Related papers: Time Matters: Examine Temporal Effects on Biomedic…
This article studies the estimation of the causal effect of a time-varying treatment on time-to-an-event or on some other continuously distributed outcome. The paper applies to the situation where treatment is repeatedly adapted to…
Time series data plays a critical role across diverse domains such as healthcare, energy, and finance, where tasks like classification, anomaly detection, and forecasting are essential for informed decision-making. Recently, large language…
Language use changes over time, and this impacts the effectiveness of NLP systems. This phenomenon is even more prevalent in social media data during crisis events where meaning and frequency of word usage may change over the course of…
Transformer-based masked language models such as BERT, trained on general corpora, have shown impressive performance on downstream tasks. It has also been demonstrated that the downstream task performance of such models can be improved by…
Machine learning models deployed in healthcare systems face data drawn from continually evolving environments. However, researchers proposing such models typically evaluate them in a time-agnostic manner, with train and test splits sampling…
In the era of digital healthcare, the huge volumes of textual information generated every day in hospitals constitute an essential but underused asset that could be exploited with task-specific, fine-tuned biomedical language representation…
Large language models (LLMs) can capture rich representations of concepts that are useful for real-world tasks. However, language alone is limited. While existing LLMs excel at text-based inferences, health applications require that models…
In machine learning, temporal shifts occur when there are differences between training and test splits in terms of time. For streaming data such as news or social media, models are commonly trained on a fixed corpus from a certain period of…
The existing methods for evaluating the medical knowledge of Large Language Models (LLMs) are largely based on atemporal examination-style benchmarks, while in reality, medical knowledge is inherently dynamic and continuously evolves as new…
Since the Transformer architecture emerged, language model development has grown, driven by their promising potential. Releasing these models into production requires properly understanding their behavior, particularly in sensitive domains…
Large language models (LLMs) are typically trained on shuffled corpora, yielding models whose knowledge is frozen at train time and whose temporal grounding remains poorly understood. In this work, we study the impact of pre-training…
Effective utilization of time series data is often constrained by the scarcity of data quantity that reflects complex dynamics, especially under the condition of distributional shifts. Existing datasets may not encompass the full range of…
Reasoning about time is of fundamental importance. Many facts are time-dependent. For example, athletes change teams from time to time, and different government officials are elected periodically. Previous time-dependent question answering…
Explanation faithfulness of model predictions in natural language processing is typically evaluated on held-out data from the same temporal distribution as the training data (i.e. synchronous settings). While model performance often…
In research areas with scarce data, representation learning plays a significant role. This work aims to enhance representation learning for clinical time series by deriving universal embeddings for clinical features, such as heart rate and…
In this paper we review an approach to estimating the causal effect of a time-varying treatment on time to some event of interest. This approach is designed for the situation where the treatment may have been repeatedly adapted to patient…
Machine learning (ML) models deployed in healthcare systems must face data drawn from continually evolving environments. However, researchers proposing such models typically evaluate them in a time-agnostic manner, splitting datasets…
Time series foundation models have shown impressive performance on a variety of tasks, across a wide range of domains, even in zero-shot settings. However, most of these models are designed to handle short univariate time series as an…
Using more test-time computation during language model inference, such as generating more intermediate thoughts or sampling multiple candidate answers, has proven effective in significantly improving model performance. This paper takes an…
Pre-trained language models trained on large-scale data have learned serious levels of social biases. Consequently, various methods have been proposed to debias pre-trained models. Debiasing methods need to mitigate only discriminatory bias…