Recent advancements in Large Language Models have increasingly demonstrated their potential for event reasoning. However, LLMs still struggle with this task due to inadequate modeling of event structures. Although introducing schema knowledge has been shown to improve event reasoning performance, existing methods rely on predefined schema library, compromising their scalability and lightweight deployment. To address these challenges, we propose SGER, a plug-and-play Schema-Guided Event Reasoning framework. In the schema extraction stage, the model maps event descriptions with diverse surface forms to potential semantic structure representations, achieving an abstract transformation from instances to schemas. The schema prediction stage captures the potential associations between historical event schemas to make forward-looking inferences about possible future event schemas. In the event reasoning stage, we integrate historical events and predicted schemas into prompts to guide LLMs in generating specific, contextually consistent predicted events. Experimental evaluations demonstrate that our framework significantly improves event reasoning performance of LLMs.

Wenqing Hou, Hongkui Tu, Ye Wang, Yue Zhang, Yuying Liu, Dong Zhu, Liqun Gao, Bin Zhou. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

When fact-checking methods based on large language models (LLMs) use external evidence to validate claims, knowledge conflicts often arise. These conflicts typically stem from inconsistencies between the external evidence and LLMs' internal pre-existing knowledge. Such an inconsistency could lead LLMs to draw incorrect answers when validating claims, especially when they are overly confident in their internal incorrect knowledge. Previous works on LLM-based fact-checking have overlooked this issue. This paper, for the first time, proposes a framework (namely KnowFC) to navigate this issue. Our key insight is dividing and adaptively utilizing the knowledge that LLMs know and do not know, thereby avoiding conflicts while enhancing the correctness and efficiency of fact-checking. Specifically, in KnowFC, we propose an adaptive retrieval method, where we train an LLM using a reinforcement learning algorithm coupled with the Dunning-Kruger effect-inspired reward mechanism to identify its knowledge boundaries through confidence calibration, thereby realizing adaptive evidence retrieval. Besides, we propose a reliable and debiased fact verification method, where we organize and construct reasoning graphs using retrieved evidence to verify claims, followed by a causal intervention method using causal mediation analysis to mitigate internal knowledge interference. Experimental results on both FEVEROUS and AVeriTeC datasets show that our method outperforms baseline methods in terms of accuracy and F1 score, while also improving fact-checking efficiency.

Open-world intent discovery is critical for task-oriented dialogue systems, where static intent taxonomies fail to capture emerging user intentions and existing methods show limited generalization beyond predefined label spaces. To address this issue, we propose Unified Generative Intent Discovery (UGID), a unified framework that reformulates intent understanding as a conditional text generation task, enabling both in-domain (IND) intent classification and out-of-domain (OOD) intent discovery within a single architecture. UGID adopts a two-stage training strategy. First, instruction-tuned supervised fine-tuning strengthens semantic discrimination among known intents. Second, a self-play reinforcement learning mechanism simulates iterative user–system interactions to explore, refine, and validate novel intent labels. In addition, a reward design combining semantic fidelity and domain relevance guides the generation process toward coherent and meaningful intent discovery. Experiments on three benchmark datasets demonstrate that UGID consistently achieves strong performance, reaching ACC scores of 79.63%, 82.70% and 87.50% on BANKING, StackOverflow and CLINC, respectively. Compared with the strongest generative baseline, IntentGPT-4, UGID further improves ACC by 14.87 and 4.21 percentage points on BANKING and CLINC, respectively. Ablation studies further verify the effectiveness of the proposed design. Overall, UGID provides an effective and scalable framework for intent understanding in dynamic open-world dialogue scenarios.

Large language models (LLMs) demonstrate significant generative capabilities but often face ethical alignment and robustness challenges. Conventional alignment methods rely on extensive human-annotated data and require retraining, leading to high computational costs and resource demands. Therefore, we propose a novel approach, Decoding Probability Correction (DPC), that aligns frozen LLMs without additional training or annotated data. DPC dynamically adjusts the probability distribution during inference, ensuring the generated content aligns with human values in real-time. Additionally, DPC incorporates a discriminator-based backtracking mechanism, further enhancing content safety by re-evaluating and refining generation choices. Experimental results on datasets such as the HH and AdvBench show that DPC significantly reduces harmful outputs while maintaining high levels of informativeness and helpfulness. The proposed method offers a cost-effective and efficient solution for enhancing the ethical alignment of LLMs in real-world applications.

Abstract Social networks have an important role in the distribution of ideas. With the rapid development of the social networks, identifying the influential nodes provides a chance to turn the new potential of global information spread into reality. The measurement of the spreading capabilities of nodes is an attractive challenge in social networks analysis. In this paper, a novel method is proposed to identify the influential nodes in complex networks. The proposed method determines the spreading capability of a node based on its local and global positions. The degree centrality is improved by the Shannon entropy to measure the local influence of nodes. The k-shell method is improved by the clustering coefficient to measure the global influence of nodes. To rank the importance of nodes, the entropy weighting method is used to calculate the weight for the local and global influences. The Vlsekriterijumska Optimizacija I Kompromisno Resenje method is used to integrate the local and global influences of a node and obtain its importance. The experiments are conducted on 13 real-world networks to evaluate the performance of the proposed method. The experimental results show that the proposed method is more powerful and accurate to identify influential nodes than other methods.

The purpose of the influence maximization problem is to determine a subset to maximize the number of affected users. This problem is very crucial for information dissemination in social networks. Most traditional influence maximization methods usually focus too heavily on the information diffusion model and randomly set influence parameters, resulting in inaccurate final outcomes. Driven by the recent criticisms of the diffusion model and the rapid development of representation learning, this paper proposes a representation learning method based on improved random walk for influence maximization (IRWIM) to maximize the influence spread. The IRWIM algorithm improves the traditional random walk and adopts multi-task neural network architecture to predict the propagation ability of nodes more accurately. Moreover, the greedy strategy is utilized to continuously optimize the marginal gain while retaining the theoretical guarantee. IRWIM is tested on four genuine datasets. Experimental results show that the accuracy of the proposed algorithm is superior to various competitive algorithms in the field of influence maximization.