For the past few months, Morten Blichfeldt Andersen has spent many hours scouring OpenAI's GPT Store. Since it launched in January, the marketplace for bespoke bots has filled up with a deep bench of useful and sometimes quirky AI tools. Cartoon generators spin up New Yorker–style illustrations and vivid anime stills. Programming and writing assistants offer shortcuts for crafting code and prose. There's also a color analysis bot, a spider identifier, and a dating coach called RizzGPT.

Can LLMs continually improve their previous outputs for better results? An affirmative answer would require LLMs to be better at discriminating among previously-generated alternatives, than generating initial responses. We explore the validity of this hypothesis in practice. We first introduce a unified framework that allows us to compare the generative and discriminative capability of any model on any task. Then, in our resulting experimental analysis of several LLMs, we do not observe the performance of those models on discrimination to be reliably better than generation. We hope these findings inform the growing literature on self-improvement AI systems.

We develop a principled procedure for determining when a large language model (LLM) should abstain from responding (e.g., by saying "I don't know") in a general domain, instead of resorting to possibly "hallucinating" a non-sensical or incorrect answer. Building on earlier approaches that use self-consistency as a more reliable measure of model confidence, we propose using the LLM itself to self-evaluate the similarity between each of its sampled responses for a given query. We then further leverage conformal prediction techniques to develop an abstention procedure that benefits from rigorous theoretical guarantees on the hallucination rate (error rate). Experimentally, our resulting conformal abstention method reliably bounds the hallucination rate on various closed-book, open-domain generative question answering datasets, while also maintaining a significantly less conservative abstention rate on a dataset with long responses (Temporal Sequences) compared to baselines using log-probability scores to quantify uncertainty, while achieveing comparable performance on a dataset with short answers (TriviaQA). To evaluate the experiments automatically, one needs to determine if two responses are equivalent given a question. Following standard practice, we use a thresholded similarity function to determine if two responses match, but also provide a method for calibrating the threshold based on conformal prediction, with theoretical guarantees on the accuracy of the match prediction, which might be of independent interest.

Requirements elicitation, a critical, yet time-consuming and challenging step in product development, often fails to capture the full spectrum of user needs. This may lead to products that fall short of expectations. This paper introduces a novel framework that leverages Large Language Models (LLMs) to automate and enhance the requirements elicitation process. LLMs are used to generate a vast array of simulated users (LLM agents), enabling the exploration of a much broader range of user needs and unforeseen use cases. These agents engage in product experience scenarios, through explaining their actions, observations, and challenges. Subsequent agent interviews and analysis uncover valuable user needs, including latent ones. We validate our framework with three experiments. First, we explore different methodologies for diverse agent generation, discussing their advantages and shortcomings. We measure the diversity of identified user needs and demonstrate that context-aware agent generation leads to greater diversity. Second, we show how our framework effectively mimics empathic lead user interviews, identifying a greater number of latent needs than conventional human interviews. Third, we showcase that LLMs can be used to analyze interviews, capture needs, and classify them as latent or not. Our work highlights the potential of using LLM agents to accelerate early-stage product development, reduce costs, and increase innovation.

The 2023 AI4EIC hackathon was the culmination of the third annual AI4EIC workshop at The Catholic University of America. This workshop brought together researchers from physics, data science and computer science to discuss the latest developments in Artificial Intelligence (AI) and Machine Learning (ML) for the Electron Ion Collider (EIC), including applications for detectors, accelerators, and experimental control. The hackathon, held on the final day of the workshop, involved using a chatbot powered by a Large Language Model, ChatGPT-3.5, to train a binary classifier neutrons and photons in simulated data from the \textsc{GlueX} Barrel Calorimeter. In total, six teams of up to four participants from all over the world took part in this intense educational and research event. This article highlights the hackathon challenge, the resources and methodology used, and the results and insights gained from analyzing physics data using the most cutting-edge tools in AI/ML.

