Scientific Reasoning: Assessment of Multimodal Generative LLMs
On the map: LLM reasoning → Multimodal reasoning
Abstract (arXiv)
Large language models (LLMs) can answer questions and reason about complex tasks, also from the scientific domain. We assess several multimodal LLMs (MLLMs) on ScienceQA and find that Gemini models show the highest accuracy with little context, and the highest textual similarity to human explanations with richer context. Adapter-tuning of smaller MLLMs did not lead to any reliable performance. Training from Gemini outputs consistently underperformed training from the original data.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 8 of its 19 references that are in the map. First posted on arXiv 3 Mar 2025.
Builds on
8 of 19 references.
References · 8
- 2023GPT-4 Technical Reportcited by 18,132
- 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
- 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
- 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
- 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
- 2024PaliGemma: A versatile 3B VLM for transfercited by 679
- 2022Teaching Small Language Models to Reasoncited by 279
- 2024Pixtral 12Bcited by 174
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning
- 2023Gemini in Reasoning: Unveiling Commonsense in Multimodal Large Language Models
- 2024Understanding the Role of LLMs in Multimodal Evaluation Benchmarks
- 2023Are LLMs the Master of All Trades? : Exploring Domain-Agnostic Reasoning Skills of LLMs
- 2025Understanding LLM Scientific Reasoning through Promptings and Model's Explanation on the Answers
- 2025MME-SCI: A Comprehensive and Challenging Science Benchmark for Multimodal Large Language Models
- 2026SciVQR: A Multidisciplinary Multimodal Benchmark for Advanced Scientific Reasoning Evaluation
- 2024Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning