DynaSaur: Large Language Agents Beyond Predefined Actions

Existing LLM agent systems typically select actions from a fixed and predefined set at every step. While this approach is effective in closed, narrowly-scoped environments, we argue that it presents two major challenges when deploying LLM agents in real-world scenarios: (1) selecting from a fixed set of actions significantly restricts the planning and acting capabilities of LLM agents, and (2) this approach requires substantial human effort to enumerate and implement all possible actions, which becomes impractical in complex environments with a vast number of potential actions. In this work, we propose an LLM agent framework that enables the dynamic creation and composition of actions in an online manner. In this framework, the agent interacts with the environment by generating and executing programs written in a general-purpose programming language at each step. Furthermore, generated actions are accumulated over time for future reuse. Our extensive experiments on the GAIA benchmark demonstrate that this framework offers significantly greater flexibility and outperforms previous methods. Notably, it allows an LLM agent to recover in scenarios where no relevant action exists in the predefined set or when existing actions fail due to unforeseen edge cases. At the time of writing, we hold the top position on the GAIA public leaderboard. Our code can be found in \href{https://github.com/adobe-research/dynasaur}{https://github.com/adobe-research/dynasaur}.

Generating Realistic Tabular Data with Large Language Models

While most generative models show achievements in image data generation, few are developed for tabular data generation. Recently, due to success of large language models (LLM) in diverse tasks, they have also been used for tabular data generation. However, these methods do not capture the correct correlation between the features and the target variable, hindering their applications in downstream predictive tasks. To address this problem, we propose a LLM-based method with three important improvements to correctly capture the ground-truth feature-class correlation in the real data. First, we propose a novel permutation strategy for the input data in the fine-tuning phase. Second, we propose a feature-conditional sampling approach to generate synthetic samples. Finally, we generate the labels by constructing prompts based on the generated samples to query our fine-tuned LLM. Our extensive experiments show that our method significantly outperforms 10 SOTA baselines on 20 datasets in downstream tasks. It also produces highly realistic synthetic samples in terms of quality and diversity. More importantly, classifiers trained with our synthetic data can even compete with classifiers trained with the original data on half of the benchmark datasets, which is a significant achievement in tabular data generation.

Robust Transfer Learning for Active Level Set Estimation with Locally Adaptive Gaussian Process Prior

The objective of active level set estimation for a black-box function is to precisely identify regions where the function values exceed or fall below a specified threshold by iteratively performing function evaluations to gather more information about the function. This becomes particularly important when function evaluations are costly, drastically limiting our ability to acquire large datasets. A promising way to sample-efficiently model the black-box function is by incorporating prior knowledge from a related function. However, this approach risks slowing down the estimation task if the prior knowledge is irrelevant or misleading. In this paper, we present a novel transfer learning method for active level set estimation that safely integrates a given prior knowledge while constantly adjusting it to guarantee a robust performance of a level set estimation algorithm even when the prior knowledge is irrelevant. We theoretically analyze this algorithm to show that it has a better level set convergence compared to standard transfer learning approaches that do not make any adjustment to the prior. Additionally, extensive experiments across multiple datasets confirm the effectiveness of our method when applied to various different level set estimation algorithms as well as different transfer learning scenarios.

Memory-efficient Training of LLMs with Larger Mini-batches

Training with larger mini-batches improves the performance and convergence rate of training machine learning models. However, training with large mini-batches becomes prohibitive for Large Language Models (LLMs) with billions of parameters, due to the large GPU memory requirement. To address this problem, we propose finding small mini-batches that simulate the dynamics of training with larger mini-batches. Specifically, we formulate selecting smaller mini-batches of examples that closely capture gradients of large mini-batches as a submodular maximization problem. Nevertheless, the very large dimensionality of the gradients makes the problem very challenging to solve. To address this, we leverage ideas from zeroth-order optimization and neural network pruning to find lower-dimensional gradient estimates that allow finding high-quality subsets effectively with a limited amount of memory. We prove the superior convergence rate of training on the small mini-batches found by our method and empirically show its effectiveness. Our method can effectively reduce the memory requirement by 2x and speed up training by 1.3x, as we confirm for fine-tuning Phi-2 on MathInstruct. Our method can be easily stacked with LoRA and other memory-efficient methods to further reduce the memory requirements of training LLMs.

