相关论文: Temporal Concept Drift and Alignment: An empirical…
In the pursuit of autonomous learning systems, the foundational assumption of stationarity, the premise that data distributions and model behaviors remain constant, is fundamentally untenable. Historically, the research community has…
The society produces textual data online in several ways, e.g., via reviews and social media posts. Therefore, numerous researchers have been working on discovering patterns in textual data that can indicate peoples' opinions, interests,…
While the ability of language models to elicit facts has been widely investigated, how they handle temporally changing facts remains underexplored. We discover Temporal Heads, specific attention heads that primarily handle temporal…
Textual queries are largely employed in information retrieval to let users specify search goals in a natural way. However, differences in user and system terminologies can challenge the identification of the user's information needs, and…
Language change both reflects and shapes social processes, and the semantic evolution of foundational concepts provides a measurable trace of historical and social transformation. Despite recent advances in diachronic semantics and…
Temporal knowledge graph (TKG) reasoning aims to infer future facts at unseen timestamps from temporally evolving entities and relations. Despite recent progress, existing approaches still suffer from inherent limitations due to their…
The rapid growth of scientific publishing has made it increasingly difficult to track how fast-moving areas evolve. Search engines and LLM-based assistants retrieve or summarize papers, but often hide how the corpus was selected, organized,…
Open-domain Timeline Summarization (TLS) is crucial for monitoring the evolution of news topics. To identify changes in news topics, existing methods typically employ general Large Language Models (LLMs) to summarize relevant timestamps…
Descriptive and empirical sciences, such as History, are the sciences that collect, observe and describe phenomena in order to explain them and draw interpretative conclusions about influences, driving forces and impacts under given…
Machine learning models in dynamic environments often suffer from concept drift, where changes in the data distribution degrade performance. While detecting this drift is a well-studied topic, explaining how and why the model's…
Biological memory solves a problem that eludes current AI: storing specific episodic facts without corrupting general semantic knowledge. Complementary Learning Systems theory explains this through two subsystems - a fast hippocampal system…
Automated detection of semantically equivalent questions in longitudinal social science surveys is crucial for long-term studies informing empirical research in the social, economic, and health sciences. Retrieving equivalent questions…
We apply an automatic topic mapping system to records of publications in knowledge organization published between 1988-2008. The data was collected from journals publishing articles in the KO field from Web of Science database (WoS). The…
Released Large Language Models (LLMs) are often paired with a claimed knowledge cutoff date, or the dates at which training data was gathered. Such information is crucial for applications where the LLM must provide up to date information.…
Large Language Models (LLMs) have great potential in the field of health care, yet they face great challenges in adapting to rapidly evolving medical knowledge. This can lead to outdated or contradictory treatment suggestions. This study…
We consider modeling the conception of knowledge in terms of temporal logic. The study of knowledge logical operations is originated around 1962 by representation of knowledge and belief using modalities. Nowadays, it is very good…
Since conventional knowledge embedding models cannot take full advantage of the abundant textual information, there have been extensive research efforts in enhancing knowledge embedding using texts. However, existing enhancement approaches…
The ability to automatically identify whether an entity is referenced in a future context can have multiple applications including decision making, planning and trend forecasting. This paper focuses on detecting implicit future references…
Most real-world knowledge graphs are characterized by a long-tail relation frequency distribution where a significant fraction of relations occurs only a handful of times. This observation has given rise to recent interest in low-shot…
Literature-based knowledge discovery process identifies the important but implicit relations among information embedded in published literature. Existing techniques from Information Retrieval and Natural Language Processing attempt to…