mlsanityData to 7 Oct 2026

Assessment of Multimodal Large Language Models in Alignment with Human Values

arXiv 2403.17830 ↗First posted 26 Mar 2024cs.CVcited by 36

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

also in 1 more
Abstract (arXiv)

Large Language Models (LLMs) aim to serve as versatile assistants aligned with human values, as defined by the principles of being helpful, honest, and harmless (hhh). However, in terms of Multimodal Large Language Models (MLLMs), despite their commendable performance in perception and reasoning tasks, their alignment with human values remains largely unexplored, given the complexity of defining hhh dimensions in the visual world and the difficulty in collecting relevant data that accurately mirrors real-world situations. To address this gap, we introduce Ch3Ef, a Compreh3ensive Evaluation dataset and strategy for assessing alignment with human expectations. Ch3Ef dataset contains 1002 human-annotated data samples, covering 12 domains and 46 tasks based on the hhh principle. We also present a unified evaluation strategy supporting assessment across various scenarios and different perspectives. Based on the evaluation results, we summarize over 10 key findings that deepen the understanding of MLLM capabilities, limitations, and the dynamic relationships between evaluation levels, guiding future advancements in the field.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 75 of its 100 references that are in the map. First posted on arXiv 26 Mar 2024.

Builds on

75 of 100 references.

Closest ancestors · 14

Same direction, newest first

  1. 2024From GPT-4 to Gemini and Beyond: Assessing the Landscape of MLLMs on Generalizability, Trustworthiness and Causality through Four Modalities26 Jan
  2. 2023VILA: On Pre-training for Visual Language Models12 Dec
  3. 2023SEED-Bench-2: Benchmarking Multimodal Large Language Models28 Nov
  4. 2023mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration7 Nov
  5. 2023Improved Baselines with Visual Instruction Tuning5 Oct
  6. 2023Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context Learning1 Oct
  7. 2023Aligning Large Multimodal Models with Factually Augmented RLHF25 Sep
  8. 2023SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension30 Jul
  9. 2023MMBench: Is Your Multi-modal Model an All-around Player?12 Jul
  10. 2023Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic27 Jun
  11. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models23 Jun
  12. 2023LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models15 Jun
2 more
  1. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning11 May
  2. 2023Otter: A Multi-Modal Model with In-Context Instruction Tuning5 May

Other references · 61

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2022Training language models to follow instructions with human feedbackcited by 15,712
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  6. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  7. 2023Visual Instruction Tuningcited by 7,792
  8. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  9. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  10. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  11. 2020Learning to summarize from human feedbackcited by 2,562
  12. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,179
38 more
  1. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,044
  2. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,881
  3. 2019Towards VQA Models That Can Readcited by 1,696
  4. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,696
  5. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,184
  6. 2023GAIA: a benchmark for General AI Assistantscited by 1,084
  7. 2023Kosmos-2: Grounding Multimodal Large Language Models to the Worldcited by 1,075
  8. 2021A General Language Assistant as a Laboratory for Alignmentcited by 1,023
  9. 2021Ethical and social risks of harm from Language Modelscited by 957
  10. 2023BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Datasetcited by 828
  11. 2023Multimodal Chain-of-Thought Reasoning in Language Modelscited by 740
  12. 2023Can Large Language Models Be an Alternative to Human Evaluations?cited by 729
  13. 2023Safe RLHF: Safe Reinforcement Learning from Human Feedbackcited by 630
  14. 2023LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Modelcited by 602
  15. 2023DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Modelscited by 505
  16. 2020The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memescited by 485
  17. 2020Artificial Intelligence, Values and Alignmentcited by 443
  18. 2017On Fairness and Calibrationcited by 406
  19. 2023RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedbackcited by 404
  20. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 394
  21. 2023Preference Ranking Optimization for Human Alignmentcited by 283
  22. 2024TrustLLM: Trustworthiness in Large Language Modelscited by 280
  23. 2017OpenNMT: Open-source Toolkit for Neural Machine Translationcited by 251
  24. 2022Selective Annotation Makes Language Models Better Few-Shot Learnerscited by 242
  25. 2023DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Drivingcited by 233
  26. 2024SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Modelscited by 225
  27. 2023Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignmentcited by 213
  28. 2020RSVQA: Visual Question Answering for Remote Sensing Datacited by 197
  29. 2023SlideVQA: A Dataset for Document Visual Question Answering on Multiple Imagescited by 175
  30. 2023RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shotcited by 173
  31. 2023LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmarkcited by 169
  32. 2023Habitat Synthetic Scenes Dataset (HSSD-200): An Analysis of 3D Scene Scale and Realism Tradeoffs for ObjectGoal Navigationcited by 162
  33. 2024Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Modelscited by 160
  34. 2023Sociotechnical Safety Evaluation of Generative AI Systemscited by 154
  35. 2021Learning To Count Everythingcited by 149
  36. 2024A Minimaximalist Approach to Reinforcement Learning from Human Feedbackcited by 141
  37. 2024Aligner: Efficient Alignment by Learning to Correctcited by 96
  38. 2020Uncertainty-based Traffic Accident Anticipation with Spatio-Temporal Relational Learningcited by 91

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 14; 2025: 17; 2026: 5.

