LLMs are now embedded in a wide range of everyday scenarios. However, their inherent hallucinations risk hiding misinformation in fluent responses, raising concerns about overreliance on AI. Detecting overreliance is challenging, as it often arises in complex, dynamic contexts and cannot be easily captured by post-hoc task outcomes. In this work, we aim to investigate how users’ behavioral patterns correlate with overreliance. We collected interaction logs from 77 participants working with an LLM injected plausible misinformation across three real-world tasks and we assessed overreliance by whether participants detected and corrected these errors. By semantically encoding and clustering segments of user interactions, we identified five behavioral patterns linked to overreliance: users with low overreliance show careful task comprehension and fine-grained navigation; users with high overreliance show frequent copy-paste, skipping initial comprehension, repeated LLM references, coarse locating, and accepting misinformation despite hesitation. We discuss design implications for mitigation.

With increasing demands for efficiency, information retrieval has developed a branch of sparse retrieval, further advancing towards inference-free retrieval where the documents are encoded during indexing time and there is no model-inference for queries. Existing sparse retrieval models rely on FLOPS regularization for sparsification, while this mechanism was originally designed for Siamese encoders, it is considered to be suboptimal in inference-free scenarios which is asymmetric. Previous attempts to adapt FLOPS for inference-free scenarios have been limited to rule-based methods, leaving the potential of sparsification approaches for inference-free retrieval models largely unexplored. In this paper, we explore ℓ0 inspired sparsification manner for inference-free retrievers. Through comprehensive out-of-domain evaluation on the BEIR benchmark, our method achieves state-of-the-art performance among inference-free sparse retrieval models and is comparable to leading Siamese sparse retrieval models. Furthermore, we provide insights into the trade-off between retrieval effectiveness and computational efficiency, demonstrating practical value for real-world applications.

In existing multiview clustering research, the comprehensive learning from multiview graph and feature spaces simultaneously remains insufficient when achieving a consistent clustering structure. In addition, a postprocessing step is often required. In light of these considerations, a cross-view approximation on Grassman manifold (CAGM) model is proposed to address inconsistencies within multiview adjacency matrices, feature matrices, and cross-view combinations from the two sources. The model uses a ratio-formed objective function, enabling parameter-free bidirectional fusion. Furthermore, the CAGM model incorporates a paired encoding mechanism to generate low-dimensional and orthogonal cross-view embeddings. Through the approximation of two measurable subspaces on the Grassmann manifold, the direct acquisition of the indicator matrix is realized. Furthermore, an effective optimization algorithm corresponding to the CAGM model is derived. Comprehensive experiments on four real-world datasets are conducted to substantiate the effectiveness of our proposed method.