This study delves into the pervasive issue of gender issues in artificial intelligence (AI), specifically within automatic scoring systems for student-written responses. The primary objective is to investigate the presence of gender biases, disparities, and fairness in generally targeted training samples with mixed-gender datasets in AI scoring outcomes. Utilizing a fine-tuned version of BERT and GPT-3.5, this research analyzes more than 1000 human-graded student responses from male and female participants across six assessment items. The study employs three distinct techniques for bias analysis: Scoring accuracy difference to evaluate bias, mean score gaps by gender (MSG) to evaluate disparity, and Equalized Odds (EO) to evaluate fairness. The results indicate that scoring accuracy for mixed-trained models shows an insignificant difference from either male- or female-trained models, suggesting no significant scoring bias. Consistently with both BERT and GPT-3.5, we found that mixed-trained models generated fewer MSG and non-disparate predictions compared to humans. In contrast, compared to humans, gender-specifically trained models yielded larger MSG, indicating that unbalanced training data may create algorithmic models to enlarge gender disparities. The EO analysis suggests that mixed-trained models generated more fairness outcomes compared with gender-specifically trained models. Collectively, the findings suggest that gender-unbalanced data do not necessarily generate scoring bias but can enlarge gender disparities and reduce scoring fairness.
相關內容
Large Language Models "Ad Referendum": How Good Are They at Machine Translation in the Legal Domain?
This study evaluates the machine translation (MT) quality of two state-of-the-art large language models (LLMs) against a tradition-al neural machine translation (NMT) system across four language pairs in the legal domain. It combines automatic evaluation met-rics (AEMs) and human evaluation (HE) by professional transla-tors to assess translation ranking, fluency and adequacy. The re-sults indicate that while Google Translate generally outperforms LLMs in AEMs, human evaluators rate LLMs, especially GPT-4, comparably or slightly better in terms of producing contextually adequate and fluent translations. This discrepancy suggests LLMs' potential in handling specialized legal terminology and context, highlighting the importance of human evaluation methods in assessing MT quality. The study underscores the evolving capabil-ities of LLMs in specialized domains and calls for reevaluation of traditional AEMs to better capture the nuances of LLM-generated translations.
The value-loading problem is a significant challenge for researchers aiming to create artificial intelligence (AI) systems that align with human values and preferences. This problem requires a method to define and regulate safe and optimal limits of AI behaviors. In this work, we propose HALO (Hormetic ALignment via Opponent processes), a regulatory paradigm that uses hormetic analysis to regulate the behavioral patterns of AI. Behavioral hormesis is a phenomenon where low frequencies of a behavior have beneficial effects, while high frequencies are harmful. By modeling behaviors as allostatic opponent processes, we can use either Behavioral Frequency Response Analysis (BFRA) or Behavioral Count Response Analysis (BCRA) to quantify the hormetic limits of repeatable behaviors. We demonstrate how HALO can solve the 'paperclip maximizer' scenario, a thought experiment where an unregulated AI tasked with making paperclips could end up converting all matter in the universe into paperclips. Our approach may be used to help create an evolving database of 'values' based on the hedonic calculus of repeatable behaviors with decreasing marginal utility. This positions HALO as a promising solution for the value-loading problem, which involves embedding human-aligned values into an AI system, and the weak-to-strong generalization problem, which explores whether weak models can supervise stronger models as they become more intelligent. Hence, HALO opens several research avenues that may lead to the development of a computational value system that allows an AI algorithm to learn whether the decisions it makes are right or wrong.
This research explores the integration of language embeddings for active learning in autonomous driving datasets, with a focus on novelty detection. Novelty arises from unexpected scenarios that autonomous vehicles struggle to navigate, necessitating higher-level reasoning abilities. Our proposed method employs language-based representations to identify novel scenes, emphasizing the dual purpose of safety takeover responses and active learning. The research presents a clustering experiment using Contrastive Language-Image Pretrained (CLIP) embeddings to organize datasets and detect novelties. We find that the proposed algorithm effectively isolates novel scenes from a collection of subsets derived from two real-world driving datasets, one vehicle-mounted and one infrastructure-mounted. From the generated clusters, we further present methods for generating textual explanations of elements which differentiate scenes classified as novel from other scenes in the data pool, presenting qualitative examples from the clustered results. Our results demonstrate the effectiveness of language-driven embeddings in identifying novel elements and generating explanations of data, and we further discuss potential applications in safe takeovers, data curation, and multi-task active learning.
Manipulative design in user interfaces (conceptualized as dark patterns) has emerged as a significant impediment to the ethical design of technology and a threat to user agency and freedom of choice. While previous research focused on exploring these patterns in the context of graphical user interfaces, the impact of speech has largely been overlooked. We conducted a listening test (N = 50) to elicit participants' preferences regarding different synthetic voices that varied in terms of synthesis method (concatenative vs. neural) and prosodic qualities (speech pace and pitch variance), and then evaluated their impact in an online decision-making study (N = 101). Our results indicate a significant effect of voice qualities on the participant's choices, independently from the content of the available options. Our results also indicate that the voice's perceived engagement, ease of understanding, and domain fit directly translate to its impact on participants' behaviour in decision-making tasks.
Context: Free and Open Source Software (FOSS) communities' ability to stay viable and productive over time is pivotal for society as they maintain the building blocks that digital infrastructure, products, and services depend on. Sustainability may, however, be characterized from multiple aspects, and less is known how these aspects interplay and impact community outputs, and software quality specifically. Objective: This study, therefore, aims to empirically explore how the different aspects of FOSS sustainability impact software quality. Method: 16 sustainability metrics across four categories were sampled and applied to a set of 217 OSS projects sourced from the Apache Software Foundation Incubator program. The impact of a decline in the sustainability metrics was analyzed against eight software quality metrics using Bayesian data analysis, which incorporates probability distributions to represent the regression coefficients and intercepts. Results: Findings suggest that selected sustainability metrics do not significantly affect defect density or code coverage. However, a positive impact of community age was observed on specific code quality metrics, such as risk complexity, number of very large files, and code duplication percentage. Interestingly, findings show that even when communities are experiencing sustainability, certain code quality metrics are negatively impacted. Conclusion: Findings imply that code quality practices are not consistently linked to sustainability, and defect management and prevention may be prioritized over the former. Results suggest that growth, resulting in a more complex and large codebase, combined with a probable lack of understanding of code quality standards, may explain the degradation in certain aspects of code quality.
Generalist Large Language Models (LLMs), such as GPT-4, have shown considerable promise in various domains, including medical diagnosis. Rare diseases, affecting approximately 300 million people worldwide, often have unsatisfactory clinical diagnosis rates primarily due to a lack of experienced physicians and the complexity of differentiating among many rare diseases. In this context, recent news such as "ChatGPT correctly diagnosed a 4-year-old's rare disease after 17 doctors failed" underscore LLMs' potential, yet underexplored, role in clinically diagnosing rare diseases. To bridge this research gap, we introduce RareBench, a pioneering benchmark designed to systematically evaluate the capabilities of LLMs on 4 critical dimensions within the realm of rare diseases. Meanwhile, we have compiled the largest open-source dataset on rare disease patients, establishing a benchmark for future studies in this domain. To facilitate differential diagnosis of rare diseases, we develop a dynamic few-shot prompt methodology, leveraging a comprehensive rare disease knowledge graph synthesized from multiple knowledge bases, significantly enhancing LLMs' diagnostic performance. Moreover, we present an exhaustive comparative study of GPT-4's diagnostic capabilities against those of specialist physicians. Our experimental findings underscore the promising potential of integrating LLMs into the clinical diagnostic process for rare diseases. This paves the way for exciting possibilities in future advancements in this field.
