Generative text-to-image models have gained great popularity among the public for their powerful capability to generate high-quality images based on natural language prompts. However, developing effective prompts for desired images can be challenging due to the complexity and ambiguity of natural language. This research proposes PromptMagician, a visual analysis system that helps users explore the image results and refine the input prompts. The backbone of our system is a prompt recommendation model that takes user prompts as input, retrieves similar prompt-image pairs from DiffusionDB, and identifies special (important and relevant) prompt keywords. To facilitate interactive prompt refinement, PromptMagician introduces a multi-level visualization for the cross-modal embedding of the retrieved images and recommended keywords, and supports users in specifying multiple criteria for personalized exploration. Two usage scenarios, a user study, and expert interviews demonstrate the effectiveness and usability of our system, suggesting it facilitates prompt engineering and improves the creativity support of the generative text-to-image model.

ChatGPT is becoming a new reality. In this paper, we show how to distinguish ChatGPT-generated publications from counterparts produced by scientists. Using a newly designed supervised Machine Learning algorithm, we demonstrate how to detect machine-generated publications from those produced by scientists. The algorithm was trained using 100 real publication abstracts, followed by a 10-fold calibration approach to establish a lower-upper bound range of acceptance. In the comparison with ChatGPT content, it was evident that ChatGPT contributed merely 23\% of the bigram content, which is less than 50\% of any of the other 10 calibrating folds. This analysis highlights a significant disparity in technical terms where ChatGPT fell short of matching real science. When categorizing the individual articles, the xFakeBibs algorithm accurately identified 98 out of 100 publications as fake, with 2 articles incorrectly classified as real publications. Though this work introduced an algorithmic approach that detected the ChatGPT-generated fake science with a high degree of accuracy, it remains challenging to detect all fake records. This work is indeed a step in the right direction to counter fake science and misinformation.

The advent of Large Language Models (LLMs), such as OpenAI's ChatGPT, Codex, and GitHub's Copilot, affects the educational landscape at its core, as LLMs offer entirely new possibilities, but also challenges for educators, learners, and institutions. Even though LLMs have only appeared very recently to a broader audience, research has started to address their implications on computing education, particularly programming. The generative potential may be used by educators for the design of new programming tasks [Sa22], or for students to gather formative feedback [Ka23, Zh22]. At the same time, implications for programming pedagogy and assessments are being discussed [Be23, BK23, RTT23], as the lowthreshold availability of LLMs raises new questions with regard to adequate task designs, students' contribution, plagiarism, and ethical conduct. Educators and institutions will soon need to reconsider the design of (formative) assessments. In this context, it is crucial to investigate the capabilities and limitations of LLMs for novice learners of programming, whose challenges have a well-documented history [SS86, Mc01, Lu18].

Building on Papert (1980)'s idea of children talking to computers, we propose ChatLogo, a hybrid natural-programming language interface for agent-based modeling and programming. We build upon previous efforts to scaffold ABM & P learning and recent development in leveraging large language models (LLMs) to support the learning of computational programming. ChatLogo aims to support conversations with computers in a mix of natural and programming languages, provide a more user-friendly interface for novice learners, and keep the technical system from over-reliance on any single LLM. We introduced the main elements of our design: an intelligent command center, and a conversational interface to support creative expression. We discussed the presentation format and future work. Responding to the challenges of supporting open-ended constructionist learning of ABM & P and leveraging LLMs for educational purposes, we contribute to the field by proposing the first constructionist LLM-driven interface to support computational and complex systems thinking.

Large language models (LLMs) have been widely used in various applications but are known to suffer from issues related to untruthfulness and toxicity. While parameter-efficient modules (PEMs) have demonstrated their effectiveness in equipping models with new skills, leveraging PEMs for deficiency unlearning remains underexplored. In this work, we propose a PEMs operation approach, namely Extraction-before-Subtraction (Ext-Sub), to enhance the truthfulness and detoxification of LLMs through the integration of ``expert'' PEM and ``anti-expert'' PEM. Remarkably, even anti-expert PEM possess valuable capabilities due to their proficiency in generating fabricated content, which necessitates language modeling and logical narrative competence. Rather than merely negating the parameters, our approach involves extracting and eliminating solely the deficiency capability within anti-expert PEM while preserving the general capabilities. To evaluate the effectiveness of our approach in terms of truthfulness and detoxification, we conduct extensive experiments on LLMs, encompassing additional abilities such as language modeling and mathematical reasoning. Our empirical results demonstrate that our approach effectively improves truthfulness and detoxification, while largely preserving the fundamental abilities of LLMs.

