# StoryReasoning Dataset: Using Chain-of-Thought for Scene Understanding and Grounded Story Generation

arXiv: https://arxiv.org/abs/2505.10292 · HTML: https://mlsanity.com/paper/2505.10292/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Hallucination detection and mitigation, one of 17 directions in LLM reasoning.
- Builds on 25 of its 40 references that are in the map.
- First posted on arXiv 15 May 2025.

## Placed in

- LLM reasoning / [Hallucination detection and mitigation](https://mlsanity.com/lr/hallucination-detection-and-mitigation/)

## Builds on (most cited first, 25 of 25)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [Multimodal Chain-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2302.00923/) (2023)
- [VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research](https://mlsanity.com/paper/1904.03493/) (2019)
- [Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval](https://mlsanity.com/paper/2004.01804/) (2020)
- [StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation](https://mlsanity.com/paper/2405.01434/) (2024)
- [Visual Storytelling](https://mlsanity.com/paper/1604.03968/) (2016)
- [REFLECT: Summarizing Robot Experiences for Failure Explanation and Correction](https://mlsanity.com/paper/2306.15724/) (2023)
- [Liger Kernel: Efficient Triton Kernels for LLM Training](https://mlsanity.com/paper/2410.10989/) (2024)
- [Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design](https://mlsanity.com/paper/2305.13035/) (2023)
- [GROUNDHOG: Grounding Large Language Models to Holistic Segmentation](https://mlsanity.com/paper/2402.16846/) (2024)
- [Character-Centric Story Visualization via Visual Planning and Token Alignment](https://mlsanity.com/paper/2210.08465/) (2022)
- [Visual Writing Prompts: Character-Grounded Story Generation with Curated Image Sequences](https://mlsanity.com/paper/2301.08571/) (2023)
- [A Character-Centric Creative Story Generation via Imagination](https://mlsanity.com/paper/2409.16667/) (2024)
- [GroundCap: A Visually Grounded Image Captioning Dataset](https://mlsanity.com/paper/2502.13898/) (2025)
- [Story Generation from Visual Inputs: Techniques, Related Tasks, and Challenges](https://mlsanity.com/paper/2406.02748/) (2024)

## Built on by (most cited first, 3 of 3)

- [NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale](https://mlsanity.com/paper/2508.10711/) (2025)
- [MultivationBench: A Benchmark for Multimodal Sequential Motivation Reasoning](https://mlsanity.com/paper/2607.26465/) (2026)
- [2K-Characters-10K-Stories: A Quality-Gated Stylized Narrative Dataset with Disentangled Control and Sequence Consistency](https://mlsanity.com/paper/2512.05557/) (2025)

## Abstract (arXiv)

Visual storytelling systems struggle to maintain character identity across frames and link actions to appropriate subjects, frequently leading to referential hallucinations. These issues can be addressed through grounding of characters, objects, and other entities on the visual elements. We propose StoryReasoning, a dataset containing 4,178 stories derived from 52,016 movie images, with both structured scene analyses and grounded stories. Each story maintains character and object consistency across frames while explicitly modeling multi-frame relationships through structured tabular representations. Our approach features cross-frame object re-identification using visual similarity and face recognition, chain-of-thought reasoning for explicit narrative modeling, and a grounding scheme that links textual elements to visual entities across multiple frames. We establish baseline performance by fine-tuning Qwen2.5-VL 7B, creating Qwen Storyteller, which performs end-to-end object detection, re-identification, and landmark detection while maintaining consistent object references throughout the story. Evaluation demonstrates a reduction from 4.06 to 3.56 (-12.3%) hallucinations on average per story and an improvement in creativity from 2.58 to 3.38 (+31.0%) when compared to a non-fine-tuned model.