Thanks to the development of geographic information technology, geospatial representation learning based on POIs (Point-of-Interest) has gained widespread attention in the past few years. POI is an important indicator to reflect urban socioeconomic activities, widely used to extract geospatial information. However, previous studies often focus on a specific area, such as a city or a district, and are designed only for particular tasks, such as land-use classification. On the other hand, large-scale pre-trained models (PTMs) have recently achieved impressive success and become a milestone in artificial intelligence (AI). Against this background, this study proposes the first large-scale pre-training geospatial representation learning model called GeoBERT. First, we collect about 17 million POIs in 30 cities across China to construct pre-training corpora, with 313 POI types as the tokens and the level-7 Geohash grids as the basic units. Second, we pre-train GeoEBRT to learn grid embedding in self-supervised learning by masking the POI type and then predicting. Third, under the paradigm of “pre-training + fine-tuning”, we design five practical downstream tasks. Experiments show that, with just one additional output layer fine-tuning, GeoBERT outperforms previous NLP methods (Word2vec, GloVe) used in geospatial representation learning by 9.21% on average in F1-score for classification tasks, such as store site recommendation and working/living area prediction. For regression tasks, such as POI number prediction, house price prediction, and passenger flow prediction, GeoBERT demonstrates greater performance improvements. The experiment results prove that pre-training on large-scale POI data can significantly improve the ability to extract geospatial information. In the discussion section, we provide a detailed analysis of what GeoBERT has learned from the perspective of attention mechanisms.

Large language models (LLMs) have demonstrated their significant potential to be applied for addressing various application tasks. However, traditional recommender systems continue to face great challenges such as poor interactivity and explainability, which actually also hinder their broad deployment in real-world systems. To address these limitations, this paper proposes a novel paradigm called Chat-Rec (ChatGPT Augmented Recommender System) that innovatively augments LLMs for building conversational recommender systems by converting user profiles and historical interactions into prompts. Chat-Rec is demonstrated to be effective in learning user preferences and establishing connections between users and products through in-context learning, which also makes the recommendation process more interactive and explainable. What's more, within the Chat-Rec framework, user's preferences can transfer to different products for cross-domain recommendations, and prompt-based injection of information into LLMs can also handle the cold-start scenarios with new items. In our experiments, Chat-Rec effectively improve the results of top-k recommendations and performs better in zero-shot rating prediction task. Chat-Rec offers a novel approach to improving recommender systems and presents new practical scenarios for the implementation of AIGC (AI generated content) in recommender system studies.

Recent advancements in Large Language Models (LLMs) have significantly extended context windows, igniting discussions about the necessity of Retrieval-Augmented Generation (RAG). U-NIAH, a unified Needle-in-a-Haystack (NIAH) framework, systematically evaluates LLMs and RAG methods in controlled long-context settings. It extends beyond traditional NIAH by incorporating more practical and complex scenarios like multi-needle, long-needle, and needle-in-needle configurations and leveraging the synthetic dataset to mitigate LLM biases. The experiments aim to address three research questions in long-context scenarios: (1) performance tradeoffs between LLMs and RAG, (2) error patterns in RAG, and (3) RAG’s limitations in complex settings. Results show that smaller LLMs benefit more from RAG. In all settings, RAG achieves a win rate of 82.58% over direct answers. Additionally, it is found that retrieval noise and chunk ordering degrade RAG performance, and we further summarized typical error patterns, including omissions due to noise, hallucinations under high noise critical conditions, and self-doubt behaviors, as well as how these phenomena vary with context length. Finally, in some challenging scenarios, experiments show that deep reasoning models are more easily affected by distractors. These findings highlight the complementary roles of RAG and LLMs and offer actionable insights for optimizing deployment strategies ( https://github.com/Tongji-KGLLM/U-NIAH ).

Industrial parks are critical to urban economic growth. Yet, their development often encounters challenges stemming from imbalances between industrial requirements and urban services, underscoring the need for strategic planning and operations. This paper introduces IndustryScopeKG, a pioneering large-scale multi-modal, multi-level industrial park knowledge graph, which integrates diverse urban data including street views, corporate, socio-economic, and geospatial information, capturing the complex relationships and semantics within industrial parks. Alongside this, we present the IndustryScopeGPT framework, which leverages Large Language Models (LLMs) with Monte Carlo Tree Search to enhance tool-augmented reasoning and decision-making in Industrial Park Planning and Operation (IPPO). Our work significantly improves site recommendation and functional planning, demonstrating the potential of combining LLMs with structured datasets to advance industrial park management. This approach sets a new benchmark for intelligent IPPO research and lays a robust foundation for advancing urban industrial development. The dataset and related code are available at https://github.com/Tongji-KGLLM/IndustryScope.