Baixuan Li, Jialong Wu, Wenbiao Yin, Kuan Li, Zhongwang Zhang, Huifeng Yin, Zhengwei Tao, Liwen Zhang, Pengjun Xie, Jingren Zhou, Yong Jiang, Wentao Zhang, Zhiqiang Gao. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Event reasoning is to reason with events and certain inter-event relations. These cutting-edge techniques possess crucial and fundamental capabilities that underlie various applications. Large language models (LLMs) have made advances in event reasoning owing to their wealth of training. However, the LLMs commonly used today still do not consistently demonstrate proficiency in managing event reasoning as humans. This discrepancy arises from not explicitly modeling events and their relations and insufficient knowledge of event relations. In addition, the different reasoning paradigms of the LLMs are trained in an imbalanced way. In this paper, we propose WIZARDEVENT, to synthesize data from the unlabeled corpus with the proposed hybrid event-aware instruction tuning. Specifically, we first represent the events and their relation in a novel structure and then extract the knowledge from the raw text. Second, we introduce hybrid event reasoning paradigms with four reasoning formats. Lastly, we wrap our constructed WIZARDEVENT with the paradigms to create the instruction tuning dataset. We fine-tune the model with this enriched dataset, significantly improving the event reasoning. The performance of WIZARDEVENT is rigorously evaluated through extensive experiments. The results demonstrate that WIZARDEVENT substantially outperforms baselines, indicating the effectiveness of our approach.

Event reasoning is a fundamental ability that underlies many applications. It requires event schema knowledge to perform global reasoning and needs to deal with the diversity of the inter-event relations and the reasoning paradigms. The extent to which LLMs excel in event reasoning across various relations and reasoning paradigms has not been thoroughly investigated. Additionally, it is still unclear whether LLMs utilize event knowledge in the same way humans do. To mitigate this disparity, we comprehensively evaluate the abilities of event reasoning of LLMs on different relations, paradigms, and levels of abstraction. We introduce a novel benchmark EV2 for EValuation of EVent reasoning. EV2 consists of two levels of evaluation on schema and instance and is comprehensive in relations and reasoning paradigms. We conduct extensive experiments on EV2. We find that 1) LLMs have abilities to accomplish event reasoning but their performances are far from satisfactory. 2) There are imbalances of event reasoning abilities on different relations and paradigms. 3) LLMs have event schema knowledge, however, they're not aligned with humans on how to utilize the knowledge. Based on these findings, we guide the LLMs in utilizing the event schema knowledge as memory leading to improvements in event reasoning.

Large language models (LLMs) have demonstrated significant advancements in code generation, yet they still face challenges when tackling tasks that extend beyond their basic capabilities. Recently, the concept of self-debugging has been proposed as a way to enhance code generation performance by leveraging execution feedback from tests. However, the availability of high-quality tests in real-world scenarios is often limited. In this context, self-debugging with self-generated tests emerges as a promising solution, though its limitations and practical potential have not been fully explored. To address this gap, we investigate the efficacy of self-debugging in code generation tasks. We propose and analyze two distinct paradigms for the self-debugging process: post-execution and in-execution self-debugging. Our findings reveal that post-execution self-debugging struggles with the test bias introduced by self-generated tests, which can lead to misleading feedback. In contrast, in-execution self-debugging enables LLMs to mitigate this bias and leverage intermediate states during program execution. By focusing on runtime information rather than relying solely on potentially flawed self-generated tests, this approach demonstrates significant promise for improving the robustness and accuracy of LLMs in code generation tasks.

Jia Li, Xuyuan Guo, Lei Li, Kechi Zhang, Ge Li, Jia Li, Zhengwei Tao, Fang Liu, Chongyang Tao, Yuqi Zhu, Zhi Jin. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Addressing intricate real-world problems necessitates in-depth information seeking and multi-step reasoning. Recent progress in agentic systems, exemplified by Deep Research, underscores the potential for autonomous multi-step research. In this work, we present a cohesive paradigm for building end-to-end agentic information seeking agents from a data-centric and training-stage perspective. Our approach consists of four key stages: (1) browsing data construction, (2) trajectories sampling, (3) supervised fine-tuning for effective cold start, and (4) reinforcement learning for enhanced generalisation. We instantiate this framework in a web agent based on the ReAct format, WebDancer. Empirical evaluations on the challenging GAIA and WebWalkerQA benchmarks demonstrate the strong performance of WebDancer, achieving considerable results and highlighting the efficacy of our training paradigm. Further analysis of agent training provides valuable insights and actionable, systematic pathways for developing more capable agentic models.

As the application of knowledge graphs becomes increasingly widespread, the issue of knowledge graph incompleteness has garnered significant attention. As a classical type of non-euclidean spatial data, knowledge graphs possess various complex structural types. However, most current knowledge graph completion models are developed within a single space, which makes it challenging to capture the inherent knowledge information embedded in the entire knowledge graph. This limitation hinders the representation learning capability of the models. To address this issue, this paper focuses on how to better extend the representation learning from a single space to Riemannian manifolds, which are capable of representing more complex structures. We propose a new knowledge graph completion model called MRME-KGC, based on multi-view Riemannian Manifolds fusion to achieve this. Specifically, MRME-KGC simultaneously considers the fusion of four views: two hyperbolic Riemannian spaces with negative curvature, a Euclidean Riemannian space with zero curvature, and a spherical Riemannian space with positive curvature to enhance knowledge graph modeling. Additionally, this paper proposes a contrastive learning method for Riemannian spaces to mitigate the noise and representation issues arising from Multi-view Riemannian Manifolds Fusion. This paper presents extensive experiments on MRME-KGC across multiple datasets. The results consistently demonstrate that MRME-KGC significantly outperforms current state-of-the-art models, achieving highly competitive performance even with low-dimensional embeddings.

Zhengwei Tao, Zhi Jin, Haiyan Zhao, Chengfeng Dou, Yongqiang Zhao, Tao Shen, Chongyang Tao. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Aspect-based sentiment analysis (ABSA) plays an indispensable role in web mining and retrieval system as it involves a wide range of tasks, including aspect term extraction, opinion term extraction, aspect sentiment classification, etc. Early works are merely applicable to a part of these tasks, leading to computation-unfriendly models and a pipeline framework. Recently, a unified framework has been proposed to learn all these ABSA tasks in an end-to-end fashion. Despite its versatility, its performance is still sub-optimal since ABSA tasks depend heavily on both sentiment and syntax knowledge, but existing task-specific knowledge integration methods are hardly applicable to such a unified framework. Therefore, we propose a brand-new unified framework for ABSA in this work, which incorporates both implicit sentiment knowledge and explicit syntax knowledge to better complete all ABSA tasks. To effectively incorporate implicit sentiment knowledge, we first design a self-supervised pre-training procedure that is general enough to all ABSA tasks. It consists of conjunctive words prediction (CWP) task, sentiment-word polarity prediction (SPP) task, attribute nouns prediction (ANP) task, and sentiment-oriented masked language modeling (SMLM) task. Empowered by the pre-training procedure, our framework acquires strong abilities in sentiment representation and sentiment understanding. Meantime, considering a subtle syntax variation can significantly affect ABSA, we further explore a sparse relational graph attention network (SR-GAT) to introduce explicit aspect-oriented syntax knowledge. By combining both worlds of knowledge, our unified model can better represent and understand the input texts towards all ABSA tasks. Extensive experiments show that our proposed framework achieves consistent and significant improvements on all ABSA tasks.