Intelligent tutoring systems (ITSs) that imitate human tutors and aim to provide immediate and customized instructions or feedback to learners have shown their effectiveness in education. With the emergence of generative artificial intelligence, large language models (LLMs) further entitle the systems to complex and coherent conversational interactions. These systems would be of great help in language education as it involves developing skills in communication, which, however, drew relatively less attention. Additionally, due to the complicated cognitive development at younger ages, more endeavors are needed for practical uses. Scaffolding refers to a teaching technique where teachers provide support and guidance to students for learning and developing new concepts or skills. It is an effective way to support diverse learning needs, goals, processes, and outcomes. In this work, we investigate how pedagogical instructions facilitate the scaffolding in ITSs, by conducting a case study on guiding children to describe images for language learning. We construct different types of scaffolding tutoring systems grounded in four fundamental learning theories: knowledge construction, inquiry-based learning, dialogic teaching, and zone of proximal development. For qualitative and quantitative analyses, we build and refine a seven-dimension rubric to evaluate the scaffolding process. In our experiment on GPT-4V, we observe that LLMs demonstrate strong potential to follow pedagogical instructions and achieve self-paced learning in different student groups. Moreover, we extend our evaluation framework from a manual to an automated approach, paving the way to benchmark various conversational tutoring systems.

We present insightful results of a survey on the adoption of generative artificial intelligence (GenAI) by university teachers in their teaching activities. The transformation of education by GenAI, particularly large language models (LLMs), has been presenting both opportunities and challenges, including cheating by students. We prepared the online survey according to best practices and the questions were created by the authors, who have pedagogy experience. The survey contained 12 questions and a pilot study was first conducted. The survey was then sent to all teachers in multiple departments across different campuses of the university of interest in Sweden: Lule{\aa} University of Technology. The survey was available in both Swedish and English. The results show that 35 teachers (more than half) use GenAI out of 67 respondents. Preparation is the teaching activity with the most frequency that GenAI is used for and ChatGPT is the most commonly used GenAI. 59% say it has impacted their teaching, however, 55% say there should be legislation around the use of GenAI, especially as inaccuracies and cheating are the biggest concerns.

Exemplar-Free Class Incremental Learning is a highly challenging setting where replay memory is unavailable. Methods relying on frozen feature extractors have drawn attention recently in this setting due to their impressive performances and lower computational costs. However, those methods are highly dependent on the data used to train the feature extractor and may struggle when an insufficient amount of classes are available during the first incremental step. To overcome this limitation, we propose to use a pre-trained text-to-image diffusion model in order to generate synthetic images of future classes and use them to train the feature extractor. Experiments on the standard benchmarks CIFAR100 and ImageNet-Subset demonstrate that our proposed method can be used to improve state-of-the-art methods for exemplar-free class incremental learning, especially in the most difficult settings where the first incremental step only contains few classes. Moreover, we show that using synthetic samples of future classes achieves higher performance than using real data from different classes, paving the way for better and less costly pre-training methods for incremental learning.

We describe the University of Amsterdam Intelligent Data Engineering Lab team's entry for the SemEval-2024 Task 6 competition. The SHROOM-INDElab system builds on previous work on using prompt programming and in-context learning with large language models (LLMs) to build classifiers for hallucination detection, and extends that work through the incorporation of context-specific definition of task, role, and target concept, and automated generation of examples for use in a few-shot prompting approach. The resulting system achieved fourth-best and sixth-best performance in the model-agnostic track and model-aware tracks for Task 6, respectively, and evaluation using the validation sets showed that the system's classification decisions were consistent with those of the crowd-sourced human labellers. We further found that a zero-shot approach provided better accuracy than a few-shot approach using automatically generated examples. Code for the system described in this paper is available on Github.

We present Sailor, a family of open language models ranging from 0.5B to 7B parameters, tailored for South-East Asian (SEA) languages. These models are continually pre-trained from Qwen1.5, a great language model for multilingual use cases. From Qwen1.5, Sailor models accept 200B to 400B tokens, primarily covering the languages of English, Chinese, Vietnamese, Thai, Indonesian, Malay, and Lao. The training leverages several techniques, including BPE dropout for improving the model robustness, aggressive data cleaning and deduplication, and small proxy models to optimize data mixture. Experimental results on four typical tasks indicate that Sailor models demonstrate strong performance across different benchmarks, including commonsense reasoning, question answering, reading comprehension and examination. Embracing the open-source spirit, we share our insights through this report to spark a wider interest in developing large language models for multilingual use cases.