36 papers.

Sort:

By area:

  1. 2024WorldSimBench: Towards Video Generation Models as World Simulatorscited by 867
  2. 2024SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Modelcited by 82
  3. 2024VLSBench: Unveiling Visual Leakage in Multimodal Safetycited by 59
  4. 2024Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detectioncited by 59
  5. 2024MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Modelscited by 51
  6. 2025T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generationcited by 47
  7. 2024MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Modelscited by 34
  8. 2024GenderBias-VL: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probingcited by 31
  9. 2025SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearningcited by 31
  10. 2025Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainabilitycited by 28
  11. 2024VLBiasBench: A Comprehensive Benchmark for Evaluating Bias in Large Vision-Language Modelcited by 26
  12. 2024Safe Inputs but Unsafe Output: Benchmarking Cross-modality Safety Alignment of Large Vision-Language Modelcited by 24
24 more
  1. 2025Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Modelscited by 21
  2. 2024The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and Defensecited by 20
  3. 2024Self-Cognition in Large Language Models: An Exploratory Studycited by 14
  4. 2025AI Sees Your Location, But With A Bias Toward The Wealthy Worldcited by 14
  5. 2025BBQ-V: Benchmarking Visual Stereotype Bias in Large Multimodal Modelscited by 10
  6. 2025MORALISE: A Structured Benchmark for Moral Alignment in Visual Language Modelscited by 10
  7. 2025SEA: Low-Resource Safety Alignment for Multimodal Large Language Models via Synthetic Embeddingscited by 9
  8. 2025Dive into the Agent Matrix: A Realistic Evaluation of Self-Replication Risk in LLM Agentscited by 5
  9. 2025REVEAL: Multi-turn Evaluation of Image-Input Harms for Vision LLMcited by 4
  10. 2025Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Modelscited by 4
  11. 2025Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalitiescited by 4
  12. 2024Multi-PA: A Multi-perspective Benchmark on Privacy Assessment for Large Vision-Language Modelscited by 3
  13. 2025SDEval: Safety Dynamic Evaluation for Multimodal Large Language Modelscited by 3
  14. 2025Harmonious Parameter Adaptation in Continual Visual Instruction Tuning for Safety-Aligned MLLMscited by 3
  15. 2025From Evaluation to Defense: Advancing Safety in Video Large Language Modelscited by 2
  16. 2025Aligning VLM Assistants with Personalized Situated Cognitioncited by 2
  17. 2025Self-adaptive Dataset Construction for Real-World Multimodal Safety Scenarioscited by 2
  18. 2024Drawing the Line: Enhancing Trustworthiness of MLLMs Through the Power of Refusalcited by 1
  19. 2026OCR-Agent: Agentic OCR with Capability and Memory Reflectioncited by 1
  20. 2026ValueGround: Evaluating Culture-Conditioned Visual Value Grounding in MLLMscited by 1
  21. 2024Technical Report for ICML 2024 TiFA Workshop MLLM Attack Challenge: Suffix Injection and Projected Gradient Descent Can Easily Fool An MLLMcited by 0
  22. 2026Automatic Hard Example Synthesis with Multi-Level Agentic Data Curationcited by 0
  23. 2026Toward a Theory of Value in AI Alignmentcited by 0
  24. 2026MAVEN: A Macro-Societal Value Evaluation Framework of Multimodal Content with Compact Aligned Evaluatorscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Aligning Multimodal LLM with Human Preference: A Survey
  2. 2023From Instructions to Intrinsic Human Values -- A Survey of Alignment Goals for Big Models
  3. 2023Large Language Models as Automated Aligners for benchmarking Vision-Language Models
  4. 2024Understanding Alignment in Multimodal LLMs: A Comprehensive Study
  5. 2025MM-RLHF: The Next Step Forward in Multimodal LLM Alignment
  6. 2025Aligning MLLM Benchmark With Human Preferences via Structural Equation Modeling
  7. 2023Sight Beyond Text: Multi-Modal Training Enhances LLMs in Truthfulness and Ethics
  8. 2025OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference