Large language models (LLMs) have gained widespread adoption in various natural language processing tasks, including question answering and dialogue systems. However, a major drawback of LLMs is the issue of hallucination, where they generate unfaithful or inconsistent content that deviates from the input source, leading to severe consequences. In this paper, we propose a robust discriminator named RelD to effectively detect hallucination in LLMs' generated answers. RelD is trained on the constructed RelQA, a bilingual question-answering dialogue dataset along with answers generated by LLMs and a comprehensive set of metrics. Our experimental results demonstrate that the proposed RelD successfully detects hallucination in the answers generated by diverse LLMs. Moreover, it performs well in distinguishing hallucination in LLMs' generated answers from both in-distribution and out-of-distribution datasets. Additionally, we also conduct a thorough analysis of the types of hallucinations that occur and present valuable insights. This research significantly contributes to the detection of reliable answers generated by LLMs and holds noteworthy implications for mitigating hallucination in the future work.

Recent years, Pre-trained Language models (PLMs) have swept into various fields of artificial intelligence and achieved great success. However, most PLMs, such as T5 and GPT3, have a huge amount of parameters, fine-tuning them is often expensive and time consuming, and storing them takes up a lot of space. Therefore, it is necessary to adopt a parameter-efficient approach to reduce parameters of PLMs in fine-tuning without compromising their performance in downstream tasks. In this paper, we design a novel adapter which only acts on self-attention outputs in PLMs. This adapter adopts element-wise linear transformation using Hadamard product, hence named as Hadamard adapter, requires the fewest parameters compared to previous parameter-efficient adapters. In addition, we also summarize some tuning patterns for Hadamard adapter shared by various downstream tasks, expecting to provide some guidance for further parameter reduction with shared adapters in future studies. The experiments conducted on the widely-used GLUE benchmark with several SOTA PLMs prove that the Hadamard adapter achieves competitive performance with only 0.033% parameters compared with full fine-tuning, and it has the fewest parameters compared with other adapters. Moreover, we further find that there is also some redundant layers in the Hadamard adapter which can be removed to achieve more parameter efficiency with only 0.022% parameters.

Existing recommendation methods usually train several independent modules for each rating information instead of an end-to-end manner. Therefore, these methods may be incapable of collaborative learning leading to sub-optimal results in predicting users' overall interests. The main disadvantage of those two-stage methods is that the overall rating heavily relies on the predicted sub-ratings, and the predictive error of sub-ratings is accumulated during the regression step. Moreover, the regression model is trained with unbiased sub-ratings but used with biased predictive sub-ratings. Meanwhile, the separate training pattern induces more training overhead. To address these problems, we propose a collective model to predict a user's overall rating, which can learn each of the multi-criteria sub-scores simultaneously in an end-to-end manner. This enables the proposed method to improve its prediction quality by transferring the knowledge of criterion to the domain of overall ratings. It reduces the dependence of the predicted score of a specific criterion, making the overall system more robust. In addition, our end-to-end method avoids learning the regress part directly from the unbiased sub-ratings, improving the performance of the overall model. Experiments on three real-world datasets show that our proposed architecture achieves up to 13.14% lower prediction error over baseline approaches.

User-generated content is daily produced in social media, as such user interest summarization is critical to distill salient information from massive information for recommendation tasks. While the interested messages (e.g., tags or posts) from a single user are usually sparse becoming a bottleneck for existing methods, we propose a neural inference method (NIGraphNet) by mining user social interest for item recommendation. It can unearth user latent topics combined with user relation learning. Specifically, we exploit a neural variational inference approach to learn the distributions between user interests and hidden topics. (We denote it as interest-topic distributions in the following.) Then, we adopt a unified graph-based training loss that jointly learns the hidden topics and user relations for item recommendation. Experiments on two datasets collected from well-known social media platforms demonstrate the superior performance of our model in the tasks of user interest summarization and item recommendation. Further discussions also show that exploiting the latent topic representations and user relations is conducive to the user’s automatic language understanding.

The multiplayer online battle arena (MOBA) genre has gained significant popularity and economic success, attracting considerable research interest within the Human-Computer Interaction community. Enhancing the gaming experience requires a deep understanding of player behavior, and a crucial aspect of MOBA games is matchmaking, which aims to assemble teams of comparable skill levels. However, existing matchmaking systems often neglect important factors such as players' position preferences and team assignment, resulting in imbalanced matches and reduced player satisfaction. To address these limitations, this paper proposes a novel framework called CUPID, which introduces a novel process called ''re-matchmaking'' to optimize team and position assignments to improve both fairness and player satisfaction. CUPID incorporates a pre-filtering step to ensure a minimum level of matchmaking quality, followed by a pre-match win-rate prediction model that evaluates the fairness of potential assignments. By simultaneously considering players' position satisfaction and game fairness, CUPID aims to provide an enhanced matchmaking experience. Extensive experiments were conducted on two large-scale, real-world MOBA datasets to validate the effectiveness of CUPID. The results surpass all existing state-of-the-art baselines, with an average relative improvement of 7.18% in terms of win prediction accuracy. Furthermore, CUPID has been successfully deployed in a popular online MOBA game. The deployment resulted in significant improvements in match fairness and player satisfaction, as evidenced by critical Human-Computer Interaction (HCI) metrics covering usability, accessibility, and engagement, observed through A/B testing. To the best of our knowledge, Cupid is the first re-matchmaking system designed specifically for large-scale MOBA games.

Industrial recommender systems usually employ multi-source data to improve the recommendation quality, while effectively sharing information between different data sources remain a challenge. In this paper, we introduce a novel Multi-View Approach with Hybrid Attentive Networks (MV-HAN) for contents retrieval at the matching stage of recommender systems. The proposed model enables high-order feature interaction from various input features while effectively transferring knowledge between different types. By employing a well-placed parameters sharing strategy, the MV-HAN substantially improves the retrieval performance in sparse types. The designed MV-HAN inherits the efficiency advantages in the online service from the two-tower model, by mapping users and contents of different types into the same features space. This enables fast retrieval of similar contents with an approximate nearest neighbor algorithm. We conduct offline experiments on several industrial datasets, demonstrating that the proposed MV-HAN significantly outperforms baselines on the content retrieval tasks. Importantly, the MV-HAN is deployed in a real-world matching system. Online A/B test results show that the proposed method can significantly improve the quality of recommendations.