Jiayang Zhang
Author directory2026
MulEG: Multi-Level Explanation-Guided Feature Attribute Graph for Zero-Shot Tabular Classification
Jiayang Zhang | Yunxiao Zhao | Xin Kang | Zhichao Yan | Boxiang Ma | Qinghua Chai | Xingtong Yu | Ru Li
Findings of the Association for Computational Linguistics: EMNLP 2026
Jiayang Zhang | Yunxiao Zhao | Xin Kang | Zhichao Yan | Boxiang Ma | Qinghua Chai | Xingtong Yu | Ru Li
Findings of the Association for Computational Linguistics: EMNLP 2026
Zero-shot classification for structured tabular data has attracted increasing attention in recent years. An important line of research is leveraging textual explanations as supervision to improve the modeling of tabular attribute features. Previous studies usually serialize tabular data into flattened explanation sequences, or employ logical rules to model directional associations between tabular attributes and labels. However, these methods often suffer from two major limitations: the former disrupts the inherent row-column topological structure of tables, while the latter mainly represents relations with fixed logical operators or aggregation weights, making it difficult to model learnable dependencies among features. To address these issues, we propose a novel method (MulEG), which harnesses multi-level textual explanations with a feature attribute graph to model both tabular topology and cell-element relations. Specifically, to preserve the intrinsic row-column topological structure of tables, we propose a multi-level textual explanation modeling with sample-level, attribute-level, and label-level perspectives. Moreover, to capture fine-grained feature dependencies, we propose a differentiable message-passing mechanism using a feature attribute graph that allows heterogeneous features to propagate through message passing. Finally, extensive experimental results on datasets covering sixteen tasks demonstrate the effectiveness of the proposed approach.
CuRLRank: Adaptive Curriculum Reinforcement Learning for Reasoning-Intensive Reranking
Xin Kang | Yunxiao Zhao | Jiayang Zhang | Juncai Li | Zhichao Yan | XiaoQi Han | Ru Li | Delvin Ce Zhang
Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
Xin Kang | Yunxiao Zhao | Jiayang Zhang | Juncai Li | Zhichao Yan | XiaoQi Han | Ru Li | Delvin Ce Zhang
Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
Document ranking aims to order candidate documents based on their relevance to a given query. However, identifying relevant documents in complex real-world scenarios requires deep reasoning beyond surface-level matching, driving a shift from semantic matching to reasoning-intensive reranking. Since the latter requires integrating information across documents for complex reasoning, it presents two key challenges: (1) varying reasoning difficulty, where assessing document relevance to the query requires multi-step reasoning with different complexity; and (2) strong contextual sensitivity, where the relevance of a document is heavily influenced by other documents within the context window. To address these challenges, we propose CuRLRank, which consists of (1) CuRL, an adaptive curriculum reinforcement learning approach that enables LLMs to develop complex reasoning capabilities across varying levels of difficulty, and (2) IFRS, an iterative filtering ranking strategy to achieve efficient and robust ranking. Extensive experiments on BRIGHT and R2MED benchmarks demonstrate that our CuRLRank significantly outperforms baseline methods while achieving lower ranking latency.
2025
LOG: A Local-to-Global Optimization Approach for Retrieval-based Explainable Multi-Hop Question Answering
Hao Xu | Yunxiao Zhao | Jiayang Zhang | Zhiqiang Wang | Ru Li
Proceedings of the 31st International Conference on Computational Linguistics
Hao Xu | Yunxiao Zhao | Jiayang Zhang | Zhiqiang Wang | Ru Li
Proceedings of the 31st International Conference on Computational Linguistics
Multi-hop question answering (MHQA) aims to utilize multi-source intensive documents retrieved to derive the answer. However, it is very challenging to model the importance of knowledge retrieved. Previous approaches primarily emphasize single-step and multi-step iterative decomposition or retrieval, which are susceptible to failure in long-chain reasoning due to the progressive accumulation of erroneous information. To address this problem, we propose a novel Local-tO-Global optimized retrieval method (LOG) to discover more beneficial information, facilitating the MHQA. In particular, we design a pointwise conditional v-information based local information modeling to cover usable documents with reasoning knowledge. We also improve tuplet objective loss, advancing multi-examples-aware global optimization to model the relationship between scattered documents. Extensive experimental results demonstrate our proposed method outperforms prior state-of-the-art models, and it can significantly improve multi-hop reasoning, notably for long-chain reasoning.