Papers by Xiangrong Zhu
RETAIL: Towards Real-world Travel Planning for Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing travel planning systems assume users provide explicit queries, limiting their practical utility. |
| Approach: | They propose a dataset RETAIL which supports decision-making for implicit queries while covering explicit queries. |
| Outcome: | The proposed model achieves a 1.0% pass rate, suggesting real-world travel planning remains challenging. |
RepoDebug: Repository-Level Multi-Task and Multi-Language Debugging Evaluation of Large Language Models (2025.findings-emnlp)
Copied to clipboard
Jingjing Liu, Zeming Liu, Zihao Cheng, Mengliang He, Xiaoming Shi, Yuhang Guo, Xiangrong Zhu, Yuanfang Guo, Yunhong Wang, Haifeng Wang
| Challenge: | Large Language Models (LLMs) have exhibited significant proficiency in code debugging, especially in automatic program repair. |
| Approach: | They propose a repository-level code debugging dataset with 22 subtypes of errors that supports 8 commonly used programming languages and 3 debug tasks. |
| Outcome: | The proposed dataset supports 8 commonly used programming languages and 3 debugging tasks. |
Knowledge Graph-Guided Retrieval Augmented Generation (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing studies on RAG focus on semantic retrieval of isolated relevant chunks, which ignore their intrinsic relationships. |
| Approach: | They propose a framework that utilizes knowledge graphs to provide fact-level relationships between chunks, improving the diversity and coherence of the retrieved results. |
| Outcome: | Extensive experiments on the HotpotQA dataset and its variants demonstrate the advantages of KG2RAG compared to existing RAG-based approaches in terms of response quality and retrieval quality. |
Multi-Aspect Controllable Text Generation with Disentangled Counterfactual Augmentation (2024.acl-long)
Copied to clipboard
| Challenge: | Existing studies neglect attribute correlations formed by the intertwining of different attributes. |
| Approach: | They propose a multi-aspect controllable text generation method with disentangled counterfactual augmentation that alleviates imbalanced attribute correlations during training by disentanglement. |
| Outcome: | The proposed method outperforms state-of-the-art methods in imbalanced and balanced attribute correlation scenarios. |
Reasoning is All You Need for Video Generalization: A Counterfactual Benchmark with Sub-question Evaluation (2025.findings-acl)
Copied to clipboard
Qiji Zhou, YiFan Gong, Guangsheng Bao, Hongjie Qiu, Jinqiang Li, Xiangrong Zhu, Huajian Zhang, Yue Zhang
| Challenge: | Existing multimodal benchmarks often overlook counterfactual reasoning, which is crucial for robust video understanding. |
| Approach: | They propose a multidimensional multimodal benchmark that systematically evaluates MLLMs across the abstract-concrete and perception-cognition dimensions. |
| Outcome: | The proposed model decomposes complex queries into structured sub-questions, enabling fine-grained reasoning analysis. |
Mem2Evolve: Towards Self-Evolving Agents via Co-Evolutionary Capability Expansion and Experience Distillation (2026.acl-long)
Copied to clipboard
Zihao Cheng, Zeming Liu, Yingyu Shan, Xinyi Wang, Xiangrong Zhu, Yunpu Ma, Hongru Wang, Yuhang Guo, Wei Lin, Yunhong Wang
| Challenge: | Existing frameworks that focus on static tools and static assets are ineffective for self-evolving agents. |
| Approach: | They propose a paradigm of co-evolutionary Capability Expansion and Experience Distillation that leverages accumulated experience to guide dynamic creation of assets. |
| Outcome: | The proposed framework improves performance in single-task and cross-task settings by 18.53% over standard LLMs, 11.80% over agents evolving solely through experience, and 6.46% over those evolving solelly through asset creation. |
Avoiding Knowledge Edit Skipping in Multi-hop Question Answering with Guided Decomposition (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for knowledge editing fail to work in multi-hop question answering due to 'edit skipping' edit skipping occurs due to the mismatch between the granularity of LLMs in problem-solving and the facts in the edited memory. |
| Approach: | They propose a retrieval-augmented generation-based method that edits knowledge without modifying parameters without retraining LLMs. |
| Outcome: | The proposed method outperforms state-of-the-art methods for KE in multi-hop question answering. |