mlsanityData to 14 Oct 2026

LLaVA-Critic: Learning to Evaluate Multimodal Models

arXiv 2410.02712 ↗First posted 3 Oct 2024cs.CV cs.CLcited by 134

On the map: Multimodal LLMs / vision-language models → MLLM training and visual instruction tuning

Abstract (arXiv)

We introduce LLaVA-Critic, the first open-source large multimodal model (LMM) designed as a generalist evaluator to assess performance across a wide range of multimodal tasks. LLaVA-Critic is trained using a high-quality critic instruction-following dataset that incorporates diverse evaluation criteria and scenarios. Our experiments demonstrate the model's effectiveness in two key areas: (1) LMM-as-a-Judge, where LLaVA-Critic provides reliable evaluation scores, performing on par with or surpassing GPT models on multiple evaluation benchmarks; and (2) Preference Learning, where it generates reward signals for preference learning, enhancing model alignment capabilities. This work underscores the potential of open-source LMMs in self-critique and evaluation, setting the stage for future research into scalable, superhuman alignment feedback mechanisms for LMMs.

Key facts. Cited by 134 papers in the map (data through 14 Oct 2026). Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 38 of its 54 references that are in the map. First posted on arXiv 3 Oct 2024.

Builds on

38 of 54 references.

Closest ancestors · 16

Same direction, newest first

  1. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution18 Sep
  2. 2024LLaVA-OneVision: Easy Visual Task Transfer6 Aug
  3. 2024LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models17 Jul
  4. 2024Calibrated Self-Rewarding Vision Language Models23 May
  5. 2024MANTIS: Interleaved Multi-Image Instruction Tuning2 May
  6. 2024Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization13 Mar
  7. 2024MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark7 Feb
  8. 2024Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences19 Jan
  9. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks21 Dec
  10. 2023Silkie: Preference Distillation for Large Visual Language Models17 Dec
  11. 2023VILA: On Pre-training for Visual Language Models12 Dec
  12. 2023What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Instruction Tuning2 Nov
4 more
  1. 2023Improved Baselines with Visual Instruction Tuning5 Oct
  2. 2023Aligning Large Multimodal Models with Factually Augmented RLHF25 Sep
  3. 2023MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities4 Aug
  4. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning11 May

Other references · 22

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  4. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  5. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,224
  6. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,986
  7. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,917
  8. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Daycited by 1,305
  9. 2024MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?cited by 586
  10. 2023HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Modelscited by 583
  11. 2023RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedbackcited by 412
  12. 2023LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understandingcited by 274
10 more
  1. 2023Multimodal Foundation Models: From Specialists to General-Purpose Assistantscited by 247
  2. 2024Aligning Modalities in Vision Large Language Models via Preference Fine-tuningcited by 198
  3. 2023SVIT: Scaling up Visual Instruction Tuningcited by 162
  4. 2024LLM Critics Help Catch LLM Bugscited by 147
  5. 2023M3IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuningcited by 126
  6. 2024Prometheus-Vision: Vision-Language Model as a Judge for Fine-Grained Evaluationcited by 125
  7. 2023GPT-4V(ision) as a Generalist Evaluator for Vision-Language Taskscited by 119
  8. 2024WildVision: Evaluating Vision-Language Models in the Wild with Human Preferencescited by 76
  9. 2024Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvementcited by 74
  10. 2023Towards End-to-End Embodied Decision Making via Multi-modal Large Language Model: Explorations with GPT4-Vision and Beyondcited by 51

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 7; 2025: 83; 2026: 44.

134 papers.

