Forecasting weather and climate events is crucial for making appropriate measures to mitigate environmental hazards and minimize associated losses. Previous research on environmental forecasting focuses on predicting numerical meteorological variables related to closed-set events rather than forecasting open-set events directly, which limits the comprehensiveness of event forecasting. We propose Weather and Climate Event Forecasting (WCEF), a new task that leverages meteorological raster data and textual event data to predict potential weather and climate events. However, due to difficulties in aligning multimodal data and the lack of sufficient supervised datasets, this task is challenging to accomplish. Therefore, we first propose a framework to align historical meteorological data with past weather and climate events using the large language model (LLM). In this framework, we construct a knowledge graph by using LLM to extract information about weather and climate events from a corpus of over 41k highly environment-focused news articles. Subsequently, we mapped these events with meteorological raster data, creating a supervised dataset, which is the largest and most novel for LLM tuning on the WCEF task. Finally, we introduced our aligned models, CLLMate (LLM for climate), a multimodal LLM to forecast weather and climate events using meteorological raster data. In evaluating CLLMate, we conducted extensive experiments. The results indicate that CLLMate surpasses both the baselines and other multimodal LLMs, showcasing the potential of utilizing LLM to align weather and climate events with meteorological data and highlighting the promising future for research on the WCEF task.

Extremely low-resource (XLR) languages lack substantial corpora for training NLP models, motivating the use of all available resources such as dictionaries and grammar books. Machine Translation from One Book (Tanzer et al., 2024) suggests prompting long-context LLMs with one grammar book enables English-Kalamang translation, an unseen XLR language - a noteworthy case of linguistic knowledge helping an NLP task. We investigate whether the book's grammatical explanations or its parallel examples are most effective for learning XLR translation, finding almost all improvement stems from the parallel examples. Further, we find similar results for Nepali, a seen low-resource language, and achieve performance comparable to an LLM with a grammar book by simply fine-tuning an encoder-decoder translation model. We then investigate where grammar books help by testing two linguistic tasks, grammaticality judgment and gloss prediction, and we explore what kind of grammatical knowledge helps by introducing a typological feature prompt that achieves leading results on these more relevant tasks. We thus emphasise the importance of task-appropriate data for XLR languages: parallel examples for translation, and grammatical data for linguistic tasks. As we find no evidence that long-context LLMs can make effective use of grammatical explanations for XLR translation, we suggest data collection for multilingual XLR tasks such as translation is best focused on parallel data over linguistic description.

The sudden emergence of large language models (LLMs) such as ChatGPT has had a disruptive impact throughout the computing education community. LLMs have been shown to excel at producing correct code to CS1 and CS2 problems, and can even act as friendly assistants to students learning how to code. Recent work shows that LLMs demonstrate unequivocally superior results in being able to explain and resolve compiler error messages -- for decades, one of the most frustrating parts of learning how to code. However, LLM-generated error message explanations have only been assessed by expert programmers in artificial conditions. This work sought to understand how novice programmers resolve programming error messages (PEMs) in a more realistic scenario. We ran a within-subjects study with $n$ = 106 participants in which students were tasked to fix six buggy C programs. For each program, participants were randomly assigned to fix the problem using either a stock compiler error message, an expert-handwritten error message, or an error message explanation generated by GPT-4. Despite promising evidence on synthetic benchmarks, we found that GPT-4 generated error messages outperformed conventional compiler error messages in only 1 of the 6 tasks, measured by students' time-to-fix each problem. Handwritten explanations still outperform LLM and conventional error messages, both on objective and subjective measures.

In everyday life, frequently used objects like cups often have unfixed positions and multiple instances within the same category, and their carriers frequently change as well. As a result, it becomes challenging for a robot to efficiently navigate to a specific instance. To tackle this challenge, the robot must capture and update scene changes and plans continuously. However, current object navigation approaches primarily focus on semantic-level and lack the ability to dynamically update scene representation. This paper captures the relationships between frequently used objects and their static carriers. It constructs an open-vocabulary Carrier-Relationship Scene Graph (CRSG) and updates the carrying status during robot navigation to reflect the dynamic changes of the scene. Based on the CRSG, we further propose an instance navigation strategy that models the navigation process as a Markov Decision Process. At each step, decisions are informed by Large Language Model's commonsense knowledge and visual-language feature similarity. We designed a series of long-sequence navigation tasks for frequently used everyday items in the Habitat simulator. The results demonstrate that by updating the CRSG, the robot can efficiently navigate to moved targets. Additionally, we deployed our algorithm on a real robot and validated its practical effectiveness.

