{"ID":2839839,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.14130","arxiv_id":"2511.14130","title":"PRISM: Prompt-Refined In-Context System Modelling for Financial Retrieval","abstract":"With the rapid progress of large language models (LLMs), financial information retrieval has become a critical industrial application. Extracting task-relevant information from lengthy financial filings is essential for both operational and analytical decision-making. We present PRISM, a training-free framework that integrates refined system prompting, in-context learning (ICL), and lightweight multi-agent coordination for document and chunk ranking tasks. Our primary contribution is a systematic empirical study of when each component provides value: prompt engineering delivers consistent performance with minimal overhead, ICL enhances reasoning for complex queries when applied selectively, and multi-agent systems show potential primarily with larger models and careful architectural design. Extensive ablation studies across FinAgentBench, FiQA-2018, and FinanceBench reveal that simpler configurations often outperform complex multi-agent pipelines, providing practical guidance for practitioners. Our best configuration achieves an NDCG@5 of 0.71818 on FinAgentBench, ranking third while being the only training-free approach in the top three. We provide comprehensive feasibility analyses covering latency, token usage, and cost trade-offs to support deployment decisions. The source code is released at https://bit.ly/prism-ailens.","short_abstract":"With the rapid progress of large language models (LLMs), financial information retrieval has become a critical industrial application. Extracting task-relevant information from lengthy financial filings is essential for both operational and analytical decision-making. We present PRISM, a training-free framework that in...","url_abs":"https://arxiv.org/abs/2511.14130","url_pdf":"https://arxiv.org/pdf/2511.14130v2","authors":"[\"Chun Chet Ng\",\"Jia Yu Lim\",\"Wei Zeng Low\"]","published":"2025-11-18T04:30:52Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.CE\",\"cs.CL\",\"cs.IR\"]","methods":"[\"Large Language Model\",\"Language Model\"]","project_urls":"[\"https://bit.ly/prism-ailens\"]","has_code":false,"code_links":[{"ID":606911,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2839839,"paper_url":"https://arxiv.org/abs/2511.14130","paper_title":"PRISM: Prompt-Refined In-Context System Modelling for Financial Retrieval","repo_url":"https://github.com/ailensgroup/prism","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0},{"ID":606912,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2839839,"paper_url":"https://arxiv.org/abs/2511.14130","paper_title":"PRISM: Prompt-Refined In-Context System Modelling for Financial Retrieval","repo_url":"https://github.com/ailensgroup/prism.git","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0},{"ID":606913,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2839839,"paper_url":"https://arxiv.org/abs/2511.14130","paper_title":"PRISM: Prompt-Refined In-Context System Modelling for Financial Retrieval","repo_url":"https://github.com/features/copilot","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0},{"ID":606914,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2839839,"paper_url":"https://arxiv.org/abs/2511.14130","paper_title":"PRISM: Prompt-Refined In-Context System Modelling for Financial Retrieval","repo_url":"https://github.com/features/spark","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0},{"ID":606915,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2839839,"paper_url":"https://arxiv.org/abs/2511.14130","paper_title":"PRISM: Prompt-Refined In-Context System Modelling for Financial Retrieval","repo_url":"https://github.com/features/models","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0},{"ID":606916,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2839839,"paper_url":"https://arxiv.org/abs/2511.14130","paper_title":"PRISM: Prompt-Refined In-Context System Modelling for Financial Retrieval","repo_url":"https://github.com/features/actions","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0},{"ID":606917,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2839839,"paper_url":"https://arxiv.org/abs/2511.14130","paper_title":"PRISM: Prompt-Refined In-Context System Modelling for Financial Retrieval","repo_url":"https://github.com/features/codespaces","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0},{"ID":606918,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2839839,"paper_url":"https://arxiv.org/abs/2511.14130","paper_title":"PRISM: Prompt-Refined In-Context System Modelling for Financial Retrieval","repo_url":"https://github.com/features/issues","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0},{"ID":606919,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2839839,"paper_url":"https://arxiv.org/abs/2511.14130","paper_title":"PRISM: Prompt-Refined In-Context System Modelling for Financial Retrieval","repo_url":"https://github.com/features/code-review","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0},{"ID":606920,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2839839,"paper_url":"https://arxiv.org/abs/2511.14130","paper_title":"PRISM: Prompt-Refined In-Context System Modelling for Financial Retrieval","repo_url":"https://github.com/security/advanced-security","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0},{"ID":606921,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2839839,"paper_url":"https://arxiv.org/abs/2511.14130","paper_title":"PRISM: Prompt-Refined In-Context System Modelling for Financial Retrieval","repo_url":"https://github.com/enterprise/startups","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0},{"ID":606922,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2839839,"paper_url":"https://arxiv.org/abs/2511.14130","paper_title":"PRISM: Prompt-Refined In-Context System Modelling for Financial Retrieval","repo_url":"https://github.com/solutions/industry","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0},{"ID":606923,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2839839,"paper_url":"https://arxiv.org/abs/2511.14130","paper_title":"PRISM: Prompt-Refined In-Context System Modelling for Financial Retrieval","repo_url":"https://github.com/solutions/use-case","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}