Papers by Haopeng Zhang
XATU: A Fine-grained Instruction-based Benchmark for Explainable Text Updates (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing text editing benchmark datasets contain coarse-grained instructions and lack explainability, resulting in outputs that deviate from intended changes. |
| Approach: | They propose a benchmark specifically designed for fine-grained instruction-based explainable text editing. |
| Outcome: | The proposed benchmark incorporates fine-grained instructions and gold-standard edit explanations. |
Extractive Summarization via ChatGPT for Faithful Summary Generation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Abstractive summarization methods struggle with generating ungrammatical or even nonfactual contents. |
| Approach: | They evaluate ChatGPT's performance on extractive summarization and compare it with traditional fine-tuning methods on benchmark datasets. |
| Outcome: | The proposed pipeline performs better than abstractive methods on summary faithfulness and in-context learning. |
Conversational Recommender System and Large Language Model Are Made for Each Other in E-commerce Pre-sales Dialogue (2023.findings-emnlp)
Copied to clipboard
Yuanxing Liu, Weinan Zhang, Yifan Chen, Yuchi Zhang, Haopeng Bai, Fan Feng, Hengbin Cui, Yongbin Li, Wanxiang Che
| Challenge: | E-commerce pre-sales dialogues elicit user needs and preferences for items . large language models lack domain-specific knowledge for accurate recommendations . |
| Approach: | They propose two collaboration strategies to integrate CRS and large language models in pre-sales dialogues. |
| Outcome: | The proposed methods can be very effective in some cases, the authors say . |
SummIt: Iterative Text Summarization via ChatGPT (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing text summarization systems generate summaries in a single step, but are often inadequate due to the issue of hallucination and the lack of accuracy. |
| Approach: | They propose an iterative text summarization framework based on large language models like ChatGPT that refines the generated summary iterativly through self-evaluation and feedback. |
| Outcome: | The proposed framework refines the generated summary iteratively through self-evaluation and feedback, closely resembling the iteration humans undertake when drafting and revising summaries. |
FormosanBench: Benchmarking Low-Resource Austronesian Languages in the Era of Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing LLMs consistently underperform across all tasks, with 10-shot learning and fine-tuning offering only limited improvements. |
| Approach: | They introduce FormosanBench, a benchmark for evaluating LLMs on low-resource Austronesian languages. |
| Outcome: | The proposed benchmark covers three endangered Formosan languages: Atayal, Amis, and Paiwan . existing LLMs consistently underperform across all tasks, with 10-shot learning and fine-tuning offering only limited improvements. |
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. |
Text Graph Transformer for Document Classification (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for text classification are not scalable to large corpus and ignore heterogeneity of text graph. |
| Approach: | They propose a Transformer-based heterogeneous graph neural network that captures structure and heterogenity from the text graph. |
| Outcome: | The proposed model outperforms state-of-the-art methods on large-sized corpus datasets and significantly reduces computing and memory costs. |
HEGEL: Hypergraph Transformer for Long Document Summarization (2022.emnlp-main)
Copied to clipboard
| Challenge: | Abstract: Extractive summarization for long documents is challenging due to the extended structured input context. |
| Approach: | They propose a hypergraph neural network for extractive summarization by capturing cross-sentence relations. |
| Outcome: | The proposed model can capture cross-sentence relations and latent topics and keywords coreference, and section structure, and can be applied to scientific papers. |
Global Context or Local Detail? Adaptive Visual Grounding for Hallucination Mitigation (2026.findings-acl)
Copied to clipboard
Yubo Jiang, Xin Yang, Abudukelimu Wuerkaixi, Zheming Yuan, Xuxin Cheng, Cao Liu, Ke Zeng, Fengying Xie, Zhiguo Jiang, Haopeng Zhang
| Challenge: | Large vision–language models suffer from object-existence hallucinations when multi-step deliberation decouples from visual evidence. |
| Approach: | They propose a framework that allocates visual computation by uncertainty . they propose highlighting retains global context, while selective zoom-in performs local verification. |
| Outcome: | The proposed framework reduces the complexity of multimodal reasoning by minimizing the operator trade-off. |
Unveiling the Magic: Investigating Attention Distillation in Retrieval-Augmented Generation (2024.naacl-short)
Copied to clipboard
| Challenge: | Retrieval-augmented generation framework addresses the limitations of large language models by enabling real-time knowledge updates for more accurate answers. |
| Approach: | They propose to use attention distillation to improve retrieval-augmented language models' learning performance by identifying key factors influencing their workflow and proposing indicators for optimizing models’ training methods and avoiding ineffective training. |
| Outcome: | The proposed framework improves the learning performance of large language models in the training phase but also reduces the impact of ineffective training. |
Token-Level Precise Attack on RAG: Searching for the Best Alternatives to Mislead Generation (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing approaches to attack large language models rely heavily on retrieval and generation stages, limiting their effectiveness in black-box scenarios. |
| Approach: | They propose a retrieval-augmented generation framework that leverages a white-box LLM as an attacker to generate and iteratively optimize malicious passages at the token level. |
| Outcome: | The proposed framework outperforms existing approaches in retrieval-stage and end-to-end attacks on black-box RAG systems. |
DiffuSum: Generation Enhanced Extractive Summarization with Diffusion (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for extractive summarization are formulated as a sequence labeling problem by making individual sentence label predictions. |
| Approach: | They propose a novel paradigm for extractive summarization by directly generating summary sentences with diffusion models and extracting sentences based on sentence representation matching. |
| Outcome: | The proposed framework achieves state-of-the-art extractive results on CNN/DailyMail with ROUGE scores of 44.83/22.56/40.56. |
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. |
Improving the Faithfulness of Abstractive Summarization via Entity Coverage Control (2022.findings-naacl)
Copied to clipboard
| Challenge: | Abstractive summarization systems have been shown to be more prone to unfaithful facts . 30% of summaries generated by pre-trained language models suffer from hallucination . |
| Approach: | They propose a method to remedy entity-level extrinsic hallucinations with Entity Coverage Control . they first compute entity coverage precision and prepend the corresponding control code . a further fine-tuning is performed to unlock zero-shot summarization . |
| Outcome: | The proposed method leads to more faithful and salient abstractive summarization in fine-tuning and zero-shot settings. |