While Large Language Models (LLMs) excel in general question answering, they typically generate uniform responses, ignoring users’ diverse intents. Current Personalized Question Answering (PQA) methods face dual limitations: individual-based prompting struggles with data sparsity, while collaborative explicit prompting suffers from inaccurate user matching and attention dispersion caused by text concatenation. To tackle these challenges, we propose Collaborative Latent Prompting (CLP), a PQA framework that fuses collaborative knowledge within a dynamic latent space rather than relying on explicit textual concatenation. First, our Multi-Grained Collaborative Retrieval (MGCR) module ensures precise retrieval of relevant reference users through a three-stage refinement. Next, the Dynamic Q-Former (DQ-Former) utilizes question-modulated dynamic latent queries to extract compact personalized features from noisy texts. Finally, these features are projected into dense soft prompts to implicitly steer a frozen LLM. Experiments across three PQA domains and three backbone LLMs show consistent improvements over representative PQA baselines.

Personalized Question Answering (PQA) requires models to shift from a fact-centric to a user-centric paradigm, inferring implicit intents from historical interactions. However, standard Retrieval-Augmented Generation (RAG) struggles with narrative noise and fragmented semantics. Similarly, while Agent Memory was proposed to maintain long-term consistency, existing implementations predominantly focus on accumulating objective facts, neglecting the subjective attitudes essential for personalization. We argue that for PQA, while objective facts provide the necessary foundational context, relying solely on them is insufficient; they must be augmented by explicit modeling of subjective attitudes to capture a comprehensive user profile. To address this, we introduce Mem-ABC, an Attitude-Aware Agent Memory framework grounded in the Tripartite Model of Attitudes (Affect, Behavior, and Cognition). Mem-ABC employs a two-stage offline process: first autonomously refining raw history into general memories to eliminate noise, and subsequently reorganizing them into a structured attitude-aware memory. This structure enables the agent to explicitly retrieve context aligned with user psychology. Experiments on the LaMP-QA benchmark demonstrate that Mem-ABC consistently outperforms strong baselines across multiple domains.

Multimodal Named Entity Recognition relies on visual context to resolve textual ambiguities. To mitigate data scarcity, Data Augmentation (DA) has become a standard practice; however, existing methods predominantly adopt a one-size-fits-all and random perturbation paradigm, ignoring the internal state of the target model. In this paper, we first conduct a quantitative analysis, revealing that a significant portion of errors (over 30%) are model-specific, stemming from the unique biases of different architectures. To address this, we propose Memory-Guided Hard Data Augmentation, a framework designed to systematically repair these specific defects. First, we employ K-fold cross-validation to identify model-specific Hard Data. Second, we construct a Memory Tree and utilize Large Language Models (LLMs) with a clustering mechanism to induce macro-level error patterns from micro-level failures. This facilitates a paradigm shift from stateless instance-driven augmentation to a logical pattern-driven approach. Finally, we introduce an iterative augmentation mechanism that triggers recursive generation for stubborn instances that fail initial quality filters. Extensive experiments on Twitter-2015 and Twitter-2017 benchmarks demonstrate that our framework consistently yields significant performance gains across various MNER backbones.