Saved in:
Bibliographic Details
Main Authors: He, Songrun, Lv, Linying, Manela, Asaf, Wu, Jimmy
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.11677
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914160844996608
author He, Songrun
Lv, Linying
Manela, Asaf
Wu, Jimmy
author_facet He, Songrun
Lv, Linying
Manela, Asaf
Wu, Jimmy
contents We introduce a family of chronologically consistent, instruction-tuned large language models to eliminate lookahead bias. Each model is trained only on data available before a clearly defined knowledge-cutoff date, ensuring strict temporal separation from any post-cutoff data. The resulting framework offers (i) a simple, conversational chat interface, (ii) fully open, fixed model weights that guarantee replicability, and (iii) a conservative lower bound on forecast accuracy, isolating the share of predictability that survives once training leakage is removed. Together, these features provide researchers with an easy-to-use generative AI tool useful for a wide range of prediction tasks that is free of lookahead bias.
format Preprint
id arxiv_https___arxiv_org_abs_2510_11677
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Instruction Tuning Chronologically Consistent Language Models
He, Songrun
Lv, Linying
Manela, Asaf
Wu, Jimmy
Machine Learning
General Finance
We introduce a family of chronologically consistent, instruction-tuned large language models to eliminate lookahead bias. Each model is trained only on data available before a clearly defined knowledge-cutoff date, ensuring strict temporal separation from any post-cutoff data. The resulting framework offers (i) a simple, conversational chat interface, (ii) fully open, fixed model weights that guarantee replicability, and (iii) a conservative lower bound on forecast accuracy, isolating the share of predictability that survives once training leakage is removed. Together, these features provide researchers with an easy-to-use generative AI tool useful for a wide range of prediction tasks that is free of lookahead bias.
title Instruction Tuning Chronologically Consistent Language Models
topic Machine Learning
General Finance
url https://arxiv.org/abs/2510.11677