The rapid spread of misinformation on social media has underscored the importance of automatic fact-checking. Existing fact-checking pipelines typically rely on multi-stage frameworks involving evidence retrieval and claim verification. However, these methods face two major challenges: (1) the retrieval process often introduces noisy evidence, which compromises the reliability of the final veracity prediction; and (2) the verification models may overlook critical factual details, resulting in hallucinated conclusions. To address these issues, we propose a fact-checking framework SLED with Self-supervised denoising evidence retrieval and LLM-Enhanced Debate-based verification. In the retrieval stage, SLED leverage trained verifier to assess credibility and necessity of retrieved evidence, enabling the elimination of noisy evidence. In the verification stage, SLED prompts the LLM to generate dual-perspective reasoning and simulates a multi-agent debate, followed by distillation into a lightweight model for final veracity prediction. Experiments on CHEF and HOVER datasets demonstrate that SLED achieves the state-of-the-art results in complex fact verification scenarios.

Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by leveraging external knowledge, where retrieval accuracy directly affects generation quality. However, dense retrievers, commonly employed in RAG, suffer degraded performance in evolving corpora where new documents arrive continuously and distribution shifts accumulate over time. In such settings, continually updating retrievers is crucial, yet conventional retraining is computationally expensive and often impractical. To address this challenge, we propose FlowRAG, a lightweight and effective method for continual retriever adaptation in evolving corpora. FlowRAG augments the encoder with Layer-wise Prompt Embeddings and introduces a Cross-Layer Fusion mechanism to capture hierarchical semantic representations. In addition, a novel Generator-Guided Loss aligns retriever scores and intermediate representations with the LLM's generation likelihoods, encouraging retrieval decisions that are both semantically relevant and beneficial for generation. Experiments on datasets spanning four domains demonstrate that FlowRAG, which updates only about 0.64% of the total model parameters, consistently outperforms strong baselines in retrieval accuracy, generation quality, and robustness to forgetting in non-stationary settings.

Knowledge graphs (KGs) can provide structured knowledge to assist large language models (LLMs) in interpretable reasoning. Knowledge graph question answering (KGQA) is a typical benchmark to evaluate KG-enhanced LLM methods. Previous methods of KG-enhanced LLMs for KGQA mainly include: 1) origin question-oriented methods, which perform KG retrieval based solely on the original question without explicitly analyzing multi-step reasoning logic; and 2) stepwise reasoning-oriented methods, which alternate between LLM generating the next reasoning step and targeted KG retrieval but lack systematic planning, leading to poor controllability. To tackle these limitations, we propose KELGoP, a framework of KG-enhanced LLM based on global planning. We propose fine-grained question categorization based on reasoning patterns and corresponding category-driven question decomposition for complex questions, enabling more controllable reasoning and atomic KG retrieval targeted to sub-questions. Furthermore, we propose an adaptive strategy that allows adjusting the reasoning pattern based on the performance of question answering, making the reasoning more flexible and robust. Finally, we introduce several efficient atomic KG retrieval strategies that operate on KG subgraphs to assist the LLM in answering atomic-level questions. A series of experiments on KGQA datasets demonstrate that our proposed framework achieves superior performance compared to existing baselines.

The development of LLM has facilitated the emergence of generative information retrieval (IR) systems, such as ''Bing Chat''. Generative IR systems return generated text with citations rather than a list of ranked search results. User studies on IR systems are essential for understanding users' interaction patterns, evaluating and optimizing systems, and improving search experience, particularly in the context of generative IR systems with novel conversational interfaces and responses. However, systematic investigations into user behavior and search experience on generative IR systems are notably lacking. To address this gap, we conducted a user study using Bing Chat to explore user behavior and feedback on generative IR systems. The participants were required to accomplish three types of tasks using Bing Chat. During the search process, we collected their various behavior (e.g., click, query reformulation) and explicit feedback (e.g., satisfaction, credibility, and success). Additionally, the same study was conducted on traditional IR systems Bing for comparison. Analyses of these data show that Bing Chat can reduce the user's search effort and lead to a better search experience without any decrease in credibility compared with Bing. We believe that this work provides valuable insight into the design and evaluation of generative information retrieval systems.

