Related papers: The challenges of temporal alignment on Twitter du…
A key question of collective social behavior is related to the influence of Mass Media on public opinion. Different approaches have been developed to address quantitatively this issue, ranging from field experiments to mathematical models.…
Most words have several senses and connotations which evolve in time due to semantic shift, so that closely related words may gain different or even opposite meanings over the years. This evolution is very relevant to the study of language…
Large Language Models (LLMs) exhibit catastrophic performance degradation when processing contexts approaching certain critical thresholds, even when information remains relevant. This intelligence degradation-defined as over 30% drop in…
Humans adjust their linguistic style to the audience they are addressing. However, the extent to which LLMs adapt to different social contexts is largely unknown. As these models increasingly mediate human-to-human communication, their…
Fine-tuning large language models (LLMs) with limited data poses a practical challenge in low-resource languages, specialized domains, and constrained deployment settings. While pre-trained LLMs provide strong foundations, effective…
Recent attempts to support high-level scene interpretation and planning in Autonomous Vehicles (AVs) using ensembles of Large Language Models (LLMs) and Large Multimodal Models (LMMs) continue to treat time as a secondary property. This…
Various domain users are increasingly leveraging real-time social media data to gain rapid situational awareness. However, due to the high noise in the deluge of data, effectively determining semantically relevant information can be…
While recent language models have the ability to take long contexts as input, relatively little is known about how well they use longer context. We analyze the performance of language models on two tasks that require identifying relevant…
Identifying changes in individuals' behaviour and mood, as observed via content shared on online platforms, is increasingly gaining importance. Most research to-date on this topic focuses on either: (a) identifying individuals at risk or…
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…
Online social networks are increasingly being utilized for collective sense making and information processing in disasters. However, the underlying mechanisms that shape the dynamics of collective intelligence in online social networks…
Language models (LMs) are trained on web text originating from many points in time and, in general, without any explicit temporal grounding. This work investigates the temporal chaos of pretrained LMs and explores various methods to align…
The spread of online hate has become a significant problem for newspapers that host comment sections. As a result, there is growing interest in using machine learning and natural language processing for (semi-) automated abusive language…
Language evolves over time in many ways relevant to natural language processing tasks. For example, recent occurrences of tokens 'BERT' and 'ELMO' in publications refer to neural network architectures rather than persons. This type of…
Multilingual Large Language Models considerably changed how technologies influence language. While previous technologies could mediate or assist humans, there is now a tendency to offload the task of writing itself to these technologies,…
How does the natural evolution of context paragraphs affect question answering in generative Large Language Models (LLMs)? To investigate this, we propose a framework for curating naturally evolved, human-edited variants of reading passages…
Social media platforms such as Twitter (now X) provide rich data for analyzing public discourse, especially during crises such as the COVID-19 pandemic. However, the brevity, informality, and noise of social media short texts often hinder…
Networked environments shape how information embedded in narratives influences individual and group beliefs and behavior. This raises key questions about how group communication around narrative media impacts belief formation and how such…
People nowadays express their opinions in online spaces, using different forms of interactions such as posting, sharing and discussing with one another. How do these digital traces change in response to events happening in the real world?…
Domain adaptation is important in sentiment analysis as sentiment-indicating words vary between domains. Recently, multi-domain adaptation has become more pervasive, but existing approaches train on all available source domains including…