Papers by Haohan Yuan
DomainSum: A Hierarchical Benchmark for Fine-Grained Domain Shift in Abstractive Text Summarization (2025.findings-naacl)
Copied to clipboard
| Challenge: | Abstractive summarization is a crucial task in natural language processing . current research focuses on summarizing specific types of documents . domain shifts between documents affect summarisation performance . |
| Approach: | They propose a hierarchical benchmark to capture fine-grained domain shifts in abstractive summarization. |
| Outcome: | The proposed benchmark measures the generalization capabilities of pre-trained language models and large language models in in-domain and cross-domain settings. |
Understanding LLM Reasoning for Abstractive Summarization (2026.findings-acl)
Copied to clipboard
| Challenge: | Explicit reasoning strategies improve reference-based quality, but weaken factual grounding, whereas implicit reasoning in LRMs shows the opposite tendency. |
| Approach: | They adapt general reasoning strategies to the summarization setting and conduct a large-scale comparative study of 8 reasoning strategies and 3 Large Reasoning Models (LRMs) they find a trade-off between summary quality and factual faithfulness. |
| Outcome: | The proposed reasoning strategies and 3 Large Reasoning Models (LRMs) are compared with 8 reasoning strategies across 8 datasets. |
StrucSum: Graph-Structured Reasoning for Long Document Extractive Summarization with LLMs (2026.findings-eacl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have shown strong performance in zero-shot summarization, but struggle to model document structure and identify salient information in long texts. |
| Approach: | They propose a training-free prompting framework that injects structural signals into prompts via sentence-level graph structures. |
| Outcome: | The proposed framework improves summary quality and factual consistency over baselines and vanilla prompting. |