With its most recent update, Google Bard can now sort through your trove of Google Docs, rediscover ancient Gmail messages, and search through every video on YouTube. Before experimenting too much with the new extensions available for Google's chatbot, it's worth going over the steps you can take to protect your privacy (and the ones you can't). Google Bard launched in March of this year, one month after OpenAI released ChatGPT to the public. You're likely familiar with how chatbots are designed to mimic human conversation, but Google's latest features are designed to give Bard more practical applications and uses. But when every conversation you have with Bard is tracked, logged, and used again to train the AI, how can you trust it with your data?

Recent advancements in artificial intelligence (AI) are fundamentally reshaping computing, with large language models (LLMs) now effectively being able to generate and interpret source code and natural language instructions. These emergent capabilities have sparked urgent questions in the computing education community around how educators should adapt their pedagogy to address the challenges and to leverage the opportunities presented by this new technology. In this working group report, we undertake a comprehensive exploration of LLMs in the context of computing education and make five significant contributions. First, we provide a detailed review of the literature on LLMs in computing education and synthesise findings from 71 primary articles. Second, we report the findings of a survey of computing students and instructors from across 20 countries, capturing prevailing attitudes towards LLMs and their use in computing education contexts. Third, to understand how pedagogy is already changing, we offer insights collected from in-depth interviews with 22 computing educators from five continents who have already adapted their curricula and assessments. Fourth, we use the ACM Code of Ethics to frame a discussion of ethical issues raised by the use of large language models in computing education, and we provide concrete advice for policy makers, educators, and students. Finally, we benchmark the performance of LLMs on various computing education datasets, and highlight the extent to which the capabilities of current models are rapidly improving. Our aim is that this report will serve as a focal point for both researchers and practitioners who are exploring, adapting, using, and evaluating LLMs and LLM-based tools in computing classrooms.

Recent advancements in technology have necessitated a paradigm shift in the people use technology necessitating a new research field called Human-Machine collaboration. ChatGPT, an Artificial intelligence (AI) assistive technology, has gained mainstream adoption and implementation in academia and industry; however, a lot is left unknown about how this new technology holds for Human-Machine Collaboration in Africa. Our survey paper highlights to answer some of these questions. To understand the effectiveness of ChatGPT on human-machine collaboration we utilized reflexive thematic analysis to analyze (N= 51) articles between 2019 and 2023 obtained from our literature search. Our findings indicate the prevalence of ChatGPT for human-computer interaction within academic sectors such as education, and research; trends also revealed the relatively high effectiveness of ChatGPT in improving human-machine collaboration.

Data contamination, i.e., the presence of test data from downstream tasks in the training data of large language models (LLMs), is a potential major issue in measuring LLMs' real effectiveness on other tasks. We propose a straightforward yet effective method for identifying data contamination within LLMs. At its core, our approach starts by identifying potential contamination at the instance level; using this information, our approach then assesses wider contamination at the partition level. To estimate contamination of individual instances, we employ "guided instruction:" a prompt consisting of the dataset name, partition type, and the random-length initial segment of a reference instance, asking the LLM to complete it. An instance is flagged as contaminated if the LLM's output either exactly or nearly matches the latter segment of the reference. To understand if an entire partition is contaminated, we propose two ideas. The first idea marks a dataset partition as contaminated if the average overlap score with the reference instances (as measured by ROUGE-L or BLEURT) is statistically significantly better with the completions from guided instruction compared to a "general instruction" that does not include the dataset and partition name. The second idea marks a dataset partition as contaminated if a classifier based on GPT-4 with few-shot in-context learning prompt marks multiple generated completions as exact/near-exact matches of the corresponding reference instances. Our best method achieves an accuracy between 92% and 100% in detecting if an LLM is contaminated with seven datasets, containing train and test/validation partitions, when contrasted with manual evaluation by human experts. Further, our findings indicate that GPT-4 is contaminated with AG News, WNLI, and XSum datasets.

Large language models (LLMs) have shown remarkable instruction-following capabilities and achieved impressive performances in various applications. However, the performances of LLMs depend heavily on the instructions given to them, which are typically manually tuned with substantial human efforts. Recent work has used the query-efficient Bayesian optimization (BO) algorithm to automatically optimize the instructions given to black-box LLMs. However, BO usually falls short when optimizing highly sophisticated (e.g., high-dimensional) objective functions, such as the functions mapping an instruction to the performance of an LLM. This is mainly due to the limited expressive power of the Gaussian process (GP) model which is used by BO as a surrogate to model the objective function. Meanwhile, it has been repeatedly shown that neural networks (NNs), especially pre-trained transformers, possess strong expressive power and can model highly complex functions. So, we adopt a neural bandit algorithm which replaces the GP in BO by an NN surrogate to optimize instructions for black-box LLMs. More importantly, the neural bandit algorithm allows us to naturally couple the NN surrogate with the hidden representation learned by a pre-trained transformer (i.e., an open-source LLM), which significantly boosts its performance. These motivate us to propose our INSTruction optimization usIng Neural bandits Coupled with Transformers} (INSTINCT) algorithm. We perform instruction optimization for ChatGPT and use extensive experiments to show that our INSTINCT consistently outperforms the existing methods in different tasks, such as in various instruction induction tasks and the task of improving the zero-shot chain-of-thought instruction.

