mlsanityData to 7 Oct 2026

Chain-of-Description: What I can understand, I can put into words

arXiv 2502.16137 ↗First posted 22 Feb 2025cs.CL cs.AIcited by 0

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

Abstract (arXiv)

In this paper, we propose a novel strategy defined as Chain-of-Description (CoD) Prompting, tailored for Multi-Modal Large Language Models. This approach involves having the model first provide a detailed description of the multi-modal input before generating an answer to the question. When applied to models such as Qwen2-Audio, Qwen2-VL, and Qwen2.5-VL, CoD Prompting significantly enhances performance compared to standard prompting methods. This is demonstrated by nearly a 4% improvement in the speech category of the audio benchmark AIR-Bench-Chat and a 5.3% improvement in the hard-level portion of the vision benchmark MMMUPro. Our ablation study further validates the effectiveness of CoD Prompting.

Key facts. No citing papers in the map yet (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 15 of its 20 references that are in the map. First posted on arXiv 22 Feb 2025.

Builds on

15 of 20 references.

Closest ancestors · 5

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. 2024How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites25 Apr
  4. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks21 Dec
  5. 2023NExT-GPT: Any-to-Any Multimodal LLM11 Sep

Other references · 10

  1. 2024A Survey on LLM-as-a-Judgecited by 1,384
  2. 2023Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Modelscited by 591
  3. 2024MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmarkcited by 494
  4. 2024LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methodscited by 451
  5. 2024AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehensioncited by 215
  6. 2024Mini-Omni: Language Models Can Hear, Talk While Thinking in Streamingcited by 204
  7. 2024LMFusion: Adapting Pretrained Language Models for Multimodal Generationcited by 120
  8. 2024SpeechVerse: A Large-scale Generalizable Audio Language Modelcited by 62
  9. 2024EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotionscited by 44
  10. 2023The Role of Chain-of-Thought in Complex Vision-Language Reasoning Taskcited by 32

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Chain-of-Thought Prompting for Speech Translation
  2. 2025QG-CoC: Question-Guided Chain-of-Captions for Large Multimodal Models
  3. 2024Chain-of-Thought in Large Language Models: Decoding, Projection, and Activation
  4. 2023Analyzing Chain-of-Thought Prompting in Large Language Models via Gradient-based Feature Attributions
  5. 2025Listening or Reading? Evaluating Speech Awareness in Chain-of-Thought Speech-to-Text Translation
  6. 2025Chain of Questions: Guiding Multimodal Curiosity in Language Models
  7. 2023Towards Better Chain-of-Thought Prompting Strategies: A Survey
  8. 2024Interleaved-Modal Chain-of-Thought