In recent years, neural machine translation (NMT) has been widely used in everyday life. However, the current NMT lacks a mechanism to adjust the difficulty level of translations to match the user's language level. Additionally, due to the bias in the training data for NMT, translations of simple source sentences are often produced with complex words. In particular, this could pose a problem for children, who may not be able to understand the meaning of the translations correctly. In this study, we propose a method that replaces words with high Age of Acquisitions (AoA) in translations with simpler words to match the translations to the user's level. We achieve this by using large language models (LLMs), providing a triple of a source sentence, a translation, and a target word to be replaced. We create a benchmark dataset using back-translation on Simple English Wikipedia. The experimental results obtained from the dataset show that our method effectively replaces high-AoA words with lower-AoA words and, moreover, can iteratively replace most of the high-AoA words while still maintaining high BLEU and COMET scores.

Technology does not exist in a vacuum; technological development, media representation, public perception, and governmental regulation cyclically influence each other to produce the collective understanding of a technology's capabilities, utilities, and risks. When these capabilities are overestimated, there is an enhanced risk of subjecting the public to dangerous or harmful technology, artificially restricting research and development directions, and enabling misguided or detrimental policy. The dangers of technological hype are particularly relevant in the rapidly evolving space of AI. Centering the research community as a key player in the development and proliferation of hype, we examine the origins and risks of AI hype to the research community and society more broadly and propose a set of measures that researchers, regulators, and the public can take to mitigate these risks and reduce the prevalence of unfounded claims about the technology.

Recently, federated learning (FL) has achieved wide successes for diverse privacy-sensitive applications without sacrificing the sensitive private information of clients. However, the data quality of client datasets can not be guaranteed since corresponding annotations of different clients often contain complex label noise of varying degrees, which inevitably causes the performance degradation. Intuitively, the performance degradation is dominated by clients with higher noise rates since their trained models contain more misinformation from data, thus it is necessary to devise an effective optimization scheme to mitigate the negative impacts of these noisy clients. In this work, we propose a two-stage framework FedELC to tackle this complicated label noise issue. The first stage aims to guide the detection of noisy clients with higher label noise, while the second stage aims to correct the labels of noisy clients' data via an end-to-end label correction framework which is achieved by learning possible ground-truth labels of noisy clients' datasets via back propagation. We implement sixteen related methods and evaluate five datasets with three types of complicated label noise scenarios for a comprehensive comparison. Extensive experimental results demonstrate our proposed framework achieves superior performance than its counterparts for different scenarios. Additionally, we effectively improve the data quality of detected noisy clients' local datasets with our label correction framework. The code is available at https://github.com/Sprinter1999/FedELC.

Path loss prediction for wireless communications is highly dependent on the local environment. Propagation models including clutter information have been shown to significantly increase model accuracy. This paper explores the application of deep learning to satellite imagery to identify environmental clutter types automatically. Recognizing these clutter types has numerous uses, but our main application is to use clutter information to enhance propagation prediction models. Knowing the type of obstruction (tree, building, and further classifications) can improve the prediction accuracy of key propagation metrics such as path loss.

Typically, a modality is linked to a particular sensor that creates a distinct communication channel, such as sight, speech, and written language. Humans possess a fundamental process in sensory perception that allows them to efficiently engage with the world in dynamic and unconstrained situations by integrating data from several sensory modalities. Each modality functions as a separate source of information that is distinguished by its own specific statistical features. A photograph depicting "elephants playing in the water" delivers visual information through numerous pixels, whereas a similar verbal description conveys this sight using distinct words. Similarly, voice can communicate the same occurrence using spectrograms or speech characteristics. A data conversion AI system must receive input from a specific modality, process, understand, and reproduce its content in a different modality, imitating human-like perception. Modality Conversion (MC) is a broad methodology for constructing artificial intelligence models that can extract and transform information from one modality of representation to another [67]. Amir Eskandari and Aman Anand contributed equally to this research.

