MAPLE: Metadata Conditioned LLM Pretraining for Locale-Aware Question Answering

arXiv:2601.15236 · cs.CL · Submitted 2026-01-21 · Read on arXiv

cs.CL

Submitted: 2026-01-21

Updated: 2026-08-31

Comments: Published as a conference paper at EMNLP 2026 (Main)

Code: https://github.com/iamshnoo/metadata_localization

License: http://creativecommons.org/licenses/by-sa/4.0/

The gist: Large language models can memorize competing locale-specific facts yet fail to select among them when the locale changes, defaulting instead to a single globally dominant answer.

Terminology

Abstract

Large language models can memorize competing locale-specific facts yet fail to select among them when the locale changes, defaulting instead to a single globally dominant answer. We formalize this as localized knowledge disambiguation and introduce LocalNewsQA, an 18,700-item English-news benchmark that pairs the same question across two locales and scores whether a model actually switches its answer when the locale changes. We also introduce MAPLE, a controlled family of decoder-only models pretrained with document-level geographic metadata (source URL, country, and continent) already present in the training corpus, and compare it to metadata-free controls trained on identical data with the same token budget, architecture, and optimization. In controlled experiments at 1B and 3B, with inference-time metadata fixed, pretraining with metadata in MAPLE produces measurable switching and improves accuracy on questions whose correct answer depends on locale. Ablations and external-benchmark evaluations further suggest that locale-conditioned prediction benefits from geographic provenance learned during pretraining and that these benefits strengthen at larger model sizes.

Related papers