Code LLMs are being rapidly deployed and there is evidence that they can make professional programmers more productive. Current benchmarks for code generation measure whether models generate correct programs given an expert prompt. In this paper, we present a new benchmark containing multiple prompts per problem, written by a specific population of non-expert prompters: beginning programmers. StudentEval contains 1,749 prompts for 48 problems, written by 80 students who have only completed one semester of Python programming. Our students wrote these prompts while working interactively with a Code LLM, and we observed very mixed success rates. We use StudentEval to evaluate 5 Code LLMs and find that StudentEval is a better discriminator of model performance than existing benchmarks. We analyze the prompts and find significant variation in students' prompting techniques. We also find that nondeterministic LLM sampling could mislead students into thinking that their prompts are more (or less) effective than they actually are, which has implications for how to teach with Code LLMs.

Word error rate (WER) and character error rate (CER) are standard metrics in Speech Recognition (ASR), but one problem has always been alternative spellings: If one's system transcribes adviser whereas the ground truth has advisor, this will count as an error even though the two spellings really represent the same word. Japanese is notorious for ``lacking orthography'': most words can be spelled in multiple ways, presenting a problem for accurate ASR evaluation. In this paper we propose a new lenient evaluation metric as a more defensible CER measure for Japanese ASR. We create a lattice of plausible respellings of the reference transcription, using a combination of lexical resources, a Japanese text-processing system, and a neural machine translation model for reconstructing kanji from hiragana or katakana. In a manual evaluation, raters rated 95.4% of the proposed spelling variants as plausible. ASR results show that our method, which does not penalize the system for choosing a valid alternate spelling of a word, affords a 2.4%-3.1% absolute reduction in CER depending on the task.

Multi-task learning (MTL) can improve the generalization performance of neural networks by sharing representations with related tasks. Nonetheless, MTL can also degrade performance through harmful interference between tasks. Recent work has pursued task-specific loss weighting as a solution for this interference. However, existing algorithms treat tasks as atomic, lacking the ability to explicitly separate harmful and helpful signals beyond the task level. To this end, we propose SLGrad, a sample-level weighting algorithm for multi-task learning with auxiliary tasks. Through sample-specific task weights, SLGrad reshapes the task distributions during training to eliminate harmful auxiliary signals and augment useful task signals. Substantial generalization performance gains are observed on (semi-) synthetic datasets and common supervised multi-task problems.

Opinion summarisation is a task that aims to condense the information presented in the source documents while retaining the core message and opinions. A summary that only represents the majority opinions will leave the minority opinions unrepresented in the summary. In this paper, we use the stance towards a certain target as an opinion. We study bias in opinion summarisation from the perspective of opinion diversity, which measures whether the model generated summary can cover a diverse set of opinions. In addition, we examine opinion similarity, a measure of how closely related two opinions are in terms of their stance on a given topic, and its relationship with opinion diversity. Through the lens of stances towards a topic, we examine opinion diversity and similarity using three debatable topics under COVID-19. Experimental results on these topics revealed that a higher degree of similarity of opinions did not indicate good diversity or fairly cover the various opinions originally presented in the source documents. We found that BART and ChatGPT can better capture diverse opinions presented in the source documents.

To promote the development of Vision-Language Pre-training (VLP) and multimodal Large Language Model (LLM) in the Chinese community, we firstly release the largest public Chinese high-quality video-language dataset named Youku-mPLUG, which is collected from Youku, a well-known Chinese video-sharing website, with strict criteria of safety, diversity, and quality. Youku-mPLUG contains 10 million Chinese video-text pairs filtered from 400 million raw videos across a wide range of 45 diverse categories for large-scale pre-training. In addition, to facilitate a comprehensive evaluation of video-language models, we carefully build the largest human-annotated Chinese benchmarks covering three popular video-language tasks of cross-modal retrieval, video captioning, and video category classification. Youku-mPLUG can enable researchers to conduct more in-depth multimodal research and develop better applications in the future. Furthermore, we release popular video-language pre-training models, ALPRO and mPLUG-2, and our proposed modularized decoder-only model mPLUG-video pre-trained on Youku-mPLUG. Experiments show that models pre-trained on Youku-mPLUG gain up to 23.1% improvement in video category classification. Besides, mPLUG-video achieves a new state-of-the-art result on these benchmarks with 80.5% top-1 accuracy in video category classification and 68.9 CIDEr score in video captioning, respectively. Finally, we scale up mPLUG-video based on the frozen Bloomz with only 1.7% trainable parameters as Chinese multimodal LLM, and demonstrate impressive instruction and video understanding ability. The zero-shot instruction understanding experiment indicates that pretraining with Youku-mPLUG can enhance the ability to comprehend overall and detailed visual semantics, recognize scene text, and leverage open-domain knowledge.

