Individual investors are disadvantaged in financial markets, overwhelmed by abundant information and lacking professional analysis.Equity research reports are crucial resources, offering valuable insights.By leveraging these reports, large language models (LLMs) can enhance investors' decision-making and strengthen financial analysis.However, two key challenges limit their effectiveness: (1) the rapid evolution of market events outpaces the slow update cycles of existing knowledge bases, and (2) the long-form, unstructured nature of financial reports hinders timely, context-aware integration by LLMs.To address these challenges, we tackle both data and methodology aspects.We introduce the Event-Enhanced Automated Construction of Financial Knowledge Graph (FinKario), a dataset with over 305,360 entities, 210,328 relational triples, and 19 relation types.FinKario integrates real-time company fundamentals and events through promptdriven extraction guided by institutional templates, providing structured, accessible financial insights for LLMs.We further propose a Two-stage, Graph-based retrieval strategy (FinKario-RAG) to optimize retrieval over evolving, large-scale financial knowledge.Experiments show that FinKario with FinKario-RAG achieves superior trend prediction accuracy, outperforming financial LLMs by 18.81% and institutional strategies by 17.85% on average in backtesting.

While stock prediction task traditionally relies on volume-price and fundamental data to predict the return ratio or price movement trend, sentiment factors derived from social media platforms such as StockTwits offer a complementary and useful source of real-time market information. However, we find that most social media posts, along with the public sentiment they reflect, provide limited value for trading predictions due to their noisy nature. To tackle this, we propose a novel dynamic expert tracing algorithm that filters out non-informative posts and identifies both true and inverse experts whose consistent predictions can serve as valuable trading signals. Our approach achieves significant improvements over existing expert identification methods in stock trend prediction. However, when using binary expert predictions to predict the return ratio, similar to all other expert identification methods, our approach faces a common challenge of signal sparsity with expert signals cover only about 4% of all stock-day combinations in our dataset. To address this challenge, we propose a dual graph attention neural network that effectively propagates expert signals across related stocks, enabling accurate prediction of return ratios and significantly increasing signal coverage. Empirical results show that our propagated expert-based signals not only exhibit strong predictive power independently but also work synergistically with traditional financial features. These combined signals significantly outperform representative baseline models in all quant-related metrics including predictive accuracy, return metrics, and correlation metrics, resulting in more robust investment strategies. We hope this work inspires further research into leveraging social media data for enhancing quantitative investment strategies. The code can be seen inhttps://github.com/wanyunzh/DualGAT.

In recent years, accurately and quickly deploying medical large language models (LLMs) has become a trend. Among these, retrieval-augmented generation (RAG) has garnered attention due to rapid deployment and privacy protection. However, the challenge hinder the practical deployment of RAG for medical diagnosis: the semantic gap between colloquial patient descriptions and the professional terminology within medical knowledge bases. We try to address the challenge from the data perspective and the method perspective. First, to address the semantic gap in existing knowledge bases, we construct DiagnosGraph, a generalist knowledge graph covering both modern medicine and Traditional Chinese Medicine. It contains 876 common diseases with the graph of 7,997 nodes and 37,201 triples. To bridge the gap between colloquial patient narratives and academic medical knowledge, DiagnosGraph also introduces 1,908 medical record by formalizing the patient chief complaint and proposing a medical diagnosis. Second, we introduce the Multi-Round Diagnostic RAG (MRD-RAG) framework. It utilizes a multi-round dialogue to refine diagnostic possibilities, emulating the clinical reasoning of a physician. Experiments conducted on four medical benchmarks, with evaluations by human physicians, demonstrate that MRD-RAG enhances the diagnostic performance of LLMs, highlighting its potential to make automated diagnosis more accurate and human-aligned. The codebase and supplementary materials can be found at our page11https://sites.google.com/view/mrd-rag.