Approaching Human-Level Forecasting with Language Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909122888204288 |
|---|---|
| author | Halawi, Danny Zhang, Fred Yueh-Han, Chen Steinhardt, Jacob |
| author_facet | Halawi, Danny Zhang, Fred Yueh-Han, Chen Steinhardt, Jacob |
| contents | Forecasting future events is important for policy and decision making. In this work, we study whether language models (LMs) can forecast at the level of competitive human forecasters. Towards this goal, we develop a retrieval-augmented LM system designed to automatically search for relevant information, generate forecasts, and aggregate predictions. To facilitate our study, we collect a large dataset of questions from competitive forecasting platforms. Under a test set published after the knowledge cut-offs of our LMs, we evaluate the end-to-end performance of our system against the aggregates of human forecasts. On average, the system nears the crowd aggregate of competitive forecasters, and in some settings surpasses it. Our work suggests that using LMs to forecast the future could provide accurate predictions at scale and help to inform institutional decision making. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_18563 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Approaching Human-Level Forecasting with Language Models Halawi, Danny Zhang, Fred Yueh-Han, Chen Steinhardt, Jacob Machine Learning Artificial Intelligence Computation and Language Information Retrieval Forecasting future events is important for policy and decision making. In this work, we study whether language models (LMs) can forecast at the level of competitive human forecasters. Towards this goal, we develop a retrieval-augmented LM system designed to automatically search for relevant information, generate forecasts, and aggregate predictions. To facilitate our study, we collect a large dataset of questions from competitive forecasting platforms. Under a test set published after the knowledge cut-offs of our LMs, we evaluate the end-to-end performance of our system against the aggregates of human forecasts. On average, the system nears the crowd aggregate of competitive forecasters, and in some settings surpasses it. Our work suggests that using LMs to forecast the future could provide accurate predictions at scale and help to inform institutional decision making. |
| title | Approaching Human-Level Forecasting with Language Models |
| topic | Machine Learning Artificial Intelligence Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2402.18563 |