Large Language Models (LLMs) have been extensively tuned to mitigate explicit biases, yet they often exhibit subtle implicit biases rooted in their pre-training data. Rather than directly probing LLMs with human-crafted questions that may trigger guardrails, we propose studying how models behave when they proactively ask questions themselves. The 20 Questions game, a multi-turn deduction task, serves as an ideal testbed for this purpose. We systematically evaluate geographic performance disparities in entity deduction using a new dataset, Geo20Q+, consisting of both notable people and culturally significant objects (e.g., foods, landmarks, animals) from diverse regions. We test popular LLMs across two gameplay configurations (canonical 20-question and unlimited turns) and in seven languages (English, Hindi, Mandarin, Japanese, French, Spanish, and Turkish). Our results reveal geographic disparities: LLMs are substantially more successful at deducing entities from the Global North than the Global South, and the Global West than the Global East. While Wikipedia pageviews and pre-training corpus frequency correlate mildly with performance, they fail to fully explain these disparities. Notably, the language in which the game is played has minimal impact on performance gaps. These findings demonstrate the value of creative, free-form evaluation frameworks for uncovering subtle biases in LLMs that remain hidden in standard prompting setups. By analyzing how models initiate and pursue reasoning goals over multiple turns, we find geographic and cultural disparities embedded in their reasoning processes. We release the dataset (Geo20Q+) and code at https://sites.google.com/view/llmbias20q/home.
University of Minnesota, Twin Cities（明尼苏达大学双城分校）；University of Southern California（南加州大学）
Named geographic entities (geo-entities for short) are the building blocks of many geographic datasets. Characterizing geo-entities is integral to various application domains, such as geo-intelligence and map comprehension, while a key challenge is to capture the spatial-varying context of an entity. We hypothesize that we shall know the characteristics of a geo-entity by its surrounding entities, similar to knowing word meanings by their linguistic context. Accordingly, we propose a novel spatial language model, SpaBERT, which provides a general-purpose geo-entity representation based on neig…
Pretrained language models (PLMs) often fail to fairly represent target users from certain world regions because of the under-representation of those regions in training datasets. With recent PLMs trained on enormous data sources, quantifying their potential biases is difficult, due to their black-box nature and the sheer scale of the data sources. In this work, we devise an approach to study the geographic bias (and knowledge) present in PLMs, proposing a Geographic-Representation Probing Framework adopting a self-conditioning method coupled with entity-country mappings. Our findings suggest …
Foundation Models for Geospatial Reasoning: Assessing Capabilities of Large Language Models in Understanding Geometries and Topological Spatial Relations
GeoDS Lab, Department of Geography, University of Wisconsin-Madison, USA（威斯康星大学麦迪逊分校地理系GeoDS实验室）；Department of Geography and Regional Research, University of Vienna, Austria（维也纳大学地理与区域研究系）；Department of Geography, University of California-Santa Barbara, USA（加州大学圣塔芭芭拉分校地理系）
University of Waterloo（滑铁卢大学）；Monash University（莫纳什大学）；Spotzi Canada Ltd（Spotzi加拿大有限公司）
Location tagging, also known as geotagging or geolocation, is the process of assigning geographical coordinates to input data. In this paper we present an algorithm for location tagging of textual documents. Our approach makes use of previous work in natural language processing by using a state-of-the-art part-of-speech tagger and named entity recognizer to find blocks of text which may refer to locations. A knowledge base (OpenStreatMap) is then used to find a list of possible locations for each block. Finally, one location is chosen for each block by assigning distance-based scores to each l…
German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）
We present MobIE, a German-language dataset, which is human-annotated with 20 coarse- and fine-grained entity types and entity linking information for geographically linkable entities. The dataset consists of 3,232 social media texts and traffic reports with 91K tokens, and contains 20.5K annotated entities, 13.1K of which are linked to a knowledge base. A subset of the dataset is human-annotated with seven mobility-related, n-ary relation types, while the remaining documents are annotated using a weakly-supervised labeling approach implemented with the Snorkel framework. To the best of our kn…
With the steady emergence of community question answering (CQA) platforms like Quora, StackExchange, and WikiHow, users now have an unprecedented access to information on various kind of queries and tasks. Moreover, the rapid proliferation and localization of these platforms spanning geographic and linguistic boundaries offer a unique opportunity to study the task requirements and preferences of users in different socio-linguistic groups. In this study, we implement an entity-embedding model trained on a large longitudinal dataset of multi-lingual and task-oriented question-answer pairs to unc…
