The authors built RICE-Alpha around two components.
Event graphs improve LLM stock forecasts across two major markets
RICE-Alpha uses temporally valid corporate event sequences to correct baseline stock scores only when historical transitions provide reliable additional signal.
Research Lab
Tong Liu · Lanmiao Liu · Xiang Hu
Zircon Security · Utrecht University · The Max Planck Institute for Psycholinguistics · China Life R&D Center
Research Digest··3 min read
Liu, Liu and Hu tested an LLM-agent framework that links company news into issuer-specific event sequences while restricting every forecast to information available at that time.
Why this paper
From The Max Planck Institute for Psycholinguistics and 3 others · Part of Context Engineering for Agents, now 38 papers
In one line
Temporally grounded, reliability-calibrated historical event transitions add incremental stock-forecasting signal when applied as a residual correction to a multi-view LLM forecast.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks (2 benchmarks)
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§