Papers by Dingyi Yang
ChangJuan: A Comprehensive Benchmark for Book-Length Chinese Story Evaluation (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models (LLMs) have significantly enhanced the capacity of Automatic Story Evaluation. |
| Approach: | They propose a method to distill raw reviews into generally agreed viewpoints across key evaluation aspects such as plot and character. |
| Outcome: | The proposed model outperforms open-source baselines and raises Qwen3’s Kendall’s tau correlation with human judgments from 24.8 to 34.1. |
Synchronized Video Storytelling: Generating Video Narrations with Structured Storyline (2024.acl-long)
Copied to clipboard
| Challenge: | Existing studies on dense video captioning and video story generation have made some progress, but in practical applications, we typically require synchronized narrations for ongoing visual scenes. |
| Approach: | They propose a task of Synchronized Video Storytelling to generate synchronized narrations for videos using a benchmark dataset with rich annotations. |
| Outcome: | The proposed framework can generate narrations with the guidance of the generated or predefined storyline and human evaluations validate the effectiveness. |
HowToNarrate: A General-Domain Benchmark for Synchronized Video Narration with External Knowledge (2026.acl-long)
Copied to clipboard
| Challenge: | Existing MLLMs overemphasize knowledge retrieval while neglecting prior context, causing redundancy and incoherence. |
| Approach: | They propose a framework that combines context compression, knowledge retrieval, and narration generation to improve models' performance. |
| Outcome: | The proposed method significantly improves MLLM performance over existing models. |
Attractive Storyteller: Stylized Visual Storytelling with Unpaired Text (2023.acl-long)
Copied to clipboard
| Challenge: | Xu et al., 2015; Guo e t al, 2022a) focus on generating objective and neutral descriptions of image content without considering style characteristics. |
| Approach: | They propose a task of Stylized Visual Storytelling to generate attractive stylized stories for a photo stream. |
| Outcome: | The proposed framework can generate attractive stories with different styles . it surpasses state-of-the-art methods on automatic and human evaluation metrics. |
What Matters in Evaluating Book-Length Stories? A Systematic Study of Long Story Evaluation (2025.acl-long)
Copied to clipboard
| Challenge: | a new study examines the effectiveness of automated evaluations of book-length stories . aggregation-based and summary-based evaluations excel in detail assessment, the study finds . |
| Approach: | They propose a system for automatic evaluation of book-length stories based on human-centered criteria . they propose aggregation-based and summary-based evaluations to improve accuracy . |
| Outcome: | The proposed evaluation criteria outperforms commercial models like GPT-4o in evaluating human-written or machine-generated stories. |