9 papers in the archive (2022–2026), average empirical rigor 6.6/10, average math complexity 2.9/10, 1 with linked code. Quadrant mix: Philosophers ×1, Street Traders ×8.
Works mostly in NLP & LLMs in Finance, Machine Learning for Market Forecasting, Factor Investing & Asset Pricing, Market Microstructure.
Frequent co-authors: Chanyeol Choi (5), Yongjae Lee (5), Hoyoung Lee (3), Sumin Kim (3), Jihoon Kwon (3), Wonbin Ahn (2).
Scores are our LLM-assisted heuristics (methodology), not peer review or citation counts. Author pages are generated from paper metadata; name variants may split one person across pages. arXiv author page →
Ordered by a blend of empirical rigor (60%) and math complexity (40%).
We document the capability of large language models (LLMs) like ChatGPT to predict stock market reactions from news headlines without direct financial training. Using post-knowledge-cutoff headlines, GPT-4 captures initial market responses, achieving approximately 90% portfolio-day hit rates for the
Mining 29,000 accounting ratios for t-statistics $> 2.0$ leads to cross-sectional return predictability similar to the peer review process. For both, $\approx50%$ of predictability remains after the original sample periods. This finding holds for many categories of research, including research with
Frozen large language model (LLM) checkpoints extract information from pre-cutoff public text that is associated with future fundamentals and equity returns beyond standard contemporaneous valuation measures. Because each frozen checkpoint has a fixed knowledge cutoff, it can be interpreted as a com
Prediction markets provide a unique setting where event-level time series are directly tied to natural-language descriptions, yet discovering robust lead-lag relationships remains challenging due to spurious statistical correlations. We propose a hybrid two-stage causal screener to address this chal
Mention markets, a type of prediction market in which contracts resolve based on whether a specified keyword is mentioned during a future public event, require accurate probabilistic forecasts of keyword-mention outcomes. While recent work shows that large language models (LLMs) can generate forecas
We introduce RFC Bench, a benchmark for evaluating large language models on financial misinformation under realistic news. RFC Bench operates at the paragraph level and captures the contextual complexity of financial news where meaning emerges from dispersed cues. The benchmark defines two complemen
In finance, Large Language Models (LLMs) face frequent knowledge conflicts arising from discrepancies between their pre-trained parametric knowledge and real-time market data. These conflicts are especially problematic in real-world investment services, where a model’s inherent biases can misalign w
Large Language Models (LLMs) are increasingly integrated into financial workflows, but evaluation practice has not kept up. Finance-specific biases can inflate performance, contaminate backtests, and make reported results useless for any deployment claim. We identify five recurring biases in financi
Evaluating finance research agents requires rubrics that reflect expert standards and fix the values correct as of an information cutoff. Expert-reviewed finance benchmarks rely on fixed, per-item rubrics, which are costly to extend and cannot encode each institution’s own standard. In FinAutoRubric