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.

Text-to-SQL is a technology that converts natural language questions into executable SQL queries, allowing users to query and manage relational databases more easily. In recent years, large language models have significantly advanced the development of text-to-SQL. However, existing methods often overlook validation of the generated results during the SQL generation process. Current error identification methods are mainly divided into self-correction approaches based on large models and feedback methods based on SQL execution, both of which have limitations. We categorize SQL errors into three main types: system errors, skeleton errors, and value errors, and propose a multi-grained error identification method. Experimental results demonstrate that this method can be integrated as a plugin into various methods, providing effective error identification and correction capabilities.

Multimodal named entity recognition (MNER) extends traditional named entity recognition (NER) by integrating visual and textual information. However, current methods still face significant challenges due to the text-image mismatch problem. Recent advancements in text-to-image synthesis provide promising solutions, as synthesized images can introduce additional visual context to enhance MNER model performance. To fully leverage the benefits of both original and synthesized images, we propose an adaptive mixup image augmentation method. This method generates augmented images by determining the mixing ratio based on the matching score between the text and image, utilizing a triplet loss-based Gaussian Mixture Model (TL-GMM). Our approach is highly adaptable and can be seamlessly integrated into existing MNER models. Extensive experiments demonstrate consistent performance improvements, and detailed ablation studies and case studies confirm the effectiveness of our method.

Sentence representation learning is a fundamental task in NLP. Existing methods use contrastive learning (CL) to learn effective sentence representations, which benefit from high-quality contrastive data but require extensive human annotation. Large language models (LLMs) like ChatGPT and GPT4 can automatically generate such data. However, this alternative strategy also encounters challenges: 1) obtaining high-quality generated data from small-parameter LLMs is difficult, and 2) inefficient utilization of the generated data. To address these challenges, we propose a novel adaptive reinforcement tuning (ART) framework. Specifically, to address the first challenge, we introduce a reinforcement learning approach for fine-tuning small-parameter LLMs, enabling the generation of high-quality hard contrastive data without human feedback. To address the second challenge, we propose an adaptive iterative framework to guide the small-parameter LLMs to generate progressively harder samples through multiple iterations, thereby maximizing the utility of generated data. Experiments conducted on seven semantic text similarity tasks demonstrate that the sentence representation models trained using the synthetic data generated by our proposed method achieve state-of-the-art performance. Our code is available at https://github.com/WuNein/AdaptCL.

Recently, multimodal information extraction from social media posts has gained increasing attention in the natural language processing community. Despite their success, current approaches overestimate the significance of images. In this paper, we argue that different social media posts should consider different modalities for multimodal information extraction. Multimodal models cannot always outperform unimodal models. Some posts are more suitable for the multimodal model, while others are more suitable for the unimodal model. Therefore, we propose a general data splitting strategy to divide the social media posts into two sets so that these two sets can achieve better performance under the information extraction models of the corresponding modalities. Specifically, for an information extraction task, we first propose a data discriminator that divides social media posts into a multimodal and a unimodal set. Then we feed these sets into the corresponding models. Finally, we combine the results of these two models to obtain the final extraction results. Due to the lack of explicit knowledge, we use reinforcement learning to train the data discriminator. Experiments on two different multimodal information extraction tasks demonstrate the effectiveness of our method. The source code of this paper can be found in https://github.com/xubodhu/RDS.