Integrating machine learning (ML) into customer service chatbots enhances their ability to understand and respond to user queries, ultimately improving service performance. However, they may appear artificial to some users and affecting customer experience. Hence, meticulous evaluation of ML models for each pipeline component is crucial for optimizing performance, though differences in functionalities can lead to unfair comparisons. In this paper, we present a tailored experimental evaluation approach for goal-oriented customer service chatbots with pipeline architecture, focusing on three key components: Natural Language Understanding (NLU), dialogue management (DM), and Natural Language Generation (NLG). Our methodology emphasizes individual assessment to determine optimal ML models. Specifically, we focus on optimizing hyperparameters and evaluating candidate models for NLU (utilizing BERT and LSTM), DM (employing DQN and DDQN), and NLG (leveraging GPT-2 and DialoGPT). The results show that for the NLU component, BERT excelled in intent detection whereas LSTM was superior for slot filling. For the DM component, the DDQN model outperformed DQN by achieving fewer turns, higher rewards, as well as greater success rates. For NLG, the large language model GPT-2 surpassed DialoGPT in BLEU, METEOR, and ROUGE metrics. These findings aim to provide a benchmark for future research in developing and optimizing customer service chatbots, offering valuable insights into model performance and optimal hyperparameters.

Goal-directed interactive agents, which autonomously complete tasks through interactions with their environment, can assist humans in various domains of their daily lives. Recent advances in large language models (LLMs) led to a surge of new, more and more challenging tasks to evaluate such agents. To properly contextualize performance across these tasks, it is imperative to understand the different challenges they pose to agents. To this end, this survey compiles relevant tasks and environments for evaluating goal-directed interactive agents, structuring them along dimensions relevant for understanding current obstacles. An up-to-date compilation of relevant resources can be found on our project website: https://coli-saar.github.io/interactive-agents.

Understanding and modeling collective intelligence is essential for addressing complex social systems. Directed graphs called fuzzy cognitive maps (FCMs) offer a powerful tool for encoding causal mental models, but extracting high-integrity FCMs from text is challenging. This study presents an approach using large language models (LLMs) to automate FCM extraction. We introduce novel graph-based similarity measures and evaluate them by correlating their outputs with human judgments through the Elo rating system. Results show positive correlations with human evaluations, but even the best-performing measure exhibits limitations in capturing FCM nuances. Fine-tuning LLMs improves performance, but existing measures still fall short. This study highlights the need for soft similarity measures tailored to FCM extraction, advancing collective intelligence modeling with NLP.

This study reports a comprehensive environmental scan of the generative AI (GenAI) infrastructure in the national network for clinical and translational science across 36 institutions supported by the Clinical and Translational Science Award (CTSA) Program led by the National Center for Advancing Translational Sciences (NCATS) of the National Institutes of Health (NIH) at the United States. With the rapid advancement of GenAI technologies, including large language models (LLMs), healthcare institutions face unprecedented opportunities and challenges. This research explores the current status of GenAI integration, focusing on stakeholder roles, governance structures, and ethical considerations by administering a survey among leaders of health institutions (i.e., representing academic medical centers and health systems) to assess the institutional readiness and approach towards GenAI adoption. Key findings indicate a diverse range of institutional strategies, with most organizations in the experimental phase of GenAI deployment. The study highlights significant variations in governance models, with a strong preference for centralized decision-making but notable gaps in workforce training and ethical oversight. Moreover, the results underscore the need for a more coordinated approach to GenAI governance, emphasizing collaboration among senior leaders, clinicians, information technology staff, and researchers. Our analysis also reveals concerns regarding GenAI bias, data security, and stakeholder trust, which must be addressed to ensure the ethical and effective implementation of GenAI technologies. This study offers valuable insights into the challenges and opportunities of GenAI integration in healthcare, providing a roadmap for institutions aiming to leverage GenAI for improved quality of care and operational efficiency.

Foundation language model deployments often include auxiliary guard-rail models to filter or classify text, detecting jailbreak attempts, biased or toxic output, or ensuring topic adherence. These additional models increase the complexity and cost of model inference, especially since many are also large language models. To address this issue, we explore training-free model merging techniques to consolidate these models into a single, multi-functional model. We propose Heterogeneous Multi-Class Model Merging (HM3) as a simple technique for merging multi-class classifiers with heterogeneous label spaces. Unlike parameter-efficient fine-tuning techniques like LoRA, which require extensive training and add complexity during inference, recent advancements allow models to be merged in a training-free manner. We report promising results for merging BERT-based guard models, some of which attain an average F1-score higher than the source models while reducing the inference time by up to 44%. We introduce self-merging to assess the impact of reduced task-vector density, finding that the more poorly performing hate speech classifier benefits from self-merging while higher-performing classifiers do not, which raises questions about using task vector reduction for model tuning.

Diffusion models have recently achieved remarkable advancements in terms of image quality and fidelity to textual prompts. Concurrently, the safety of such generative models has become an area of growing concern. This work introduces a novel type of jailbreak, which triggers T2I models to generate the image with visual text, where the image and the text, although considered to be safe in isolation, combine to form unsafe content. To systematically explore this phenomenon, we propose a dataset to evaluate the current diffusion-based text-to-image (T2I) models under such jailbreak. We benchmark nine representative T2I models, including two close-source commercial models. Experimental results reveal a concerning tendency to produce unsafe content: all tested models suffer from such type of jailbreak, with rates of unsafe generation ranging from 8\% to 74\%. In real-world scenarios, various filters such as keyword blocklists, customized prompt filters, and NSFW image filters, are commonly employed to mitigate these risks. We evaluate the effectiveness of such filters against our jailbreak and found that, while current classifiers may be effective for single modality detection, they fail to work against our jailbreak. Our work provides a foundation for further development towards more secure and reliable T2I models.