Research map / Large language models / Language, safety and interpretability
Global Merger-Arbitrage Forecasting with Language Models
Hinal Jajal, Michał Mucha, Charles Sweat, Chris Pulman, Charlie Flanagan, Peter Anderson
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| finetune GPT-4o with hindsight supervision | GPT-4o · Merger outcome +/- prediction | class-balanced Brier: 0.201 -> 0.151 | Improved |
| add isotonic post-hoc calibration instead of finetuning | GPT-4o · Merger outcome +/- prediction | class-balanced Brier: 0.201 -> 0.186 | Improved |
| add full training data (vs 50%) (ablation) | GPT-4o-FT · Merger outcome +/- prediction | class-balanced Brier: 0.177 -> 0.151 | Improved |
| add oversampling of terminated deals (ablation) | GPT-4o-FT · Merger outcome +/- prediction | class-balanced Brier: 0.170 -> 0.151 | Improved |
| oversample more aggressively (2.0, 1.65) (ablation) | GPT-4o-FT · Merger outcome +/- prediction | class-balanced Brier: 0.151 -> 0.163 | Hurt |
| add hindsight-guided postmortem supervision (ablation) | GPT-4o-FT · Merger outcome +/- prediction | class-balanced Brier: 0.183 -> 0.151 | Improved |
| add market-probability smoothing (ablation) | GPT-4o-FT · Merger outcome +/- prediction | class-balanced Brier: 0.181 -> 0.151 | Improved |
| add specialized research agents to Deal Card (ablation) | GPT-4o-FT · Merger outcome +/- prediction | class-balanced Brier: 0.172 -> 0.151 | Improved |
| add Stakeholder Ownership agent to Deal Card only (ablation) | GPT-4o-FT · Merger outcome +/- prediction | class-balanced Brier: 0.172 -> 0.158 | Improved |
| finetune GPT-4o | GPT-4o · Days to completion | MAPE: 0.463 -> 0.385 | Improved |
| finetune GPT-4o with hindsight supervision | GPT-4o · Rubric coverage of Day-1 reports | rubric coverage: 21.5% -> 50.2% | Improved |
| finetune GPT-4o | GPT-4o · Deal report grounding | unsupported-claim rate: 0.3% -> 0.1% | No clear effect |
Closest papers by meaning
- FinBen: A Holistic Financial Benchmark for Large Language Models (NeurIPS 2024 · similarity 0.89)
- Conformal Arbitrage: Risk-Controlled Balancing of Competing Objectives in Language Models (NeurIPS 2025 · similarity 0.84)
- EnterpriseBench: Evaluating LLM Agents on End-to-End Spreadsheet Tasks in Finance (NeurIPS 2026 · similarity 0.84)
- FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning (ICLR 2026 · similarity 0.83)
- Martingale Score: An Unsupervised Metric for Bayesian Rationality in LLM Reasoning (NeurIPS 2025 · similarity 0.83)
- Prune 'n Predict: Optimizing LLM Decision-making with Conformal Prediction (ICML 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