Sort:

By area:

  1. 2024LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methodscited by 465
  2. 2024Agent-as-a-Judge: Evaluate Agents with Agentscited by 238
  3. 2025Unified Reward Model for Multimodal Understanding and Generationcited by 199
  4. 2025Thyme: Think Beyond Imagescited by 167
  5. 2025LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMscited by 147
  6. 2025SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvementcited by 145
  7. 2025LLM Post-Training: A Deep Dive into Reasoning Large Language Modelscited by 135
  8. 2025Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuningcited by 90
  9. 2024VL-RewardBench: A Challenging Benchmark for Vision-Language Generative Reward Modelscited by 86
  10. 2025MM-RLHF: The Next Step Forward in Multimodal LLM Alignmentcited by 83
  11. 2025InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Modelcited by 74
  12. 2025Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Modelscited by 70
38 more
  1. 2025Vision-R1: Evolving Human-Free Alignment in Large Vision-Language Models via Vision-Guided Reinforcement Learningcited by 69
  2. 2025R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learningcited by 65
  3. 2026Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agentscited by 64
  4. 2025MindJourney: Test-Time Scaling with World Models for Spatial Reasoningcited by 50
  5. 2025Multimodal RewardBench: Holistic Evaluation of Reward Models for Vision Language Modelscited by 44
  6. 2025Teaching Language Models to Critique via Reinforcement Learningcited by 42
  7. 2025A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoningcited by 40
  8. 2025LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Modelcited by 35
  9. 2025MINERVA: Evaluating Complex Video Reasoningcited by 32
  10. 2025UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generationcited by 32
  11. 2025Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMscited by 32
  12. 2025AlphaOne: Reasoning Models Thinking Slow and Fast at Test Timecited by 29
  13. 2026LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decodingcited by 28
  14. 2025Look Before You Leap: A GUI-Critic-R1 Model for Pre-Operative Error Diagnosis in GUI Automationcited by 27
  15. 2025ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMscited by 25
  16. 2025Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1)cited by 23
  17. 2025Process-based Self-Rewarding Language Modelscited by 22
  18. 2024MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimizationcited by 21
  19. 2025Evaluating MLLMs with Multimodal Multi-image Reasoning Benchmarkcited by 21
  20. 2025Multimodal RewardBench 2: Evaluating Omni Reward Models for Interleaved Text and Imagecited by 20
  21. 2024LoRA.rar: Learning to Merge LoRAs via Hypernetworks for Subject-Style Conditioned Image Generationcited by 19
  22. 2025Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuningcited by 19
  23. 2025Uncertainty Quantification for Language Models: A Suite of Black-Box, White-Box, LLM Judge, and Ensemble Scorerscited by 18
  24. 2025ImAgent: A Unified Multimodal Agent Framework for Test-Time Scalable Image Generationcited by 17
  25. 2025ViLBench: A Suite for Vision-Language Process Reward Modelingcited by 16
  26. 2025CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalizationcited by 16
  27. 2025BaseReward: A Strong Baseline for Multimodal Reward Modelcited by 15
  28. 2025Multi-Crit: Benchmarking Multimodal Judges on Pluralistic Criteria-Followingcited by 15
  29. 2024VISCO: Benchmarking Fine-Grained Critique and Correction Towards Self-Improvement in Visual Reasoningcited by 14
  30. 2025Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewardscited by 14
  31. 2025Aligning Multimodal LLM with Human Preference: A Surveycited by 13
  32. 2025Perception in Reflectioncited by 13
  33. 2025Generative RLHF-V: Learning Principles from Multi-modal Human Preferencecited by 13
  34. 2025IndustryEQA: Pushing the Frontiers of Embodied Question Answering in Industrial Scenarioscited by 13
  35. 2025Sherlock: Self-Correcting Reasoning in Vision-Language Modelscited by 13
  36. 2025ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoningcited by 13
  37. 2026Unified Personalized Reward Model for Vision Generationcited by 13
  38. 2025VR-Thinker: Boosting Video Reward Models through Thinking-with-Image Reasoningcited by 12

50 most cited of 134 All 134 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025MM-CRITIC: A Holistic Evaluation of Large Multimodal Models as Multimodal Critique
  2. 2026MMPostTrainBench: Benchmarking Autonomous Research for Multimodal Post-Training
  3. 2023Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context Learning
  4. 2025LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training
  5. 2023An Empirical Study of Scaling Instruct-Tuned Large Multimodal Models
  6. 2026Judge Model for Large-scale Multimodality Benchmarks
  7. 2024Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback
  8. 2024Error-driven Data-efficient Large Multimodal Model Tuning