In this paper, we investigate the problem of learning with noisy labels in real-world annotation scenarios, where noise can be categorized into two types: factual noise and ambiguity noise. To better distinguish these noise types and utilize their semantics, we propose a novel sample selection-based approach for noisy label learning, called Proto-semi. Proto-semi initially divides all samples into the confident and unconfident datasets via warm-up. By leveraging the confident dataset, prototype vectors are constructed to capture class characteristics. Subsequently, the distances between the unconfident samples and the prototype vectors are calculated to facilitate noise classification. Based on these distances, the labels are either corrected or retained, resulting in the refinement of the confident and unconfident datasets. Finally, we introduce a semi-supervised learning method to enhance training. Empirical evaluations on a real-world annotated dataset substantiate the robustness of Proto-semi in handling the problem of learning from noisy labels. Meanwhile, the prototype-based repartitioning strategy is shown to be effective in mitigating the adverse impact of label noise. Our code and data are available at https://github.com/fuxiAIlab/ProtoSemi.

Multi-modal search engines have experienced significant growth and widespread use in recent years, making them the second most common internet use. While search engine systems offer a range of services, the image search field has recently become a focal point in the information retrieval community, as the adage goes, "a picture is worth a thousand words". Although popular search engines like Google excel at image search accuracy and agility, there is an ongoing debate over whether their search results can be biased in terms of gender, language, demographics, socio-cultural aspects, and stereotypes. This potential for bias can have a significant impact on individuals' perceptions and influence their perspectives. In this paper, we present our study on bias and fairness in web search, with a focus on keyword-based image search. We first discuss several kinds of biases that exist in search systems and why it is important to mitigate them. We narrow down our study to assessing and mitigating occupational stereotypes in image search, which is a prevalent fairness issue in image retrieval. For the assessment of stereotypes, we take gender as an indicator. We explore various open-source and proprietary APIs for gender identification from images. With these, we examine the extent of gender bias in top-tanked image search results obtained for several occupational keywords. To mitigate the bias, we then propose a fairness-aware re-ranking algorithm that optimizes (a) relevance of the search result with the keyword and (b) fairness w.r.t genders identified. We experiment on 100 top-ranked images obtained for 10 occupational keywords and consider random re-ranking and re-ranking based on relevance as baselines. Our experimental results show that the fairness-aware re-ranking algorithm produces rankings with better fairness scores and competitive relevance scores than the baselines.

Conservation laws are key theoretical and practical tools for understanding, characterizing, and modeling nonlinear dynamical systems. However, for many complex systems, the corresponding conserved quantities are difficult to identify, making it hard to analyze their dynamics and build stable predictive models. Current approaches for discovering conservation laws often depend on detailed dynamical information or rely on black box parametric deep learning methods. We instead reformulate this task as a manifold learning problem and propose a non-parametric approach for discovering conserved quantities. We test this new approach on a variety of physical systems and demonstrate that our method is able to both identify the number of conserved quantities and extract their values. Using tools from optimal transport theory and manifold learning, our proposed method provides a direct geometric approach to identifying conservation laws that is both robust and interpretable without requiring an explicit model of the system nor accurate time information.

Jared Genser in many ways fits a certain Washington, D.C., type. He wears navy suits and keeps his hair cut short. He graduated from a top law school, joined a large firm, and made partner at 40. Eventually, he became disenchanted with big law and started his own boutique practice with offices off--where else--Dupont Circle. What distinguishes Genser from the city's other 50-something lawyers is his unusual clientele: He represents high-value political prisoners.

The performance of large language models (LLMs) has recently improved to the point where the models can perform well on many language tasks. We show here that for the first time, the models can also generate coherent and valid formal analyses of linguistic data and illustrate the vast potential of large language models for analyses of their metalinguistic abilities. LLMs are primarily trained on language data in the form of text; analyzing and evaluating their metalinguistic abilities improves our understanding of their general capabilities and sheds new light on theoretical models in linguistics. In this paper, we probe into GPT-4's metalinguistic capabilities by focusing on three subfields of formal linguistics: syntax, phonology, and semantics. We outline a research program for metalinguistic analyses of large language models, propose experimental designs, provide general guidelines, discuss limitations, and offer future directions for this line of research. This line of inquiry also exemplifies behavioral interpretability of deep learning, where models' representations are accessed by explicit prompting rather than internal representations.