Incorporating explicit personas into dialogue models is critical for generating responses that fulfill specific user needs and preferences, creating a more personalized and engaging interaction. Early works on persona-based dialogue generation directly concatenate the persona descriptions and dialogue history into relatively small pre-trained language models (PLMs) for response generation, which leads to uninformative and inferior results due to the sparse persona information and the limited model generation capabilities. Recently, large language models (LLMs) have shown their surprising capabilities in language generation. Prompting the LLMs with the persona descriptions for role-playing dialogue generation has also achieved promising results. However, deploying LLMs is challenging for practical applications due to their large scale, spurring efforts to distill the generation capabilities into more concise and compact models through teacher-student learning. In this article, we propose an efficient compact K nowledge-grounded P ersona-based D ialogue model enhanced by LLM D istillation (KPDD). Specifically, first, we propose to enrich the annotated persona descriptions by integrating external knowledge graphs (KGs) with a mixed encoding network, coupled with a mixture of experts (MoE) module for both informative and diverse response generation. The mixed encoding network contains multiple layers of modality interaction operations, enabling information from both modalities propagates to the other. Second, to fully exploit the generation capabilities of LLMs, we turn to the distillation technique to improve the generation capabilities of our model, facilitated by a natural language inference (NLI)-based filtering mechanism to extract high-quality information from LLMs. In addition, we employ a curriculum learning strategy to train our model on the high-quality filtered distilled data and progressively on the relatively noisy original data, enhancing its adaptability and performance. Extensive experiments show that KPDD outperforms state-of-the-art baselines in terms of both automatic and human evaluation.

The Dialogue-level Aspect-based Sentiment Quadruple analysis (DiaASQ) task has recently received attention in the Aspect-Based Sentiment Analysis (ABSA) field. It aims to extract(target, aspect, opinion, sentiment) quadruples from multi-turn and multi-party dialogues. Compared to previous ABSA tasks focusing on text such as sentences, the DiaASQ task involves more complex contextual information and corresponding relations between terms, as well as longer sequences. These characteristics challenge existing methods that struggle to model explicit span-level interactions or have high computational costs. In this paper, we propose a span-pair interaction and tagging method to solve these issues, which includes a novel Span-pair Tagging Scheme (STS) and a simple and efficient Multi-level Representation Model (MRM). STS simplifies the DiaASQ task to a span-pair tagging task and explicitly captures complete span-level semantics by tagging span pairs. MRM efficiently models the dialogue structure information and span-level interactions by constructing multi-level contextual representation. Besides, we train a span ranker to improve the running efficiency of MRM. Extensive experiments on multilingual datasets demonstrate that our method outperforms existing state-of-the-art methods.

Reading is a vital and complex cognitive activity during users’ information-seeking process. Several studies have focused on understanding users’ reading behavior in desktop search. Their findings greatly contribute to the design of information retrieval models. However, little is known about how users read a result in mobile search, although search currently happens more frequently in mobile scenarios. In this paper, we conduct a lab-based user study to investigate users’ fine-grained reading behavior patterns in mobile search. We find that users’ reading attention allocation is strongly affected by several behavior biases, such as position and selection biases. Inspired by these findings, we propose a probabilistic generative model, the Passage-level Reading behavior Model (PRM), to model users’ reading behavior in mobile search. The PRM utilizes observable passage-level exposure and viewport duration events to infer users’ unobserved skimming event, reading event, and satisfaction perception during the reading process. Besides fitting the passage-level reading behavior, we utilize the fitted parameters of PRM to estimate the passage-level and document-level relevance. Experimental results show that PRM outperforms existing unsupervised relevance estimation models. PRM has strong interpretability and provides valuable insights into the understanding of how users seek and perceive useful information in mobile search.

