Related papers: Do Language Models Know the Way to Rome?
Vision-language models (VLMs) have demonstrated strong performance in image geolocation, a capability further sharpened by frontier multimodal large reasoning models (MLRMs). This poses a significant privacy risk, as these widely accessible…
Grammatical features across human languages show intriguing correlations often attributed to learning biases in humans. However, empirical evidence has been limited to experiments with highly simplified artificial languages, and whether…
We investigate the behavior of maps learned by machine translation methods. The maps translate words by projecting between word embedding spaces of different languages. We locally approximate these maps using linear maps, and find that they…
We explore the geospatial reasoning capabilities of Large Language Models (LLMs), specifically, whether LLMs can read road network maps and perform navigation. We frame trajectory recovery as a proxy task, which requires models to…
Factuality is a necessary precursor to useful educational tools. As adoption of Large Language Models (LLMs) in education continues of grow, ensuring correctness in all settings is paramount. Despite their strong English capabilities, LLM…
Language understanding research is held back by a failure to relate language to the physical world it describes and to the social interactions it facilitates. Despite the incredible effectiveness of language processing models to tackle…
Figurative language is a challenge for language models since its interpretation is based on the use of words in a way that deviates from their conventional order and meaning. Yet, humans can easily understand and interpret metaphors,…
Language models (LMs) trained on raw texts have no direct access to the physical world. Gordon and Van Durme (2013) point out that LMs can thus suffer from reporting bias: texts rarely report on common facts, instead focusing on the unusual…
The explosion in the availability of natural language data in the era of social media has given rise to a host of applications such as sentiment analysis and opinion mining. Simultaneously, the growing availability of precise geolocation…
This work analyses the practice of sister city pairing. We investigate structural properties of the resulting city and country networks and present rankings of the most central nodes in these networks. We identify different country clusters…
Cities can be seen as the epitome of complex systems. They arise from a set of interactions and components so diverse that is almost impossible to describe them exhaustively. Amid this diversity, we chose an object which orchestrates the…
Multilingual large language models (LLMs) have minimized the fluency gap between languages. This advancement, however, exposes models to the risk of biased behavior, as knowledge and norms may propagate across languages. In this work, we…
Conversational grounding is a collaborative mechanism for establishing mutual knowledge among participants engaged in a dialogue. This experimental study analyzes information-seeking conversations to investigate the capabilities of large…
If a Large Language Model (LLM) answers "yes" to the question "Are mountains tall?" then does it know what a mountain is? Can you rely on it responding correctly or incorrectly to other questions about mountains? The success of Large…
Transformer-based models are now predominant in NLP. They outperform approaches based on static models in many respects. This success has in turn prompted research that reveals a number of biases in the language models generated by…
Despite significant progress in multimodal language models (LMs), it remains unclear whether visual grounding enhances their understanding of embodied knowledge compared to text-only models. To address this question, we propose a novel…
Language models trained on billions of tokens have recently led to unprecedented results on many NLP tasks. This success raises the question of whether, in principle, a system can ever ``understand'' raw text without access to some form of…
The confluence of recent advances in availability of geospatial information, computing power, and artificial intelligence offers new opportunities to understand how and where our cities differ or are alike. Departing from a traditional…
Much of the knowledge encoded in transformer language models (LMs) may be expressed in terms of relations: relations between words and their synonyms, entities and their attributes, etc. We show that, for a subset of relations, this…
This paper shows that text-only Language Models (LM) can learn to ground spatial relations like "left of" or "below" if they are provided with explicit location information of objects and they are properly trained to leverage those…