Large Language Models (LLMs) are showcasing impressive ability in handling complex reasoning tasks. In real-world situations, problems often span a spectrum of complexities. Humans inherently adjust their problem-solving approaches based on task complexity. However, most methodologies that leverage LLMs tend to adopt a uniform approach: utilizing consistent models, prompting methods, and degrees of problem decomposition, regardless of the problem complexity. Inflexibility of them can bring unnecessary computational overhead or sub-optimal performance. To address this problem, we introduce an Adaptive-Solver framework. It strategically modulates solving strategies based on the difficulties of the problems. Given an initial solution, the framework functions with two primary modules. The initial evaluation module assesses the adequacy of the current solution. If improvements are needed, the subsequent adaptation module comes into play. Within this module, three key adaptation strategies are employed: (1) Model Adaptation: Switching to a stronger LLM when a weaker variant is inadequate. (2) Prompting Method Adaptation: Alternating between different prompting techniques to suit the problem's nuances. (3) Decomposition Granularity Adaptation: Breaking down a complex problem into more fine-grained sub-questions to enhance solvability. Through such dynamic adaptations, our framework not only enhances computational efficiency but also elevates the overall performance. This dual-benefit ensures both the efficiency of the system for simpler tasks and the precision required for more complex questions. Experimental results from complex reasoning tasks reveal that the prompting method adaptation and decomposition granularity adaptation enhance performance across all tasks. Furthermore, the model adaptation approach significantly reduces API costs (up to 50%) while maintaining superior performance.

In this study, we use the existing Large Language Models ENnhanced to See Framework (LENS Framework) to test the feasibility of multimodal task-oriented dialogues. The LENS Framework has been proposed as a method to solve computer vision tasks without additional training and with fixed parameters of pre-trained models. We used the Multimodal Dialogs (MMD) dataset, a multimodal task-oriented dialogue benchmark dataset from the fashion field, and for the evaluation, we used the ChatGPT-based G-EVAL, which only accepts textual modalities, with arrangements to handle multimodal data. Compared to Transformer-based models in previous studies, our method demonstrated an absolute lift of 10.8% in fluency, 8.8% in usefulness, and 5.2% in relevance and coherence. The results show that using large-scale models with fixed parameters rather than using models trained on a dataset from scratch improves performance in multimodal task-oriented dialogues. At the same time, we show that Large Language Models (LLMs) are effective for multimodal task-oriented dialogues. This is expected to lead to efficient applications to existing systems.

In recent years, large language models (LLMs) have achieved remarkable performances in various NLP tasks. They can generate texts that are indistinguishable from those written by humans. Such remarkable performance of LLMs increases their risk of being used for malicious purposes, such as generating fake news articles. Therefore, it is necessary to develop methods for distinguishing texts written by LLMs from those written by humans. Watermarking is one of the most powerful methods for achieving this. Although existing watermarking methods have successfully detected texts generated by LLMs, they significantly degrade the quality of the generated texts. In this study, we propose the Necessary and Sufficient Watermark (NS-Watermark) for inserting watermarks into generated texts without degrading the text quality. More specifically, we derive minimum constraints required to be imposed on the generated texts to distinguish whether LLMs or humans write the texts. Then, we formulate the NS-Watermark as a constrained optimization problem and propose an efficient algorithm to solve it. Through the experiments, we demonstrate that the NS-Watermark can generate more natural texts than existing watermarking methods and distinguish more accurately between texts written by LLMs and those written by humans. Especially in machine translation tasks, the NS-Watermark can outperform the existing watermarking method by up to 30 BLEU scores. Large language models (LLMs) have achieved remarkable performances in a wide range of NLP tasks, including language generation (Chen et al., 2021), question answering (Joshi et al., 2017; Kwiatkowski et al., 2019), and reasoning tasks (Bisk et al., 2020; Kojima et al., 2022). Recently, many pre-trained LLMs have been released (Brown et al., 2020; Chung et al., 2022; Zhang et al., 2022; Touvron et al., 2023), which can now generate natural and fluent texts that are indistinguishable from texts written by humans.

Translation of natural language into syntactically correct commands for data visualization is an important application of natural language models and could be leveraged to many different tasks. A closely related effort is the task of translating natural languages into SQL queries, which in turn could be translated into visualization with additional information from the natural language query supplied[1]. Contributing to the progress in this area of research, we built natural language translation models to construct simplified versions of data and visualization queries in a language called Vega Zero first proposed by Luo, Yuyu, et al[2]. In this paper, we explore the design and performance of these sequence to sequence transformer based machine learning model architectures using large language models such as BERT as encoders to predict visualization commands from natural language queries, as well as apply available T5 sequence to sequence models to the problem for comparison.

Aligning large language models (LLMs) with human preferences is essential for safe and useful LLMs. Previous works mainly adopt reinforcement learning (RLHF) and direct preference optimization (DPO) with human feedback for alignment. Nevertheless, they have certain drawbacks. One such limitation is that they can only align models with one preference at the training time (e.g., they cannot learn to generate concise responses when the preference data prefers detailed responses), or have certain constraints for the data format (e.g., DPO only supports pairwise preference data). To this end, prior works incorporate controllable generations for alignment to make language models learn multiple preferences and provide outputs with different preferences during inference if asked. Controllable generation also offers more flexibility with regard to data format (e.g., it supports pointwise preference data). Specifically, it uses different control tokens for different preferences during training and inference, making LLMs behave differently when required. Current controllable generation methods either use a special token or hand-crafted prompts as control tokens, and optimize them together with LLMs. As control tokens are typically much lighter than LLMs, this optimization strategy may not effectively optimize control tokens. To this end, we first use parameter-efficient tuning (e.g., prompting tuning and low-rank adaptation) to optimize control tokens and then fine-tune models for controllable generations, similar to prior works. Our approach, alignMEnt with parameter-Efficient Tuning (MEET), improves the quality of control tokens, thus improving controllable generation quality consistently by an apparent margin on two well-recognized datasets compared with prior works.