The major challenge in the task of entity alignment (EA) lies in the heterogeneity of the knowledge graph. The traditional solution to EA is to first map entities to the same space via knowledge embedding and then calculate the similarity between entities from different knowledge graphs. However, these methods mainly rely on manually labeled seeds of EA, which limits their applicability. Some researchers have begun using pseudo-labels rather than seeds for unsupervised EA. However, directly using pseudo-labels causes new problems, such as noise in the pseudo-labels. In this article, we propose a model called the Semantically Driven Hybrid Network (SDHN) to reduce the impact of noise in the pseudo-labels on the performance of EA models. The SDHN consists of two modules: a Teacher–Student Network (TSN) and a Rotation and Penalty (RAP) module. The TSN module reduces the impact of noise in two ways: (1) The TSN’s teacher network guides its student network to construct pseudo-labels based on semantic information instead of directly creating pseudo-labels. (2) It adaptively fuses semantic information into student networks to improve the final representation of entity embedding. Finally, the TSN enhances the performance of models of entity alignment via the RAP module. The results of experiments on multiple benchmark datasets showed that the SDHN outperforms state-of-the-art models.

Entity alignment (EA), which aims to discover equivalent entities in knowledge graphs (KGs), bridges heterogeneous sources of information and facilitates the integration of knowledge. Recently, based on translational models, EA has achieved impressive performance in utilizing graph structures or by adopting auxiliary information. However, existing entity alignment methods mainly rely on manually labeled entity alignment seeds, limiting their applicability in real scenarios. In this paper, a simple but effective Uncertainty-aware Pseudo Label Refinery (UPLR) framework is proposed without manually labeling requirement and is capable of learning high-quality entity embeddings from pseudo-labeled data sets containing noisy data. Our proposed model relies on two key factors: First, a non-sampling calibration strategy is provided that does not require artificially designed thresholds to reduce the influence of noise labels. Second, the entity alignment model achieves goal-oriented uncertainty correction through a gradual enhancement strategy. Experimental results on benchmark datasets demonstrate that our proposed model outperforms the existing supervised methods in cross-lingual knowledge graph tasks. Our source code is available at: https://github.com/Jia-Li2/UPLR/.

Named Entity Recognition (NER) is a fundamental problem in Natural Language Processing and has received much research attention. Although the current neural-based NER approaches have achieved the state-of-the-art performance, they still suffer from one or more of the following three problems in their architectures: (1) boundary tag sparsity, (2) lacking of global decoding information; and (3) boundary error propagation. In this paper, we propose a novel Boundary-aware Bidirectional Neural Networks (Ba-BNN) model to tackle these problems for neural-based NER. The proposed Ba-BNN model is constructed based on the structure of pointer networks for tackling the first problem on boundary tag sparsity. Moreover, we also use a boundary-aware binary classifier to capture the global decoding information as input to the decoders. In the Ba-BNN model, we propose to use two decoders to process the information in two different directions (i.e., from left-to-right and right-to-left). The final hidden states of the left-to-right decoder are obtained by incorporating the hidden states of the right-to-left decoder in the decoding process. In addition, a boundary retraining strategy is also proposed to help reduce boundary error propagation caused by the pointer networks in boundary detection and entity classification. We have conducted extensive experiments based on three NER benchmark datasets. The performance results have shown that the proposed Ba-BNN model has outperformed the current state-of-the-art models.

Fundamental information extraction tasks, such as relation extraction and event detection , suffer from a data imbalance problem. To alleviate this problem, existing methods rely mostly on well-designed loss functions to reduce the negative influence of imbalanced data . However, this approach requires additional hyper-parameters and limits scalability. Furthermore, these methods can only benefit specific tasks and do not provide a unified framework across relation extraction and event detection. In this paper, a Classifier-Adaptation Knowledge Distillation (CAKD) framework is proposed to address these issues, thus improving relation extraction and event detection performance. The first step is to exploit sentence-level identification information across relation extraction and event detection, which can reduce identification errors caused by the data imbalance problem without relying on additional hyper-parameters. Moreover, this sentence-level identification information is used by a teacher network to guide the baseline model’s training by sharing its classifier. Like an instructor, the classifier improves the baseline model’s ability to extract this sentence-level identification information from raw texts, thus benefiting overall performance. Experiments were conducted on both relation extraction and event detection using the Text Analysis Conference Relation Extraction Dataset (TACRED) and Automatic Content Extraction (ACE) 2005 English datasets, respectively. The results demonstrate the effectiveness of the proposed framework.