Yuhong Dai, Jianxun Lian, Yitian Huang, Wei Zhang, Mingyang Zhou, Mingqi Wu, Xing Xie, Hao Liao. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Role-playing capabilities in large language models (LLMs) often lack cognitive consistency in complex scenarios that require deep understanding and coherent reasoning.While recent reasoning models excel in math and coding tasks, they show limited effectiveness in open-ended role-playing scenarios.We introduce R-CHAR (Role-Consistent Hierarchical Adaptive Reasoning), a metacognition-driven framework that enhances role-playing performance through guided thinking trajectories synthesis and adaptive evaluation.Our approach demonstrates that concise thinking processes can achieve superior performance efficiently compared to elaborate reasoning chains in roleplaying social intelligence tasks, outperforming existing specialized models.Experimental results on the SocialBench benchmark show significant and stable performance improvements across varying scenario complexities, showing particular strength in long-context comprehension (from 34.64% to 68.59%) and grouplevel social interactions.Our work advances the development of cognitively consistent roleplaying systems, bridging the gap between surface-level mimicry and authentic character simulation.

Explainable recommender systems ( ERS ) aim to enhance users’ trust in the systems by offering personalized recommendations with transparent explanations. This transparency provides users with a clear understanding of the rationale behind the recommendations, fostering a sense of confidence and reliability in the system’s outputs. Generally, the explanations are presented in a familiar and intuitive way, which is in the form of natural language, thus enhancing their accessibility to users. Recently, there has been an increasing focus on leveraging reviews as a valuable source of rich information in both modeling user-item preferences and generating textual interpretations, which can be performed simultaneously in a multi-task framework. Despite the progress made in these review-based recommendation systems, the integration of implicit feedback derived from user-item interactions and user-written text reviews has yet to be fully explored. To fill this gap, we propose a model named SERMON (A s pect-enhanced E xplainable R ecommendation with M ulti-modal C o ntrast Lear n ing). Our model explores the application of multimodal contrastive learning to facilitate reciprocal learning across two modalities, thereby enhancing the modeling of user preferences. Moreover, our model incorporates the aspect information extracted from the review, which provides two significant enhancements to our tasks. Firstly, the quality of the generated explanations is improved by incorporating the aspect characteristics into the explanations generated by a pre-trained model with controlled textual generation ability. Secondly, the commonly used user-item interactions are transformed into user-item-aspect interactions, which we refer to as interaction triple, resulting in a more nuanced representation of user preference. To validate the effectiveness of our model, we conduct extensive experiments on three real-world datasets. The experimental results show that our model outperforms state-of-the-art baselines, with a 2.0% improvement in prediction accuracy and a substantial 24.5% enhancement in explanation quality for the TripAdvisor dataset.

Wensheng Lu, Jianxun Lian, Wei Zhang, Guanghua Li, Mingyang Zhou, Hao Liao, Xing Xie. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Hao Cheng, Shuo Wang, Wensheng Lu, Wei Zhang, Mingyang Zhou, Kezhong Lu, Hao Liao. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

In this paper, we propose a novel approach to enhance user and restaurant representations in the context of predicting the closure of a restaurant and give an explanation based on data generated from user-restaurant interactions. In order to accurately predict the operating status of a restaurant and give a reasonable explanation, we need rich relevant information of user-restaurant interaction and reviews to model their representations. However, the interaction information between the user and the restaurant is usually sparse. To address this issue, we propose a new model, which is called the Co-Attentive Contrastive Learning (CACL) model. Our model employs a contrastive learning algorithm to deal with data sparsity and leverages co-attention mechanism to select the most relevant review information assisting the former to obtain a more accurate and granular representation. By fusing these module, we obtain rich information to perform two tasks with better quality. To demonstrate the effectiveness of our model, extensive experiments was conducted in six different cities, and the results showed that CACL was superior to the previous method in terms of prediction accuracy and explainable ability (average 4.8% improvement in prediction and 35.4% improvement in explanation).

The ease of spreading false information online enables individuals with malicious intent to manipulate public opinion and destabilize social stability. Recently, fake news detection based on evidence retrieval has gained popularity in an effort to identify fake news reliably and reduce its impact. Evidence retrieval-based methods can improve the reliability of fake news detection by computing the textual consistency between the evidence and the claim in the news. In this paper, we propose a framework for fake news detection based on MUlti- Step Evidence Retrieval enhancement (MUSER), which simulates the steps of human beings in the process of reading news, summarizing, consulting materials, and inferring whether the news is true or fake. Our model can explicitly model dependencies among multiple pieces of evidence, and perform multi-step associations for the evidence required for news verification through multi-step retrieval. In addition, our model is able to automatically collect existing evidence through paragraph retrieval and key evidence selection, which can save the tedious process of manual evidence collection. We conducted extensive experiments on real-world datasets in different languages, and the results demonstrate that our proposed model outperforms state-of-the-art baseline methods for detecting fake news by at least 3% in F1-Macro and 4% in F1-Micro. Furthermore, it provides interpretable evidence for end users.

In this paper, we present an algorithmic study on how to surpass competitors in popularity by strategic promotions in social networks. We first propose a novel model, in which we integrate the Preferential Attachment (PA) model for popularity growth with the Independent Cascade (IC) model for influence propagation in social networks called PA-IC model. In PA-IC, a popular item and a novice item grab shares of popularity from the natural popularity growth via the PA model, while the novice item tries to gain extra popularity via influence cascade in a social network. The popularity ratio is defined as the ratio of the popularity measure between the novice item and the popular item. We formulate Popularity Ratio Maximization (PRM) as the problem of selecting seeds in multiple rounds to maximize the popularity ratio in the end. We analyze the popularity ratio and show that it is monotone but not submodular. To provide an effective solution, we devise a surrogate objective function and show that empirically it is very close to the original objective function while theoretically, it is monotone and submodular. We design two efficient algorithms, one for the overlapping influence and non-overlapping seeds (across rounds) setting and the other for the non-overlapping influence and overlapping seed setting, and further discuss how to deal with other models and problem variants. Our empirical evaluation further demonstrates that our proposed method consistently achieves the best popularity promotion compared to other methods. Our theoretical and empirical analyses shed light on the interplay between influence maximization and preferential attachment in social networks.