Machine learning (ML), the process of leveraging algorithms and optimization to infer strategies for solving learning tasks, has enabled some of the greatest developments in artificial intelligence (AI) in the last decade, enabling the automated segmentation or class identification of images, the ability to answer nearly any text-based question, and the ability to generate images never seen before. In biomedical research, many of these ML models are quickly being applied to medical images and decision support systems in conjunction with a significant shift from traditional and statistical methods to increasing application of deep learning models. At the same time, the importance of both plentiful and well-curated data has become better understood, coinciding as of the time of writing this article with the incredible premise of OpenAI's ChatGPT and GPT-4 engines as well as other generative AI models which are trained on a vast, well-curated, and diverse array of content from across the internet [1]. As more data has become available, a wider selection of datasets containing more than one modality has also enabled growth in the multimodal research sphere. Multimodal data is intrinsic to biomedical research and clinical care.

The common sense reasoning abilities and vast general knowledge of Large Language Models (LLMs) make them a natural fit for interpreting user requests in a Smart Home assistant context. LLMs, however, lack specific knowledge about the user and their home limit their potential impact. SAGE (Smart Home Agent with Grounded Execution), overcomes these and other limitations by using a scheme in which a user request triggers an LLM-controlled sequence of discrete actions. These actions can be used to retrieve information, interact with the user, or manipulate device states. SAGE controls this process through a dynamically constructed tree of LLM prompts, which help it decide which action to take next, whether an action was successful, and when to terminate the process. The SAGE action set augments an LLM's capabilities to support some of the most critical requirements for a Smart Home assistant. These include: flexible and scalable user preference management ("is my team playing tonight?"), access to any smart device's full functionality without device-specific code via API reading "turn down the screen brightness on my dryer", persistent device state monitoring ("remind me to throw out the milk when I open the fridge"), natural device references using only a photo of the room ("turn on the light on the dresser"), and more. We introduce a benchmark of 50 new and challenging smart home tasks where SAGE achieves a 75% success rate, significantly outperforming existing LLM-enabled baselines (30% success rate).

In-context learning is a promising paradigm that utilizes in-context examples as prompts for the predictions of large language models. These prompts are crucial for achieving strong performance. However, since the prompts need to be sampled from a large volume of annotated examples, finding the right prompt may result in high annotation costs. To address this challenge, this paper introduces an influence-driven selective annotation method that aims to minimize annotation costs while improving the quality of in-context examples. The essence of our method is to select a pivotal subset from a large-scale unlabeled data pool to annotate for the subsequent sampling of prompts. Specifically, a directed graph is first constructed to represent unlabeled data. Afterward, the influence of candidate unlabeled subsets is quantified with a diffusion process. A simple yet effective greedy algorithm for unlabeled data selection is lastly introduced. It iteratively selects the data if it provides a maximum marginal gain with respect to quantified influence. Compared with previous efforts on selective annotations, our influencedriven method works in an end-to-end manner, avoids an intractable explicit balance between data diversity and representativeness, and enjoys theoretical support. Experiments confirm the superiority of the proposed method on various benchmarks, achieving better performance under lower time consumption during subset selection. The project page is available at https://skzhang1.github.io/IDEAL/. In-context learning (ICL) entails presenting a small set of examples with demonstrations as prompts (called in-context examples) to large language models (LLMs), before making predictions on test inputs (Wei et al., 2022a; Min et al., 2022; Akyürek et al., 2023). This emerging few-shot learning paradigm is an appealing alternative to supervised fine-tuning as it can avoid heavy parameter updates of language models while improving accuracy (Liu et al., 2021; Yoo et al., 2022). Recent studies indicate that obtaining prompts from a vast collection of annotated examples is crucial to achieving strong performance (Rubin et al., 2022). Notably, these studies have illuminated the substantial performance improvements when retrieving analogous examples (under specific embedding criteria) as in-context examples tailored for each individual test input.

Large language models (LLMs) with enormous pre-training tokens and parameters emerge diverse abilities, including math reasoning, code generation, and instruction following. These abilities are further enhanced by supervised fine-tuning (SFT). While the open-source community has explored ad-hoc SFT for enhancing individual capabilities, proprietary LLMs exhibit versatility across various skills. Therefore, understanding the facilitation of multiple abilities via SFT is paramount. In this study, we specifically focuses on the interplay of data composition between mathematical reasoning, code generation, and general human-aligning abilities during SFT. We propose four intriguing research questions to explore the association between model performance and various factors including data amount, composition ratio, model size and SFT strategies. Our experiments reveal that distinct capabilities scale differently and larger models generally show superior performance with same amount of data. Mathematical reasoning and code generation consistently improve with increasing data amount, whereas general abilities plateau after roughly a thousand samples. Moreover, we observe data composition appears to enhance various abilities under limited data conditions, yet can lead to performance conflicts when data is plentiful. Our findings also suggest the amount of composition data influences performance more than the composition ratio. In analysis of SFT strategies, we find that sequentially learning multiple skills risks catastrophic forgetting. Our proposed Dual-stage Mixed Fine-tuning (DMT) strategy offers a promising solution to learn multiple abilities with different scaling patterns.

