mlsanityData to 7 Oct 2026

Global Merger-Arbitrage Forecasting with Language Models

arXiv 2607.09921 ↗First posted 10 Jul 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

We present a language-model forecasting system for merger arbitrage, a specialized high-stakes financial setting in which the task is to predict the outcome of announced M&A deals. Unlike prior work on judgmental forecasting with LLMs, which has focused on broad mixed-topic benchmarks and short context such as news snippets, we study a setting that requires long-context reasoning over hundreds of pages of technical documents. Our system combines expert-guided context engineering with finetuning on hindsight-guided reasoning traces derived from historical deals. Given an announced deal, it outputs a probability distribution over three mutually exclusive outcomes: closing at announced terms, a higher bid, or deal termination. On an out-of-sample set of more than 400 large deals spanning 42 countries, our finetuned system achieves the best performance of any method we evaluate, reducing class-balanced Brier score to 0.151. This is 24% below calibrated market-implied probabilities, 19% below XGBoost, and 25-42% below frontier language models. These results, together with ablation studies, show that LLM-based forecasting can succeed in specialized, long-context financial workflows, with hindsight-based supervision and expert-designed context playing a critical role.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 17 of its 22 references that are in the map. First posted on arXiv 10 Jul 2026.

Builds on

17 of 22 references.

References · 17

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2023Let's Verify Step by Stepcited by 3,598
  3. 2022Solving math word problems with process- and outcome-based feedbackcited by 871
  4. 2024ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilitiescited by 104
  5. 2024Approaching Human-Level Forecasting with Language Modelscited by 102
  6. 2024Wisdom of the Silicon Crowd: LLM Ensemble Prediction Capabilities Rival Human Crowd Accuracycited by 66
  7. 2024Consistency Checks for Language Model Forecasterscited by 27
  8. 2025Pitfalls in Evaluating Language Model Forecasterscited by 23
  9. 2024AI-Augmented Predictions: LLM Assistants Improve Human Forecasting Accuracycited by 21
  10. 2025Outcome-based Reinforcement Learning to Predict the Futurecited by 21
  11. 2025Bench to the Future: A Pastcasting Benchmark for Forecasting Agentscited by 20
  12. 2024Are LLMs Prescient? A Continuous Evaluation using Daily News as the Oraclecited by 19
5 more
  1. 2024Can Language Models Use Forecasting Strategies?cited by 13
  2. 2024Greenback Bears and Fiscal Hawks: Finance is a Jungle and Text Embeddings Must Adaptcited by 12
  3. 2025AIA Forecaster: Technical Reportcited by 9
  4. 2024Reasoning and Tools for Human-Level Forecastingcited by 7
  5. 2021Alignment Problems With Current Forecasting Platformscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Reasoning through Verifiable Forecast Actions: Consistency-Grounded RL for Financial LLMs
  2. 2024FinBen: A Holistic Financial Benchmark for Large Language Models
  3. 2023Temporal Data Meets LLM -- Explainable Financial Time Series Forecasting
  4. 2026Look-Ahead-Bench: a Standardized Benchmark of Look-ahead Bias in Point-in-Time LLMs for Finance
  5. 2026LLM-based Agents for Forecasting and Prediction: Methods, Training, Evaluation, and Applications
  6. 2026FinAbstain: Uncertainty-Calibrated Multimodal RAG for Selective Financial Forecasting
  7. 2025BizFinBench: A Business-Driven Real-World Financial Benchmark for Evaluating LLMs
  8. 2025XFinBench: Benchmarking LLMs in Complex Financial Problem Solving and Reasoning