Solving math story problems is a complex task for students and NLP models alike, requiring them to understand the world as described in the story and reason over it to compute an answer. Recent years have seen impressive performance on automatically solving these problems with large pre-trained language models and innovative techniques to prompt them. However, it remains unclear if these models possess accurate representations of mathematical concepts. This leads to lack of interpretability and trustworthiness which impedes their usefulness in various applications. In this paper, we consolidate previous work on categorizing and representing math story problems and develop MathWorld, which is a graph-based semantic formalism specific for the domain of math story problems. With MathWorld, we can assign world models to math story problems which represent the situations and actions introduced in the text and their mathematical relationships. We combine math story problems from several existing datasets and annotate a corpus of 1,019 problems and 3,204 logical forms with MathWorld. Using this data, we demonstrate the following use cases of MathWorld: (1) prompting language models with synthetically generated question-answer pairs to probe their reasoning and world modeling abilities, and (2) generating new problems by using the world models as a design space.

DCE-MRI provides information about vascular permeability and tissue perfusion through the acquisition of pharmacokinetic parameters. However, traditional methods for estimating these pharmacokinetic parameters involve fitting tracer kinetic models, which often suffer from computational complexity and low accuracy due to noisy arterial input function (AIF) measurements. Although some deep learning approaches have been proposed to tackle these challenges, most existing methods rely on supervised learning that requires paired input DCE-MRI and labeled pharmacokinetic parameter maps. This dependency on labeled data introduces significant time and resource constraints, as well as potential noise in the labels, making supervised learning methods often impractical. To address these limitations, here we present a novel unpaired deep learning method for estimating both pharmacokinetic parameters and the AIF using a physics-driven CycleGAN approach. Our proposed CycleGAN framework is designed based on the underlying physics model, resulting in a simpler architecture with a single generator and discriminator pair. Crucially, our experimental results indicate that our method, which does not necessitate separate AIF measurements, produces more reliable pharmacokinetic parameters than other techniques.

In recent years, there has been an increased focus on early detection, prevention, and prediction of diseases. This, together with advances in sensor technology and the Internet of Things, has led to accelerated efforts in the development of personal health monitoring systems. Semantic technologies have emerged as an effective way to not only deal with the issue of interoperability associated with heterogeneous health sensor data, but also to represent expert health knowledge to support complex reasoning required for decision-making. This study evaluates the state of the art in the use of semantic technologies in sensor-based personal health monitoring systems. Using a systematic approach, a total of 40 systems representing the state of the art in the field are analysed. Through this analysis, six key challenges that such systems must overcome for optimal and effective health monitoring are identified: interoperability, context awareness, situation detection, situation prediction, decision support, and uncertainty handling. The study critically evaluates the extent to which these systems incorporate semantic technologies to deal with these challenges and identifies the prominent architectures, system development and evaluation methodologies that are used. The study provides a comprehensive mapping of the field, identifies inadequacies in the state of the art, and provides recommendations for future research directions.

Available corpora for Argument Mining differ along several axes, and one of the key differences is the presence (or absence) of discourse markers to signal argumentative content. Exploring effective ways to use discourse markers has received wide attention in various discourse parsing tasks, from which it is well-known that discourse markers are strong indicators of discourse relations. To improve the robustness of Argument Mining systems across different genres, we propose to automatically augment a given text with discourse markers such that all relations are explicitly signaled. Our analysis unveils that popular language models taken out-of-the-box fail on this task; however, when fine-tuned on a new heterogeneous dataset that we construct (including synthetic and real examples), they perform considerably better. We demonstrate the impact of our approach on an Argument Mining downstream task, evaluated on different corpora, showing that language models can be trained to automatically fill in discourse markers across different corpora, improving the performance of a downstream model in some, but not all, cases. Our proposed approach can further be employed as an assistive tool for better discourse understanding.

Deploying NMT models on mobile devices is essential for privacy, low latency, and offline scenarios. For high model capacity, NMT models are rather large. Running these models on devices is challenging with limited storage, memory, computation, and power consumption. Existing work either only focuses on a single metric such as FLOPs or general engine which is not good at auto-regressive decoding. In this paper, we present MobileNMT, a system that can translate in 15MB and 30ms on devices. We propose a series of principles for model compression when combined with quantization. Further, we implement an engine that is friendly to INT8 and decoding. With the co-design of model and engine, compared with the existing system, we speed up 47.0x and save 99.5% of memory with only 11.6% loss of BLEU. The code is publicly available at https://github.com/zjersey/Lightseq-ARM.