Papers by Dingyi Yang

5 papers
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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations