Large language models (LLMs) excel in zero-shot abstractive summarization tasks, delivering fluent and pertinent summaries. Recent advancements have extended their capabilities to handle long-input contexts, surpassing token limits of 100k. However, in the realm of multi-document question answering, language models exhibit uneven utilization of their input context. They tend to favor the initial and final segments, resulting in a U-shaped performance pattern concerning where the answer is located within the input. This bias raises concerns, particularly in summarization tasks where crucial content may be dispersed throughout the source document(s). This paper presents a comprehensive investigation encompassing 10 datasets, 5 LLMs, and 5 evaluation metrics to analyze how these models leverage their input for abstractive summarization. Our findings reveal a pronounced bias towards the introductory content (and to a lesser extent, the final content), posing challenges for LLM performance across a range of diverse summarization benchmarks.

Generative artificial intelligence (GenAI), exemplified by ChatGPT, Midjourney, and other state-of-the-art large language models and diffusion models, holds significant potential for transforming education and enhancing human productivity. While the prevalence of GenAI in education has motivated numerous research initiatives, integrating these technologies within the learning analytics (LA) cycle and their implications for practical interventions remain underexplored. This paper delves into the prospective opportunities and challenges GenAI poses for advancing LA. We present a concise overview of the current GenAI landscape and contextualise its potential roles within Clow's generic framework of the LA cycle. We posit that GenAI can play pivotal roles in analysing unstructured data, generating synthetic learner data, enriching multimodal learner interactions, advancing interactive and explanatory analytics, and facilitating personalisation and adaptive interventions. As the lines blur between learners and GenAI tools, a renewed understanding of learners is needed. Future research can delve deep into frameworks and methodologies that advocate for human-AI collaboration. The LA community can play a pivotal role in capturing data about human and AI contributions and exploring how they can collaborate most effectively. As LA advances, it is essential to consider the pedagogical implications and broader socioeconomic impact of GenAI for ensuring an inclusive future.

Since the natural language processing (NLP) community started to make large language models (LLMs), such as GPT-4, act as a critic to evaluate the quality of generated texts, most of them only train a critique generation model of a specific scale on specific datasets. We argue that a comprehensive investigation on the key factor of LLM-based evaluation models, such as scaling properties, is lacking, so that it is still inconclusive whether these models have potential to replace GPT-4's evaluation in practical scenarios. In this paper, we propose a new critique generation model called CritiqueLLM, which includes a dialogue-based prompting method for high-quality referenced / reference-free evaluation data. Experimental results show that our model can achieve comparable evaluation performance to GPT-4 especially in system-level correlations, and even outperform GPT-4 in 3 out of 8 tasks in a challenging reference-free setting. We conduct detailed analysis to show promising scaling properties of our model in the quality of generated critiques. We also demonstrate that our generated critiques can act as scalable feedback to directly improve the generation quality of LLMs.

Conversational AI tools that can generate and discuss clinically correct radiology reports for a given medical image have the potential to transform radiology. Such a human-in-the-loop radiology assistant could facilitate a collaborative diagnostic process, thus saving time and improving the quality of reports. Towards this goal, we introduce RaDialog, the first thoroughly evaluated and publicly available large vision-language model for radiology report generation and interactive dialog. RaDialog effectively integrates visual image features and structured pathology findings with a large language model (LLM) while simultaneously adapting it to a specialized domain using parameter-efficient fine-tuning. To keep the conversational abilities of the underlying LLM, we propose a comprehensive, semi-automatically labeled, image-grounded instruct dataset for chest X-ray radiology tasks. By training with this dataset, our method achieves state-of-the-art clinical correctness in report generation and shows impressive abilities in interactive tasks such as correcting reports and answering questions, serving as a foundational step toward clinical dialog systems. Our code is available on github: https://github.com/ChantalMP/RaDialog.

Adept traffic models are critical to both planning and closed-loop simulation for autonomous vehicles (AV), and key design objectives include accuracy, diverse multimodal behaviors, interpretability, and downstream compatibility. Recently, with the advent of large language models (LLMs), an additional desirable feature for traffic models is LLM compatibility. We present Categorical Traffic Transformer (CTT), a traffic model that outputs both continuous trajectory predictions and tokenized categorical predictions (lane modes, homotopies, etc.). The most outstanding feature of CTT is its fully interpretable latent space, which enables direct supervision of the latent variable from the ground truth during training and avoids mode collapse completely. As a result, CTT can generate diverse behaviors conditioned on different latent modes with semantic meanings while beating SOTA on prediction accuracy. In addition, CTT's ability to input and output tokens enables integration with LLMs for common-sense reasoning and zero-shot generalization.

Recently, the visual programming framework (VisProg) has emerged as a significant framework for executing compositional visual tasks due to its interpretability and flexibility. However, the performance of VisProg on specific Visual Reasoning (VR) tasks is markedly inferior compared to well-trained task-specific models since its employed visual sub-modules have limited generalization capabilities. Due to the non-differentiability of VisProg, it is quite challenging to improve these visual sub-modules within VisProg for the specific VR task while maintaining their generalizability on the un-seen tasks. Attempt to overcome these difficulties, we propose CLVP, a Continuous Learning paradigm for VisProg across various visual reasoning tasks. Specifically, our CLVP distills the capabilities of well-trained task-specific models into the visual sub-modules in a stepwise and anti-forgetting manner. This can continually improve the performance of VisProg on multiple visual tasks while preserving the flexibility of VisProg. Extensive and comprehensive experimental results demonstrate that our CLVP obtains significant performance gains on specific VR benchmarks, i.e., GQA (+1.4%) and NLVRv2 (+5.6%), compared to the VisProg baseline, and also maintains a promising generalizability for VR on un-seen and previous learned tasks.

Conceptual engineering (CE) is a philosophical methodology concerned with the assessment and improvement of concepts [1]. Koch, Löhr and Pinder have surveyed recent work on the theory of CE, discussing different theories defining the targets of CE, i.e., "what conceptual engineers are (or should be) trying to engineer" [2]. In one such theory, Nado proposes as targets classification procedures, defined as abstract'recipes' which sort entities "into an'in'-group and an'out'-group" [3]. Our work builds on Nado's idea by defining a method for implementing classification procedures consistent with this definition. A large language model (LLM) is a probabilistic model trained on a natural language corpus that, given a sequence of tokens from a vocabulary occurring in the corpus, generates a continuation of the input sequence.

This study investigates the application of large language models (LLMs), specifically GPT-3.5 and GPT-4, with Chain-of-Though (CoT)in the automatic scoring of student-written responses to science assessments. We focused on overcoming the challenges of accessibility, technical complexity, and lack of explainability that have previously limited the use of automatic assessment tools among researchers and educators. We used a testing dataset comprising six assessment tasks (three binomial and three trinomial) with 1,650 student responses. We employed six prompt engineering strategies, combining zero-shot or few-shot learning with CoT, either alone or alongside item stem and scoring rubrics. Results indicated that few-shot (acc = .67) outperformed zero-shot learning (acc = .60), with 12.6\% increase. CoT, when used without item stem and scoring rubrics, did not significantly affect scoring accuracy (acc = .60). However, CoT prompting paired with contextual item stems and rubrics proved to be a significant contributor to scoring accuracy (13.44\% increase for zero-shot; 3.7\% increase for few-shot). Using a novel approach PPEAS, we found a more balanced accuracy across different proficiency categories, highlighting the importance of domain-specific reasoning in enhancing the effectiveness of LLMs in scoring tasks. Additionally, we also found that GPT-4 demonstrated superior performance over GPT-3.5 in various scoring tasks, showing 8.64\% difference. The study revealed that the single-call strategy with GPT-4, particularly using greedy sampling, outperformed other approaches, including ensemble voting strategies. This study demonstrates the potential of LLMs in facilitating automatic scoring, emphasizing that CoT enhances accuracy, particularly when used with item stem and scoring rubrics.

This paper assesses the potential for large language models (LLMs) to serve as assistive tools in the creative writing process, by means of a single, in-depth case study. In the course of the study, we develop interactive and multi-voice prompting strategies that interleave background descriptions (scene setting, plot elements), instructions that guide composition, samples of text in the target style, and critical discussion of the given samples. We qualitatively evaluate the results from a literary critical perspective, as well as from the standpoint of computational creativity (a sub-field of artificial intelligence). Our findings lend support to the view that the sophistication of the results that can be achieved with an LLM mirrors the sophistication of the prompting.

Decentralized training of large language models has emerged as an effective way to democratize this technology. However, the potential threats associated with this approach have not been carefully discussed, which would hinder the development of decentralized training infrastructures. This paper aims to initiate discussion towards this end by exploring the robustness of decentralized training from three main perspectives. First, we demonstrate the vulnerabilities inherent in decentralized training frameworks in terms of hardware, data, and models. Second, we highlight the fundamental difference between decentralized foundation model training and vanilla federated learning, where the security techniques employed in federated learning cannot be applied directly. Third, we discuss the essential components required for a robust and efficient decentralized training framework and present a case study by modeling a concrete threat model. Our objective in this vision paper is to emphasize the importance of addressing security concerns in the context of decentralized training for large language models.