Papers by Xiao Zong

5 papers
We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning? (2025.acl-long)

Copied to clipboard

Challenge: Existing benchmarks focus more on end-to-end performance, but neglect the underlying principles of knowledge acquisition and generalization.
Approach: They propose a benchmark specifically designed to explore the problem-solving principles by decomposing 6.5K visual math problems into 10.9K step-level questions for evaluation.
Outcome: The proposed benchmark covers 6.5K visual math problems and 10.9K step-level questions spanning 5 layers of knowledge granularity and 67 hierarchical knowledge concepts.
CFSum Coarse-to-Fine Contribution Network for Multimodal Summarization (2023.acl-long)

Copied to clipboard

Challenge: Existing multimodal summarization models ignore the contribution of visual modalities . we propose a novel contribution network to consider different contributions of images .
Approach: They propose a Coarse-to-Fine contribution network for multimodal summarization to consider different contributions of images for summarizing.
Outcome: The proposed system outperforms baselines on the visual and textual modalities.
TROVE: A Challenge for Fine-Grained Text Provenance via Source Sentence Tracing and Relationship Classification (2025.acl-long)

Copied to clipboard

Challenge: Large language models have demonstrated great potential in natural language generation, but their widespread adoption has raised concerns regarding content reliability and accountability.
Approach: They propose a challenge to trace each sentence of a target text back to specific source sentences within potentially lengthy or multi-document inputs.
Outcome: The proposed challenge traces each sentence of a target text back to specific source sentences . the dataset includes 11 scenarios covering QA and summarization in english and Chinese .
AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora (2026.acl-long)

Copied to clipboard

Challenge: Existing knowledge graph construction frameworks require predefined schemas, limiting their scalability and domain coverage.
Approach: They propose a framework for fully autonomous knowledge graph construction that eliminates the need for predefined schemas.
Outcome: The proposed framework outperforms state-of-the-art models on multi-hop QA tasks and enhances LLM factuality.
Pay More Attention to Images: Numerous Images-Oriented Multimodal Summarization (2025.naacl-long)

Copied to clipboard

Challenge: Existing multimodal summarization approaches struggle with scenarios involving multiple images as input.
Approach: They propose a task to generate multimodal summaries by integrating multiple images as input . they propose 'multimodal information evaluation' method that measures differences between generated summary and input based on multimodal input - and compares various methods .
Outcome: The proposed method correlates more closely with human judgments than five widely used metrics .

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