Reproducibility is a major concern across scientific fields. Human-Computer Interaction (HCI), in particular, is subject to diverse reproducibility challenges due to the wide range of research methodologies employed. In this article, we explore how the increasing adoption of Large Language Models (LLMs) across all user experience (UX) design and research activities impacts reproducibility in HCI. In particular, we review upcoming reproducibility challenges through the lenses of analogies from past to future (mis)practices like p-hacking and prompt-hacking, general bias, support in data analysis, documentation and education requirements, and possible pressure on the community. We discuss the risks and chances for each of these lenses with the expectation that a more comprehensive discussion will help shape best practices and contribute to valid and reproducible practices around using LLMs in HCI research.
相關內容
Principal Component Analysis (PCA) is one of the most used tools for extracting low-dimensional representations of data, in particular for time series. Performances are known to strongly depend on the quality (amount of noise) and the quantity of data. We here investigate the impact of heterogeneities, often present in real data, on the reconstruction of low-dimensional trajectories and of their associated modes. We focus in particular on the effects of sample-to-sample fluctuations and of component-dependent temporal convolution and noise in the measurements. We derive analytical predictions for the error on the reconstructed trajectory and the confusion between the modes using the replica method in a high-dimensional setting, in which the number and the dimension of the data are comparable. We find in particular that sample-to-sample variability, is deleterious for the reconstruction of the signal trajectory, but beneficial for the inference of the modes, and that the fluctuations in the temporal convolution kernels prevent perfect recovery of the latent modes even for very weak measurement noise. Our predictions are corroborated by simulations with synthetic data for a variety of control parameters.
The rapid growth of Large Language Models (LLMs) has put forward the study of biases as a crucial field. It is important to assess the influence of different types of biases embedded in LLMs to ensure fair use in sensitive fields. Although there have been extensive works on bias assessment in English, such efforts are rare and scarce for a major language like Bangla. In this work, we examine two types of social biases in LLM generated outputs for Bangla language. Our main contributions in this work are: (1) bias studies on two different social biases for Bangla, (2) a curated dataset for bias measurement benchmarking and (3) testing two different probing techniques for bias detection in the context of Bangla. This is the first work of such kind involving bias assessment of LLMs for Bangla to the best of our knowledge. All our code and resources are publicly available for the progress of bias related research in Bangla NLP.
We consider the computational efficiency of Monte Carlo (MC) and Multilevel Monte Carlo (MLMC) methods applied to partial differential equations with random coefficients. These arise, for example, in groundwater flow modelling, where a commonly used model for the unknown parameter is a random field. We make use of the circulant embedding procedure for sampling from the aforementioned coefficient. To improve the computational complexity of the MLMC estimator in the case of highly oscillatory random fields, we devise and implement a smoothing technique integrated into the circulant embedding method. This allows to choose the coarsest mesh on the first level of MLMC independently of the correlation length of the covariance function of the random field, leading to considerable savings in computational cost. We illustrate this with numerical experiments, where we see a saving of factor 5-10 in computational cost for accuracies of practical interest.
Background: Multiple Sclerosis (MS), an autoimmune disease affecting millions worldwide, is characterized by its variable course, in which some patients will experience a more benign disease course and others a more active one, with the latter leading to permanent neural damage and disability. Methods: This study uses a Markov Chain model to demonstrate the probability of movement across different states on the Expanded Disability Status Scale (EDSS) and attempted to define worsening, improvement, cycling, and stability of these different pathways. Most importantly we were interested in assessing the lack of impermanence of confirmed disability worsening and if it could be estimated from the Markov model. Results: The study identified only 8.1% were considered worsening, 5.6% consistent improving and 86% cyclers and less than 1% consistently stable. More importantly we also found that many (approximately 30%) of participants with confirmed disability worsening (CDW) regressed to stages that were not considered worsening, on subsequent visits after CDW. Conclusions: These finding are similar to what has been reported previously as predictors of worsening, and also for a lack of durability of CDW, but our results suggest that clinical trial endpoints may need to be modified to more accurately capture differences between the treatment and control groups. Further, this suggests that the rate of worsening in trials that use time to CDW are overestimating the extent of CDW. The trials remain valid since the regressing applies to both treatment and control groups, but that the results may be underestimating the treatment benefit due to misclassification.
