-Augmented Text-to-Image Generation
by: Li, Chuanhao, et al.
Published: (2025)

RankJudge: A Multi-Turn LLM-as-a-Judge Synthetic Benchmark Generator
by: Tang, Zhenwei, et al.
Published: (2026)

VideoJudge: Bootstrapping Enables Scalable Supervision of MLLM-as-a-Judge for Video Understanding
by: Waheed, Abdul, et al.
Published: (2025)

ProBench: Judging Multimodal Foundation Models on Open-ended Multi-domain Expert Tasks
by: Yang, Yan, et al.
Published: (2025)

MLLM-CTBench: A Benchmark for Continual Instruction Tuning with Reasoning Process Diagnosis
by: Guo, Haiyun, et al.
Published: (2025)

MLLM-as-a-Judge for Image Safety without Human Labeling
by: Wang, Zhenting, et al.
Published: (2024)

IF-RewardBench: Benchmarking Judge Models for Instruction-Following Evaluation
by: Wen, Bosi, et al.
Published: (2026)

Human-Aligned MLLM Judges for Fine-Grained Image Editing Evaluation: A Benchmark, Framework, and Analysis
by: Liu, Runzhou, et al.
Published: (2026)

Benchmarking LLM-as-a-Judge for Long-Form Output Evaluation
by: Chen, Junjie, et al.
Published: (2026)

Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmark
by: Song, Enxin, et al.
Published: (2025)

MCJudgeBench: A Benchmark for Constraint-Level Judge Evaluation in Multi-Constraint Instruction Following
by: Lee, Jaeyun, et al.
Published: (2026)

MLLM as a UI Judge: Benchmarking Multimodal LLMs for Predicting Human Perception of User Interfaces
by: Luera, Reuben A., et al.
Published: (2025)

Judge Before Answer: Can MLLM Discern the False Premise in Question?
by: Li, Jidong, et al.
Published: (2025)

MLLM-as-a-Judge Exhibits Model Preference Bias
by: Koyama, Shuitsu, et al.
Published: (2026)