The ActiveAI project addresses key challenges in AI education for grades 7-9 students by providing an engaging AI literacy learning experience based on the AI4K12 knowledge framework. Utilizing learning science mechanisms such as goal-based scenarios, immediate feedback, project-based learning, and intelligent agents, the app incorporates a variety of learner inputs like sliders, steppers, and collectors to enhance understanding. In these courses, students work on real-world scenarios like analyzing sentiment in social media comments. This helps them learn to effectively engage with AI systems and develop their ability to evaluate AI-generated output. The Learning Engineering Process (LEP) guided the project's creation and data instrumentation, focusing on design and impact. The project is currently in the implementation stage, leveraging the intelligent tutor design principles for app development. The extended abstract presents the foundational design and development, with further evaluation and research to be conducted in the future.

Large language models (LLMs) have recently gained popularity. However, the impact of their general availability through ChatGPT on sensitive areas of everyday life, such as education, remains unclear. Nevertheless, the societal impact on established educational methods is already being experienced by both students and educators. Our work focuses on higher physics education and examines problem solving strategies. In a study, students with a background in physics were assigned to solve physics exercises, with one group having access to an internet search engine (N=12) and the other group being allowed to use ChatGPT (N=27). We evaluated their performance, strategies, and interaction with the provided tools. Our results showed that nearly half of the solutions provided with the support of ChatGPT were mistakenly assumed to be correct by the students, indicating that they overly trusted ChatGPT even in their field of expertise. Likewise, in 42% of cases, students used copy & paste to query ChatGPT -- an approach only used in 4% of search engine queries -- highlighting the stark differences in interaction behavior between the groups and indicating limited reflection when using ChatGPT. In our work, we demonstrated a need to (1) guide students on how to interact with LLMs and (2) create awareness of potential shortcomings for users.

Abstract. While the use of location-based augmented reality (AR) for education has demonstrated benefits on participants' motivation, engagement, and on their physical activity, geolocation data inaccuracy causes augmented objects to jitter or drift, which is a factor in downgrading user experience. We developed a free and open source web AR application and conducted a comparative user test (n = 54) in order to assess the impact of geolocation data on usability, exploration, and focus. A control group explored biodiversity in nature using the system in combination with embedded GNSS data, and an experimental group used an external module for RTK data. During the test, eye tracking data, geolocated traces, and in-app user-triggered events were recorded. Participants answered usability questionnaires (SUS, UEQ, HARUS).We found that the geolocation data the RTK group was exposed to was less accurate in average than that of the control group. The RTK group reported lower usability scores on all scales, of which 5 out of 9 were significant, indicating that inaccurate data negatively predicts usability. The GNSS group walked more than the RTK group, indicating a partial effect on exploration. We found no significant effect on interaction time with the screen, indicating no specific relation between data accuracy and focus. While RTK data did not allow us to better the usability of location-based AR interfaces, results allow us to assess our system's overall usability as excellent, and to define optimal operating conditions for future use with pupils.

This paper presents a comprehensive survey of ChatGPT-related (GPT-3.5 and GPT-4) research, state-of-the-art large language models (LLM) from the GPT series, and their prospective applications across diverse domains. Indeed, key innovations such as large-scale pre-training that captures knowledge across the entire world wide web, instruction fine-tuning and Reinforcement Learning from Human Feedback (RLHF) have played significant roles in enhancing LLMs' adaptability and performance. We performed an in-depth analysis of 194 relevant papers on arXiv, encompassing trend analysis, word cloud representation, and distribution analysis across various application domains. The findings reveal a significant and increasing interest in ChatGPT-related research, predominantly centered on direct natural language processing applications, while also demonstrating considerable potential in areas ranging from education and history to mathematics, medicine, and physics. This study endeavors to furnish insights into ChatGPT's capabilities, potential implications, ethical concerns, and offer direction for future advancements in this field.

We propose a new way to assess certain short constructed responses to mathematics items. Our approach uses a pipeline that identifies the key values specified by the student in their response. This allows us to determine the correctness of the response, as well as identify any misconceptions. The information from the value identification pipeline can then be used to provide feedback to the teacher and student. The value identification pipeline consists of two fine-tuned language models. The first model determines if a value is implicit in the student response. The second model identifies where in the response the key value is specified. We consider both a generic model that can be used for any prompt and value, as well as models that are specific to each prompt and value. The value identification pipeline is a more accurate and informative way to assess short constructed responses than traditional rubric-based scoring. It can be used to provide more targeted feedback to students, which can help them improve their understanding of mathematics.