Global rates of mental health concerns are rising and there is increasing realization that existing models of mental healthcare will not adequately expand to meet the demand. With the emergence of large language models (LLMs) has come great optimism regarding their promise to create novel, large-scale solutions to support mental health. Despite their nascence, LLMs have already been applied to mental health-related tasks. In this review, we summarize the extant literature on efforts to use LLMs to provide mental health education, assessment, and intervention and highlight key opportunities for positive impact in each area. We then highlight risks associated with LLMs application to mental health and encourage adoption of strategies to mitigate these risks. The urgent need for mental health support must be balanced with responsible development, testing, and deployment of mental health LLMs. Especially critical is ensuring that mental health LLMs are fine-tuned for mental health, enhance mental health equity, adhere to ethical standards, and that people, including those with lived experience with mental health concerns, are involved in all stages from development through deployment. Prioritizing these efforts will minimize potential harms to mental health and maximize the likelihood that LLMs will positively impact mental health globally.
相關內容
Prediction models are increasingly proposed for guiding treatment decisions, but most fail to address the special role of treatments, leading to inappropriate use. This paper highlights the limitations of using standard prediction models for treatment decision support. We identify `causal blind spots' in three common approaches to handling treatments in prediction modelling: including treatment as a predictor, restricting data based on treatment status and ignoring treatments. When predictions are used to inform treatment decisions, confounders, colliders and mediators, as well as changes in treatment protocols over time may lead to misinformed decision-making. We illustrate potential harmful consequences in several medical applications. We advocate for an extension of guidelines for development, reporting and evaluation of prediction models to ensure that the intended use of the model is matched to an appropriate risk estimand. When prediction models are intended to inform treatment decisions, prediction models should specify upfront the treatment decisions they aim to support and target a prediction estimand in line with that goal. This requires a shift towards developing predictions under the specific treatment options under consideration (`predictions under interventions'). Predictions under interventions need causal reasoning and inference techniques during development and validation. We argue that this will improve the efficacy of prediction models in guiding treatment decisions and prevent potential negative effects on patient outcomes.
We study the properties of a family of distances between functions of a single variable. These distances are examples of integral probability metrics, and have been used previously for comparing probability measures on the line; special cases include the Earth Mover's Distance and the Kolmogorov Metric. We examine their properties for general signals, proving that they are robust to a broad class of deformations. We also establish corresponding robustness results for the induced sliced distances between multivariate functions. Finally, we establish error bounds for approximating the univariate metrics from finite samples, and prove that these approximations are robust to additive Gaussian noise. The results are illustrated in numerical experiments, which include comparisons with Wasserstein distances.
In some causal inference scenarios, the treatment variable is measured inaccurately, for instance in epidemiology or econometrics. Failure to correct for the effect of this measurement error can lead to biased causal effect estimates. Previous research has not studied methods that address this issue from a causal viewpoint while allowing for complex nonlinear dependencies and without assuming access to side information. For such a scenario, this study proposes a model that assumes a continuous treatment variable that is inaccurately measured. Building on existing results for measurement error models, we prove that our model's causal effect estimates are identifiable, even without knowledge of the measurement error variance or other side information. Our method relies on a deep latent variable model in which Gaussian conditionals are parameterized by neural networks, and we develop an amortized importance-weighted variational objective for training the model. Empirical results demonstrate the method's good performance with unknown measurement error. More broadly, our work extends the range of applications in which reliable causal inference can be conducted.
Agent-based models (ABMs) are simulation models used in economics to overcome some of the limitations of traditional frameworks based on general equilibrium assumptions. However, agents within an ABM follow predetermined, not fully rational, behavioural rules which can be cumbersome to design and difficult to justify. Here we leverage multi-agent reinforcement learning (RL) to expand the capabilities of ABMs with the introduction of fully rational agents that learn their policy by interacting with the environment and maximising a reward function. Specifically, we propose a 'Rational macro ABM' (R-MABM) framework by extending a paradigmatic macro ABM from the economic literature. We show that gradually substituting ABM firms in the model with RL agents, trained to maximise profits, allows for a thorough study of the impact of rationality on the economy. We find that RL agents spontaneously learn three distinct strategies for maximising profits, with the optimal strategy depending on the level of market competition and rationality. We also find that RL agents with independent policies, and without the ability to communicate with each other, spontaneously learn to segregate into different strategic groups, thus increasing market power and overall profits. Finally, we find that a higher degree of rationality in the economy always improves the macroeconomic environment as measured by total output, depending on the specific rational policy, this can come at the cost of higher instability. Our R-MABM framework is general, it allows for stable multi-agent learning, and represents a principled and robust direction to extend existing economic simulators.
