Line of inquiry
Inquiring lines›How do training data and architect…›What does iterative improvement ac…›this line of inquiry
What improves LLM forecasting accuracy beyond base model capability?
A broader line of inquiry — a family of 26 specific questions the research asks around this. Follow one into its inquiring-line page, or move sideways to a related line below.
Questions in this line of inquiry 26
Specific inquiring lines the field asks around this — ordered from the most general framing down to the most specific angle.
- Do newer language model generations improve forecasting ability without additional training?
- Do longer prediction horizons systematically degrade LLM forecasting accuracy?
- Do monolithic prompts underutilize LLM strengths in forecasting workflows?
- How do search and reasoning workflows improve forecasting performance over base models?
- What real-world forecasting domains benefit most from contextual reasoning integration?
- Do LLMs and human forecasters make better predictions when pooled together?
- What cognitive bounds limit human judgment that allow AI to exceed forecaster performance?
- Can self-ratings of output quality predict forecast performance?
- Why do macro and micro forecasting scales require different reasoning approaches?
- What role does retrieval mechanism design play in forecast accuracy?
- Can language models match competitive crowd forecasters on real future events?
- When does prediction accuracy actually translate to better managerial decisions?
- What strategic decisions do humans keep when AI handles forecasting?
- Why does LLM performance improve when forecasting tasks include organized reasoning?
- Can LLMs forecast performance improve with retrieval augmentation on venture tasks?
- How does training-data leakage threaten forecasting comparisons with historical venture datasets?
- Why are post-cutoff test sets essential for evaluating genuine forecasting ability?
- How much does domain expertise actually improve human forecasting under uncertainty?
- How should forecasting methods adapt to a post-AGI regime?
- Do LLMs generalize venture forecasting skill to other strategic foresight domains?
- How much does workflow architecture matter compared to raw model capability in forecasting?
- When do prediction models' optimization for data fit actually support better policy decisions?
- How do AI researcher forecasts compare across different timeline question phrasings?
- What distinguishes an error bound from a forecast of system behavior?
- What privacy-preserving evaluation methods best capture real-world forecasting ability?
- Can economic world models explain outcomes or only predict them?