Engaging in the deliberate generation of abnormal outputs from Large Language Models (LLMs) by attacking them is a novel human activity. This paper presents a thorough exposition of how and why people perform such attacks, defining LLM red-teaming based on extensive and diverse evidence. Using a formal qualitative methodology, we interviewed dozens of practitioners from a broad range of backgrounds, all contributors to this novel work of attempting to cause LLMs to fail. We focused on the research questions of defining LLM red teaming, uncovering the motivations and goals for performing the activity, and characterizing the strategies people use when attacking LLMs. Based on the data, LLM red teaming is defined as a limit-seeking, non-malicious, manual activity, which depends highly on a team-effort and an alchemist mindset. It is highly intrinsically motivated by curiosity, fun, and to some degrees by concerns for various harms of deploying LLMs. We identify a taxonomy of 12 strategies and 35 different techniques of attacking LLMs. These findings are presented as a comprehensive grounded theory of how and why people attack large language models: LLM red teaming.
Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural sciences. Today, AI has started to advance natural sciences by improving, accelerating, and enabling our understanding of natural phenomena at a wide range of spatial and temporal scales, giving rise to a new area of research known as AI for science (AI4Science). Being an emerging research paradigm, AI4Science is unique in that it is an enormous and highly interdisciplinary area. Thus, a unified and technical treatment of this field is needed yet challenging. This work aims to provide a technically thorough account of a subarea of AI4Science; namely, AI for quantum, atomistic, and continuum systems. These areas aim at understanding the physical world from the subatomic (wavefunctions and electron density), atomic (molecules, proteins, materials, and interactions), to macro (fluids, climate, and subsurface) scales and form an important subarea of AI4Science. A unique advantage of focusing on these areas is that they largely share a common set of challenges, thereby allowing a unified and foundational treatment. A key common challenge is how to capture physics first principles, especially symmetries, in natural systems by deep learning methods. We provide an in-depth yet intuitive account of techniques to achieve equivariance to symmetry transformations. We also discuss other common technical challenges, including explainability, out-of-distribution generalization, knowledge transfer with foundation and large language models, and uncertainty quantification. To facilitate learning and education, we provide categorized lists of resources that we found to be useful. We strive to be thorough and unified and hope this initial effort may trigger more community interests and efforts to further advance AI4Science.
Australia is a leading AI nation with strong allies and partnerships. Australia has prioritised robotics, AI, and autonomous systems to develop sovereign capability for the military. Australia commits to Article 36 reviews of all new means and methods of warfare to ensure weapons and weapons systems are operated within acceptable systems of control. Additionally, Australia has undergone significant reviews of the risks of AI to human rights and within intelligence organisations and has committed to producing ethics guidelines and frameworks in Security and Defence. Australia is committed to OECD's values-based principles for the responsible stewardship of trustworthy AI as well as adopting a set of National AI ethics principles. While Australia has not adopted an AI governance framework specifically for Defence; Defence Science has published 'A Method for Ethical AI in Defence' (MEAID) technical report which includes a framework and pragmatic tools for managing ethical and legal risks for military applications of AI.
Recently, Mutual Information (MI) has attracted attention in bounding the generalization error of Deep Neural Networks (DNNs). However, it is intractable to accurately estimate the MI in DNNs, thus most previous works have to relax the MI bound, which in turn weakens the information theoretic explanation for generalization. To address the limitation, this paper introduces a probabilistic representation of DNNs for accurately estimating the MI. Leveraging the proposed MI estimator, we validate the information theoretic explanation for generalization, and derive a tighter generalization bound than the state-of-the-art relaxations.
Deep Learning has implemented a wide range of applications and has become increasingly popular in recent years. The goal of multimodal deep learning is to create models that can process and link information using various modalities. Despite the extensive development made for unimodal learning, it still cannot cover all the aspects of human learning. Multimodal learning helps to understand and analyze better when various senses are engaged in the processing of information. This paper focuses on multiple types of modalities, i.e., image, video, text, audio, body gestures, facial expressions, and physiological signals. Detailed analysis of past and current baseline approaches and an in-depth study of recent advancements in multimodal deep learning applications has been provided. A fine-grained taxonomy of various multimodal deep learning applications is proposed, elaborating on different applications in more depth. Architectures and datasets used in these applications are also discussed, along with their evaluation metrics. Last, main issues are highlighted separately for each domain along with their possible future research directions.
Within the rapidly developing Internet of Things (IoT), numerous and diverse physical devices, Edge devices, Cloud infrastructure, and their quality of service requirements (QoS), need to be represented within a unified specification in order to enable rapid IoT application development, monitoring, and dynamic reconfiguration. But heterogeneities among different configuration knowledge representation models pose limitations for acquisition, discovery and curation of configuration knowledge for coordinated IoT applications. This paper proposes a unified data model to represent IoT resource configuration knowledge artifacts. It also proposes IoT-CANE (Context-Aware recommendatioN systEm) to facilitate incremental knowledge acquisition and declarative context driven knowledge recommendation.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191