The carbon footprint associated with large language models (LLMs) is a significant concern, encompassing emissions from their training, inference, experimentation, and storage processes, including operational and embodied carbon emissions. An essential aspect is accurately estimating the carbon impact of emerging LLMs even before their training, which heavily relies on GPU usage. Existing studies have reported the carbon footprint of LLM training, but only one tool, mlco2, can predict the carbon footprint of new neural networks prior to physical training. However, mlco2 has several serious limitations. It cannot extend its estimation to dense or mixture-of-experts (MoE) LLMs, disregards critical architectural parameters, focuses solely on GPUs, and cannot model embodied carbon footprints. Addressing these gaps, we introduce LLMCarbon, an end-to-end carbon footprint projection model designed for both dense and MoE LLMs. Compared to mlco2, LLMCarbon significantly enhances the accuracy of carbon footprint estimations for various LLMs. Large language models (LLMs) have established their supremacy in addressing a wide spectrum of natural language processing tasks (Brown et al., 2020). However, the proliferation of these models, coupled with increasingly expansive datasets (Sanderson, 2023; Anil et al., 2023), has woven LLM inferences into the fabric of everyday life (Campello de Souza et al., 2023).

Large language models exhibit superior capabilities in processing and understanding language, yet their applications in educational contexts remain underexplored. Learnersourcing enhances learning by engaging students in creating their own educational content. When learnersourcing multiple-choice questions, creating explanations for the solution of a question is a crucial step; it helps other students understand the solution and promotes a deeper understanding of related concepts. However, it is often difficult for students to craft effective solution explanations, due to limited subject understanding. To help scaffold the task of automated explanation generation, we present and evaluate a framework called "ILearner-LLM", that iteratively enhances the generated explanations for the given questions with large language models. Comprising an explanation generation model and an explanation evaluation model, the framework generates high-quality student-aligned explanations by iteratively feeding the quality rating score from the evaluation model back into the instruction prompt of the explanation generation model. Experimental results demonstrate the effectiveness of our ILearner-LLM on LLaMA2-13B and GPT-4 to generate higher quality explanations that are closer to those written by students on five PeerWise datasets. Our findings represent a promising path to enrich the learnersourcing experience for students and to enhance the capabilities of large language models for educational applications.

Building agents with large language models (LLMs) for computer control is a burgeoning research area, where the agent receives computer states and performs actions to complete complex tasks. Previous computer agents have demonstrated the benefits of in-context learning (ICL); however, their performance is hindered by several issues. First, the limited context length of LLMs and complex computer states restrict the number of exemplars, as a single webpage can consume the entire context. Second, the exemplars in current methods, such as high-level plans and multi-choice questions, cannot represent complete trajectories, leading to suboptimal performance in long-horizon tasks. Third, existing computer agents rely on task-specific exemplars and overlook the similarity among tasks, resulting in poor generalization to novel tasks. To address these challenges, we introduce Synapse, a computer agent featuring three key components: i) state abstraction, which filters out task-irrelevant information from raw states, allowing more exemplars within the limited context, ii) trajectory-as-exemplar prompting, which prompts the LLM with complete trajectories of the abstracted states and actions to improve multi-step decision-making, and iii) exemplar memory, which stores the embeddings of exemplars and retrieves them via similarity search for generalization to novel tasks. We evaluate Synapse on MiniWoB++, a standard task suite, and Mind2Web, a real-world website benchmark. In MiniWoB++, Synapse achieves a 99.2% average success rate (a 10% relative improvement) across 64 tasks using demonstrations from only 48 tasks. Notably, Synapse is the first ICL method to solve the book-flight task in MiniWoB++. Synapse also exhibits a 56% relative improvement in average step success rate over the previous state-of-the-art prompting scheme in Mind2Web.

We explore incorporating natural language inference (NLI) into the text generative pipeline by using a pre-trained NLI model to assess whether a generated sentence entails, contradicts, or is neutral to the prompt and preceding text. First, we show that the NLI task is predictive of generation errors made by GPT-3. We use these results to develop an NLI-informed generation procedure for GPT-J. Then, we evaluate these generations by obtaining human annotations on error types and overall quality. We find that an NLI strategy of maximizing entailment improves text generation when the nucleus sampling randomness parameter value is high, while one which maximizes contradiction is in fact productive when the parameter value is low. Overall, though, we demonstrate that an NLI strategy of maximizing the neutral class provides the highest quality of generated text (significantly better than the vanilla generations), regardless of parameter value.

The cost of making further progress in artificial intelligence is becoming as startling as a hallucination by ChatGPT. Demand for the graphics chips known as GPUs needed for large-scale AI training has driven prices of the crucial components through the roof. OpenAI has said that training the algorithm that now powers ChatGPT cost the firm over 100 million. The race to compete in AI also means that data centers are now consuming worrying amounts of energy. The AI gold rush has a few startups hatching bold plans to create new computational shovels to sell.

Last year saw new artificial intelligence products released at the most rapid pace yet, though predictions of an AI boom on the scale of last decade's tech explosion have yet to come to fruition. "I think 2023 was the year that AI astonished people and 2024 will be the year of retrenchment as people learn the limitations of AI and where various AI systems have the greatest utility," Christopher Alexander, chief analytics officer for Pioneer Development Group, told Fox News Digital. "I think that the race for AI utility has just begun and AI will become a permanent fixture in people's lives. I think that the grand predictions for AI in this past year confused the current state of AI and the future state, which has led to some confusion in the market." Alexander's comments come after what was in many ways a landmark year for AI technology in 2023, with new platforms and developments making headlines throughout the year.