Personalized Chain-of-Thought Summarization of Financial News for Investor Decision Support

2025/10/24 by Tianyi Zhang, Zhang, Tianyi, Mu Chen +1 · 1 voice
Computer Science · Decision Sciences · Economics, Econometrics and Finance · #Advanced Text Analysis Techniques #Artificial Intelligence (cs.AI) #Complex Systems and Time Series Analysis #Computational Engineering #FOS: Computer and information sciences #FOS: Economics and business #Finance #General Finance (q-fin.GN) #Stock Market Forecasting Methods #and Science (cs.CE) #cs.AI #cs.CE #q-fin.GN

paper · pdf · doi:10.48550/arxiv.2511.05508

openalex publication_date 2025/10/24 · arxiv published 2025/10/24 · openalex created_date 2025/11/12 · arxiv updated 2025/11/13 · openalex updated_date 2026/07/28

Abstract

Financial advisors and investors struggle with information overload from financial news, where irrelevant content and noise obscure key market signals and hinder timely investment decisions. To address this, we propose a novel Chain-of-Thought (CoT) summarization framework that condenses financial news into concise, event-driven summaries. The framework integrates user-specified keywords to generate personalized outputs, ensuring that only the most relevant contexts are highlighted. These personalized summaries provide an intermediate layer that supports language models in producing investor-focused narratives, bridging the gap between raw news and actionable insights.

Citations

• FAITH: A Framework for Assessing Intrinsic Tabular Hallucinations in Finance
• Are Generative AI Agents Effective Personalized Financial Advisors?
• Multi-round, Chain-of-thought Post-editing for Unfaithful Summaries
• From Single to Multi: How LLMs Hallucinate in Multi-Document Summarization
• PersonalSum: A User-Subjective Guided Personalized Summarization Dataset for Large Language Models
• Are Large Language Models In-Context Personalized Summarizers? Get an iCOPERNICUS Test Done!
• Improving Faithfulness of Large Language Models in Summarization via Sliding Generation and Self-Consistency
• Characterizing Multimodal Long-form Summarization: A Case Study on Financial Reports
• Deficiency of Large Language Models in Finance: An Empirical Examination of Hallucination
• Mistral 7B
• Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
• Refocusing on Relevance: Personalization in NLG
• CTRLsum: Towards Generic Controllable Text Summarization
• GSum: A General Framework for Guided Neural Abstractive Summarization
• It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners
• PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization

Discussions

• Tianyi Zhang, Mu Chen: Personalized Chain-of-Thought Summarization of Financial News for Investor Decision Support https://arxiv.org/abs/2511.05508 https://arxiv.org/pdf/2511.05508 https://arxiv.org/h [bsky, 0 points, 0 comments]

Related

• Financial News Summarization: Can extractive methods still offer a true alternative to LLMs?
• Analogy-Driven Financial Chain-of-Thought (AD-FCoT): A Prompting Approach for Financial Sentiment Analysis
• Extracting Structured Insights from Financial News: An Augmented LLM Driven Approach
• Unlocking Financial Insights: An advanced Multimodal Summarization with Multimodal Output Framework for Financial Advisory Videos
• Question-focused Summarization by Decomposing Articles into Facts and Opinions and Retrieving Entities