When deploying machine learning models in production for any product/application, there are three properties that are commonly desired. First, the models should be generalizable, in that we can extend it to further use cases as our knowledge of the domain area develops. Second they should be evaluable, so that there are clear metrics for performance and the calculation of those metrics in production settings are feasible. Finally, the deployment should be cost-optimal as far as possible. In this paper we propose that these three objectives (i.e. generalization, evaluation and cost-optimality) can often be relatively orthogonal and that for large language models, despite their performance over conventional NLP models, enterprises need to carefully assess all the three factors before making substantial investments in this technology. We propose a framework for generalization, evaluation and cost-modeling specifically tailored to large language models, offering insights into the intricacies of development, deployment and management for these large language models.

State-of-the-art automated test generation techniques, such as search-based testing, are usually ignorant about what a developer would create as a test case. Therefore, they typically create tests that are not human-readable and may not necessarily detect all types of complex bugs developer-written tests would do. In this study, we leverage Transformer-based code models to generate unit tests that can complement search-based test generation. Specifically, we use CodeT5, i.e., a state-of-the-art large code model, and fine-tune it on the test generation downstream task. For our analysis, we use the Methods2test dataset for fine-tuning CodeT5 and Defects4j for project-level domain adaptation and evaluation. The main contribution of this study is proposing a fully automated testing framework that leverages developer-written tests and available code models to generate compilable, human-readable unit tests. Results show that our approach can generate new test cases that cover lines that were not covered by developer-written tests. Using domain adaptation, we can also increase line coverage of the model-generated unit tests by 49.9% and 54% in terms of mean and median (compared to the model without domain adaptation). We can also use our framework as a complementary solution alongside common search-based methods to increase the overall coverage with mean and median of 25.3% and 6.3%. It can also increase the mutation score of search-based methods by killing extra mutants (up to 64 new mutants were killed per project in our experiments).

The recent proliferation of research into transformer based natural language processing has led to a number of studies which attempt to detect the presence of human-like cognitive behavior in the models. We contend that, as is true of human psychology, the investigation of cognitive behavior in language models must be conducted in an appropriate population of an appropriate size for the results to be meaningful. We leverage work in uncertainty estimation in a novel approach to efficiently construct experimental populations. The resultant tool, PopulationLM, has been made open source. We provide theoretical grounding in the uncertainty estimation literature and motivation from current cognitive work regarding language models. We discuss the methodological lessons from other scientific communities and attempt to demonstrate their application to two artificial population studies. Through population based experimentation we find that language models exhibit behavior consistent with typicality effects among categories highly represented in training. However, we find that language models don't tend to exhibit structural priming effects. Generally, our results show that single models tend to over estimate the presence of cognitive behaviors in neural models.

Personalized text generation is an emerging research area that has attracted much attention in recent years. Most studies in this direction focus on a particular domain by designing bespoke features or models. In this work, we propose a general approach for personalized text generation using large language models (LLMs). Inspired by the practice of writing education, we develop a multistage and multitask framework to teach LLMs for personalized generation. In writing instruction, the task of writing from sources is often decomposed into multiple steps that involve finding, evaluating, summarizing, synthesizing, and integrating information. Analogously, our approach to personalized text generation consists of multiple stages: retrieval, ranking, summarization, synthesis, and generation. In addition, we introduce a multitask setting that helps the model improve its generation ability further, which is inspired by the observation in education that a student's reading proficiency and writing ability are often correlated. We evaluate our approach on three public datasets, each of which covers a different and representative domain. Our results show significant improvements over a variety of baselines.

We investigate the emergent abilities of the recently proposed web-scale speech model Whisper, by adapting it to unseen tasks with prompt engineering. We selected three tasks: audio-visual speech recognition (AVSR), code-switched speech recognition (CS-ASR), and speech translation (ST) on unseen language pairs. We design task-specific prompts, by either leveraging another large-scale model, or simply manipulating the special tokens in the default prompts. Experiments show that compared to the default prompts, our proposed prompts improve performance by 10% to 45% on the three zero-shot tasks, and even outperform SotA supervised models on some datasets. In addition, our experiments reveal many interesting properties of Whisper, including its robustness to prompts, bias on accents, and the multilingual understanding in its latent space. Code is available at https://github.com/jasonppy/PromptingWhisper