LoFTI: Localization and Factuality Transfer to Indian Locales
This addresses the issue of biased or hallucinated responses in LLMs for users in non-Western regions, but it is incremental as it focuses on evaluation rather than solving the bias.
The authors tackled the problem of geographical bias in large language models (LLMs) by introducing LoFTI, a benchmark for evaluating localization and factual transfer to Indian locales, and found that models like GPT-4 produced skewed results across varying hyperlocality levels.
Large language models (LLMs) encode vast amounts of world knowledge acquired via training on large web-scale datasets crawled from the internet. However, these datasets typically exhibit a geographical bias towards English-speaking Western countries. This results in LLMs producing biased or hallucinated responses to queries that require answers localized to other geographical regions. In this work, we introduce a new benchmark named LoFTI (Localization and Factuality Transfer to Indian Locales) that can be used to evaluate an LLM's localization and factual text transfer capabilities. LoFTI consists of factual statements about entities in source and target locations; the source locations are spread across the globe and the target locations are all within India with varying degrees of hyperlocality (country, states, cities). The entities span a wide variety of categories. We use LoFTI to evaluate Mixtral, GPT-4 and two other Mixtral-based approaches well-suited to the task of localized factual transfer. We demonstrate that LoFTI is a high-quality evaluation benchmark and all the models, including GPT-4, produce skewed results across varying levels of hyperlocality.