Supervised machine learning models and public surveillance data has been employed for infectious disease forecasting in many settings. These models leverage various data sources capturing drivers of disease spread, such as climate conditions or human behavior. However, few models have incorporated the organizational structure of different geographic locations for forecasting. Traveling waves of seasonal outbreaks have been reported for dengue, influenza, and other infectious diseases, and many of the drivers of infectious disease dynamics may be shared across different cities, either due to their geographic or socioeconomic proximity. In this study, we developed a machine learning model to predict case counts of four infectious diseases across Brazilian cities one week ahead by incorporating information from related cities. We compared selecting related cities using both geographic distance and GDP per capita. Incorporating information from geographically proximate cities improved predictive performance for two of the four diseases, specifically COVID-19 and Zika. We also discuss the impact on forecasts in the presence of anomalous contagion patterns and the limitations of the proposed methodology.
With the recent success of generative models in image and text, the evaluation of generative models has gained a lot of attention. Whereas most generative models are compared in terms of scalar values such as Frechet Inception Distance (FID) or Inception Score (IS), in the last years (Sajjadi et al., 2018) proposed a definition of precision-recall curve to characterize the closeness of two distributions. Since then, various approaches to precision and recall have seen the light (Kynkaanniemi et al., 2019; Naeem et al., 2020; Park & Kim, 2023). They center their attention on the extreme values of precision and recall, but apart from this fact, their ties are elusive. In this paper, we unify most of these approaches under the same umbrella, relying on the work of (Simon et al., 2019). Doing so, we were able not only to recover entire curves, but also to expose the sources of the accounted pitfalls of the concerned metrics. We also provide consistency results that go well beyond the ones presented in the corresponding literature. Last, we study the different behaviors of the curves obtained experimentally.
Many clinical questions involve estimating the effects of multiple treatments using observational data. When using longitudinal data, the interest is often in the effect of treatment strategies that involve sustaining treatment over time. This requires causal inference methods appropriate for handling multiple treatments and time-dependent confounding. Robins Generalised methods (g-methods) are a family of methods which can deal with time-dependent confounding and some of these have been extended to situations with multiple treatments, although there are currently no studies comparing different methods in this setting. We show how five g-methods (inverse-probability-of-treatment weighted estimation of marginal structural models, g-formula, g-estimation, censoring and weighting, and a sequential trials approach) can be extended to situations with multiple treatments, compare their performances in a simulation study, and demonstrate their application with an example using data from the UK CF Registry.
While neural networks can be approximated by linear models as their width increases, certain properties of wide neural networks cannot be captured by linear models. In this work we show that recently proposed Neural Quadratic Models can exhibit the "catapult phase" [Lewkowycz et al. 2020] that arises when training such models with large learning rates. We then empirically show that the behaviour of neural quadratic models parallels that of neural networks in generalization, especially in the catapult phase regime. Our analysis further demonstrates that quadratic models can be an effective tool for analysis of neural networks.
In large-scale systems there are fundamental challenges when centralised techniques are used for task allocation. The number of interactions is limited by resource constraints such as on computation, storage, and network communication. We can increase scalability by implementing the system as a distributed task-allocation system, sharing tasks across many agents. However, this also increases the resource cost of communications and synchronisation, and is difficult to scale. In this paper we present four algorithms to solve these problems. The combination of these algorithms enable each agent to improve their task allocation strategy through reinforcement learning, while changing how much they explore the system in response to how optimal they believe their current strategy is, given their past experience. We focus on distributed agent systems where the agents' behaviours are constrained by resource usage limits, limiting agents to local rather than system-wide knowledge. We evaluate these algorithms in a simulated environment where agents are given a task composed of multiple subtasks that must be allocated to other agents with differing capabilities, to then carry out those tasks. We also simulate real-life system effects such as networking instability. Our solution is shown to solve the task allocation problem to 6.7% of the theoretical optimal within the system configurations considered. It provides 5x better performance recovery over no-knowledge retention approaches when system connectivity is impacted, and is tested against systems up to 100 agents with less than a 9% impact on the algorithms' performance.
Knowledge graphs (KGs) of real-world facts about entities and their relationships are useful resources for a variety of natural language processing tasks. However, because knowledge graphs are typically incomplete, it is useful to perform knowledge graph completion or link prediction, i.e. predict whether a relationship not in the knowledge graph is likely to be true. This paper serves as a comprehensive survey of embedding models of entities and relationships for knowledge graph completion, summarizing up-to-date experimental results on standard benchmark datasets and pointing out potential future research directions.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191