Large Language Models (LLMs) create exciting possibilities for powerful language processing tools to accelerate research in materials science. While LLMs have great potential to accelerate materials understanding and discovery, they currently fall short in being practical materials science tools. In this position paper, we show relevant failure cases of LLMs in materials science that reveal current limitations of LLMs related to comprehending and reasoning over complex, interconnected materials science knowledge. Given those shortcomings, we outline a framework for developing Materials Science LLMs (MatSci-LLMs) that are grounded in materials science knowledge and hypothesis generation followed by hypothesis testing. The path to attaining performant MatSci-LLMs rests in large part on building high-quality, multi-modal datasets sourced from scientific literature where various information extraction challenges persist. As such, we describe key materials science information extraction challenges which need to be overcome in order to build large-scale, multi-modal datasets that capture valuable materials science knowledge. Finally, we outline a roadmap for applying future MatSci-LLMs for real-world materials discovery via: 1. Automated Knowledge Base Generation; 2. Automated In-Silico Material Design; and 3. MatSci-LLM Integrated Self-Driving Materials Laboratories.
Believable proxies of human behavior can empower interactive applications ranging from immersive environments to rehearsal spaces for interpersonal communication to prototyping tools. In this paper, we introduce generative agents--computational software agents that simulate believable human behavior. Generative agents wake up, cook breakfast, and head to work; artists paint, while authors write; they form opinions, notice each other, and initiate conversations; they remember and reflect on days past as they plan the next day. To enable generative agents, we describe an architecture that extends a large language model to store a complete record of the agent's experiences using natural language, synthesize those memories over time into higher-level reflections, and retrieve them dynamically to plan behavior. We instantiate generative agents to populate an interactive sandbox environment inspired by The Sims, where end users can interact with a small town of twenty five agents using natural language. In an evaluation, these generative agents produce believable individual and emergent social behaviors: for example, starting with only a single user-specified notion that one agent wants to throw a Valentine's Day party, the agents autonomously spread invitations to the party over the next two days, make new acquaintances, ask each other out on dates to the party, and coordinate to show up for the party together at the right time. We demonstrate through ablation that the components of our agent architecture--observation, planning, and reflection--each contribute critically to the believability of agent behavior. By fusing large language models with computational, interactive agents, this work introduces architectural and interaction patterns for enabling believable simulations of human behavior.
Reinforcement Learning (RL) is a popular machine learning paradigm where intelligent agents interact with the environment to fulfill a long-term goal. Driven by the resurgence of deep learning, Deep RL (DRL) has witnessed great success over a wide spectrum of complex control tasks. Despite the encouraging results achieved, the deep neural network-based backbone is widely deemed as a black box that impedes practitioners to trust and employ trained agents in realistic scenarios where high security and reliability are essential. To alleviate this issue, a large volume of literature devoted to shedding light on the inner workings of the intelligent agents has been proposed, by constructing intrinsic interpretability or post-hoc explainability. In this survey, we provide a comprehensive review of existing works on eXplainable RL (XRL) and introduce a new taxonomy where prior works are clearly categorized into model-explaining, reward-explaining, state-explaining, and task-explaining methods. We also review and highlight RL methods that conversely leverage human knowledge to promote learning efficiency and final performance of agents while this kind of method is often ignored in XRL field. Some open challenges and opportunities in XRL are discussed. This survey intends to provide a high-level summarization and better understanding of XRL and to motivate future research on more effective XRL solutions. Corresponding open source codes are collected and categorized at //github.com/Plankson/awesome-explainable-reinforcement-learning.
Compared with cheap addition operation, multiplication operation is of much higher computation complexity. The widely-used convolutions in deep neural networks are exactly cross-correlation to measure the similarity between input feature and convolution filters, which involves massive multiplications between float values. In this paper, we present adder networks (AdderNets) to trade these massive multiplications in deep neural networks, especially convolutional neural networks (CNNs), for much cheaper additions to reduce computation costs. In AdderNets, we take the $\ell_1$-norm distance between filters and input feature as the output response. The influence of this new similarity measure on the optimization of neural network have been thoroughly analyzed. To achieve a better performance, we develop a special back-propagation approach for AdderNets by investigating the full-precision gradient. We then propose an adaptive learning rate strategy to enhance the training procedure of AdderNets according to the magnitude of each neuron's gradient. As a result, the proposed AdderNets can achieve 74.9% Top-1 accuracy 91.7% Top-5 accuracy using ResNet-50 on the ImageNet dataset without any multiplication in convolution layer.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191