Innovations across science and industry are evaluated using randomized trials (i.e., A/B tests). While simple and robust, such static designs are inefficient or infeasible for testing many hypotheses. Adaptive designs can greatly improve statistical power in theory, but they have seen limited adoption due to their fragility in practice. We present a benchmark for adaptive experimentation based on realworld datasets, highlighting prominent practical challenges to operationalizing adaptivity: non-stationarity, batched/delayed feedback, multiple outcomes and objectives, and external validity. Our benchmark aims to spur methodological development that puts practical performance (e.g., robustness) as a central concern, rather than mathematical guarantees on contrived instances. We release an opensource library, AExGym, which is designed with modularity and extensibility in mind to allow experimentation practitioners to develop and benchmark custom environments and algorithms.

Developing questions that are pedagogically sound, relevant, and promote learning is a challenging and time-consuming task for educators. Modern-day large language models (LLMs) generate high-quality content across multiple domains, potentially helping educators to develop high-quality questions. Automated educational question generation (AEQG) is important in scaling online education catering to a diverse student population. Past attempts at AEQG have shown limited abilities to generate questions at higher cognitive levels. In this study, we examine the ability of five state-of-the-art LLMs of different sizes to generate diverse and high-quality questions of different cognitive levels, as defined by Bloom's taxonomy. We use advanced prompting techniques with varying complexity for AEQG. We conducted expert and LLM-based evaluations to assess the linguistic and pedagogical relevance and quality of the questions. Our findings suggest that LLms can generate relevant and high-quality educational questions of different cognitive levels when prompted with adequate information, although there is a significant variance in the performance of the five LLms considered. We also show that automated evaluation is not on par with human evaluation.

The Eye Movements on Machine-Generated Texts Corpus (EMTeC) is a naturalistic eye-movements-while-reading corpus of 107 native English speakers reading machine-generated texts. The texts are generated by three large language models using five different decoding strategies, and they fall into six different text type categories. EMTeC entails the eye movement data at all stages of pre-processing, i.e., the raw coordinate data sampled at 2000 Hz, the fixation sequences, and the reading measures. It further provides both the original and a corrected version of the fixation sequences, accounting for vertical calibration drift. Moreover, the corpus includes the language models' internals that underlie the generation of the stimulus texts: the transition scores, the attention scores, and the hidden states. The stimuli are annotated for a range of linguistic features both at text and at word level. We anticipate EMTeC to be utilized for a variety of use cases such as, but not restricted to, the investigation of reading behavior on machine-generated text and the impact of different decoding strategies; reading behavior on different text types; the development of new pre-processing, data filtering, and drift correction algorithms; the cognitive interpretability and enhancement of language models; and the assessment of the predictive power of surprisal and entropy for human reading times. The data at all stages of pre-processing, the model internals, and the code to reproduce the stimulus generation, data pre-processing and analyses can be accessed via https://github.com/DiLi-Lab/EMTeC/.

Retrieval-augmented language models are being increasingly tasked with subjective, contentious, and conflicting queries such as "is aspartame linked to cancer". To resolve these ambiguous queries, one must search through a large range of websites and consider "which, if any, of this evidence do I find convincing?". In this work, we study how LLMs answer this question. In particular, we construct ConflictingQA, a dataset that pairs controversial queries with a series of real-world evidence documents that contain different facts (e.g., quantitative results), argument styles (e.g., appeals to authority), and answers (Yes or No). We use this dataset to perform sensitivity and counterfactual analyses to explore which text features most affect LLM predictions. Overall, we find that current models rely heavily on the relevance of a website to the query, while largely ignoring stylistic features that humans find important such as whether a text contains scientific references or is written with a neutral tone. Taken together, these results highlight the importance of RAG corpus quality (e.g., the need to filter misinformation), and possibly even a shift in how LLMs are trained to better align with human judgements.

Transformers have revolutionized machine learning, yet their inner workings remain opaque to many. We present Transformer Explainer, an interactive visualization tool designed for non-experts to learn about Transformers through the GPT-2 model. Our tool helps users understand complex Transformer concepts by integrating a model overview and enabling smooth transitions across abstraction levels of mathematical operations and model structures. It runs a live GPT-2 instance locally in the user's browser, empowering users to experiment with their own input and observe in real-time how the internal components and parameters of the Transformer work together to predict the next tokens. Our tool requires no installation or special hardware, broadening the public's education access to modern generative AI techniques. Our open-sourced tool is available at https://poloclub.github.io/transformer-explainer/. A video demo is available at https://youtu.be/ECR4oAwocjs.