MacroLens: A Multi-Task Benchmark for Contextual Financial Reasoning under Macroeconomic Scenarios

• URL: http://arxiv.org/abs/2606.24950v1
• Date: Tue, 23 Jun 2026 07:52:44 GMT
• Title: MacroLens: A Multi-Task Benchmark for Contextual Financial Reasoning under Macroeconomic Scenarios
• Abstract summary: MacroLens covers 4,416 U.S. small-cap splits and micro-cap gradient splits.<n>Seven tasks share one point-in-time panel of prices, 46.8M equities over accounting facts, 53 macroeconomic series, 295,860 SEC filings, and 215,882 news articles.<n>Tasks span contextual forecasting, public and private valuation, statement generation from fundamentals and descriptions, scenario-conditioned returns, and real-estate valuation.
• Score: 44.59910717749994
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Financial decision-making is contextual: forecasting prices, valuing companies, and assessing event exposure weigh price history, accounting fundamentals, macroeconomic regime, and contemporaneous text. A benchmark over these four signals is hard to build because finance violates four assumptions of time-series evaluation: text must be gated by its publication date to prevent look-ahead, quarterly fundamentals are reported with a one- to ninety-day lag, filing text is partly redundant with the numerical statement fields it accompanies, and macroeconomic regimes leak across calendar splits. No public benchmark addresses all four signals jointly. MacroLens covers 4,416 U.S. small- and micro-cap equities over 2021-2026. Seven tasks share one point-in-time panel of prices, 46.8M XBRL accounting facts, 53 macroeconomic series, 295,860 SEC filings, and 215,882 news articles, plus a scenario layer of 1,130 macroeconomic events across 49 types automatically detected and rendered as natural language. Tasks span contextual forecasting, public and private valuation, statement generation from fundamentals and descriptions, scenario-conditioned returns, and real-estate valuation. We evaluate 19 methods across six families spanning naive heuristics through time-series foundation models, fine-tuned LLM-based time-series models, and zero-shot large language models (LLMs), plus a five-step feature-context ablation on two frontier LLMs and a gradient-boosted baseline. MacroLens is released at https://huggingface.co/datasets/DeepAuto-AI/MacroLens.

Related papers

• Nexus : An Agentic Framework for Time Series Forecasting [72.73790673303154]
  Time series forecasting requires reasoning with unstructured contextual data such as news or events.<n>We introduce Nexus, a multi-agent forecasting framework that decomposes prediction into specialized stages.<n>We show that current-generation LLMs possess substantially stronger intrinsic forecasting ability than previously recognized.
  arXiv  Detail & Related papers  (2026-05-14T05:12:13Z)
• PolyBench: Benchmarking LLM Forecasting and Trading Capabilities on Live Prediction Market Data [3.7753883100108525]
  We present textbfPolyBench,' a benchmark for predicting real-world events from live market signals.<n>Using PolyBench, we evaluate seven state-of-the-art Large Language Models.<n>Our framework assesses directional accuracy, our proposed Confidence-Weighted Return (CWR), Annualized Percentage Yield (APY), and Sharpe ratio.
  arXiv  Detail & Related papers  (2026-04-03T06:25:21Z)
• QuitoBench: A High-Quality Open Time Series Forecasting Benchmark [32.21290355342465]
  Time series forecasting is critical across finance, healthcare, and cloud computing.<n>We introduce textscQuitoBench, a regime-balanced benchmark for time series forecasting.
  arXiv  Detail & Related papers  (2026-03-27T02:24:34Z)
• Same Claim, Different Judgment: Benchmarking Scenario-Induced Bias in Multilingual Financial Misinformation Detection [64.75447949495307]
  Large language models (LLMs) have been widely applied across various domains of finance.<n> behavioral biases can lead to instability and uncertainty in decision-making.<n>mfmdscen is a benchmark for evaluating behavioral biases in mfmd across diverse economic scenarios.
  arXiv  Detail & Related papers  (2026-01-08T22:00:32Z)
• History Rhymes: Macro-Contextual Retrieval for Robust Financial Forecasting [1.8911049192403768]
  We introduce macro-contextual retrieval, a retrieval-augmented forecasting framework that grounds each prediction in historically analogous macroeconomic regimes.<n>We trained on seventeen years of S&P 500 data (2007-2023) and evaluated OOD on AAPL (2024) and XOM (2024), and the framework consistently narrows the CV to OOD performance gap.<n>By operationalizing the principle that "financial history may not repeat, but it often rhymes," this work demonstrates that macro-aware retrieval yields robust, explainable forecasts under distributional change.
  arXiv  Detail & Related papers  (2025-11-12T21:34:23Z)
• MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application [118.63802040274999]
  MultiFinBen is the first expert-annotated multilingual (five languages) and multimodal benchmark for evaluating LLMs in realistic financial contexts.<n>Financial reasoning tests cross-lingual evidence integration from filings and news, and financial OCR, which extracts structured text from scanned documents.<n> evaluating 21 leading LLMs shows that even frontier multimodal models like GPT-4o achieve only 46.01% overall, stronger on vision and audio but dropping sharply in multilingual settings.
  arXiv  Detail & Related papers  (2025-06-16T22:01:49Z)
• Open-FinLLMs: Open Multimodal Large Language Models for Financial Applications [88.96861155804935]
  We introduce textitOpen-FinLLMs, the first open-source multimodal financial LLMs.<n>FinLLaMA is pre-trained on a comprehensive 52-billion-token corpus; FinLLaMA-Instruct, fine-tuned with 573K financial instructions; and FinLLaVA, enhanced with 1.43M multimodal tuning pairs.<n>We evaluate Open-FinLLMs across 14 financial tasks, 30 datasets, and 4 multimodal tasks in zero-shot, few-shot, and supervised fine-tuning settings.
  arXiv  Detail & Related papers  (2024-08-20T16:15:28Z)
• Macroeconomic Forecasting with Large Language Models [2.5234156040689233]
  This paper presents a comparative analysis evaluating the accuracy of Large Language Models (LLMs) against traditional macro time series forecasting approaches.<n>Our findings provide valuable insights into the strengths and limitations of LLMs in forecasting macroeconomic time series, shedding light on their applicability in real-world scenarios.
  arXiv  Detail & Related papers  (2024-07-01T01:25:26Z)
• FinBen: A Holistic Financial Benchmark for Large Language Models [75.09474986283394]
  FinBen is the first extensive open-source evaluation benchmark, including 36 datasets spanning 24 financial tasks. FinBen offers several key innovations: a broader range of tasks and datasets, the first evaluation of stock trading, novel agent and Retrieval-Augmented Generation (RAG) evaluation, and three novel open-source evaluation datasets for text summarization, question answering, and stock trading.
  arXiv  Detail & Related papers  (2024-02-20T02:16:16Z)
• Trillion Dollar Words: A New Financial Dataset, Task & Market Analysis [1.933681537640272]
  We construct the largest tokenized and annotated dataset of Federal Open Market Committee (FOMC) speeches, meeting minutes, and press conference transcripts. Using the best-performing model (RoBERTa-large), we construct a measure of monetary policy stance for the document release days. Our dataset, models, and code are publicly available on Huggingface and GitHub under CC BY-NC 4.0 license.
  arXiv  Detail & Related papers  (2023-05-13T17:32:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.