GPT-4V Cannot Generate Radiology Reports Yet

GPT-4V's purported strong multimodal abilities raise interests in using it to automate radiology report writing, but there lacks thorough evaluations. In this work, we perform a systematic evaluation of GPT-4V in generating radiology reports on two chest X-ray report datasets: MIMIC-CXR and IU X-Ray. We attempt to directly generate reports using GPT-4V through different prompting strategies and find that it fails terribly in both lexical metrics and clinical efficacy metrics. To understand the low performance, we decompose the task into two steps: 1) the medical image reasoning step of predicting medical condition labels from images; and 2) the report synthesis step of generating reports from (groundtruth) conditions. We show that GPT-4V's performance in image reasoning is consistently low across different prompts. In fact, the distributions of model-predicted labels remain constant regardless of which groundtruth conditions are present on the image, suggesting that the model is not interpreting chest X-rays meaningfully. Even when given groundtruth conditions in report synthesis, its generated reports are less correct and less natural-sounding than a finetuned LLaMA-2. Altogether, our findings cast doubt on the viability of using GPT-4V in a radiology workflow.

Multi-Objective Linguistic Control of Large Language Models

Large language models (LLMs), despite their breakthroughs on many challenging benchmark tasks, lean to generate verbose responses and lack the controllability of output complexity, which is usually preferred by human users in practice. In this paper, we study how to precisely control multiple linguistic complexities of LLM output by finetuning using off-the-shelf data. To this end, we propose multi-control tuning (MCTune), which includes multiple linguistic complexity values of ground-truth responses as controls in the input for instruction tuning. We finetune LLaMA2-7B on Alpaca-GPT4 and WizardLM datasets. Evaluations on widely used benchmarks demonstrate that our method does not only improve LLMs' multi-complexity controllability substantially but also retains or even enhances the quality of the responses as a side benefit.

RuleR: Improving LLM Controllability by Rule-based Data Recycling

Large language models (LLMs) still lack delicate controllability over their responses, which is critical to enhancing their performance and the user experience. However, curating supervised fine-tuning (SFT) datasets to improve LLM controllability usually relies on human experts or proprietary LLMs, which requires additional costs. To bridge this gap, we propose Rule-based Data Recycling (RuleR), a data augmentation method incorporating multiple constraints into the original data samples according to predefined rules, which creates new training tasks to consolidate the controllability of LLMs. Instead of creating new data from scratch, RuleR ``recycles'' existing data by simply applying rule-based edits to their responses and appending the rule-instructions in their original instructions. Experimental results demonstrate RuleR's effectiveness in improving LLM controllability while maintaining general instruction-following capabilities. The code will be released on https://github.com/MingLiiii/RuleR.

Multi-level Phenotypic Models of Cardiovascular Disease and Obstructive Sleep Apnea Comorbidities: A Longitudinal Wisconsin Sleep Cohort Study

Cardiovascular diseases (CVDs) are notably prevalent among patients with obstructive sleep apnea (OSA), posing unique challenges in predicting CVD progression due to the intricate interactions of comorbidities. Traditional models typically lack the necessary dynamic and longitudinal scope to accurately forecast CVD trajectories in OSA patients. This study introduces a novel multi-level phenotypic model to analyze the progression and interplay of these conditions over time, utilizing data from the Wisconsin Sleep Cohort, which includes 1,123 participants followed for decades. Our methodology comprises three advanced steps: (1) Conducting feature importance analysis through tree-based models to underscore critical predictive variables like total cholesterol, low-density lipoprotein (LDL), and diabetes. (2) Developing a logistic mixed-effects model (LGMM) to track longitudinal transitions and pinpoint significant factors, which displayed a diagnostic accuracy of 0.9556. (3) Implementing t-distributed Stochastic Neighbor Embedding (t-SNE) alongside Gaussian Mixture Models (GMM) to segment patient data into distinct phenotypic clusters that reflect varied risk profiles and disease progression pathways. This phenotypic clustering revealed two main groups, with one showing a markedly increased risk of major adverse cardiovascular events (MACEs), underscored by the significant predictive role of nocturnal hypoxia and sympathetic nervous system activity from sleep data. Analysis of transitions and trajectories with t-SNE and GMM highlighted different progression rates within the cohort, with one cluster progressing more slowly towards severe CVD states than the other. This study offers a comprehensive understanding of the dynamic relationship between CVD and OSA, providing valuable tools for predicting disease onset and tailoring treatment approaches.

Make the Most of Your Data: Changing the Training Data Distribution to Improve In-distribution Generalization Performance

Can we modify the training data distribution to encourage the underlying optimization method toward finding solutions with superior generalization performance on in-distribution data? In this work, we approach this question for the first time by comparing the inductive bias of gradient descent (GD) with that of sharpness-aware minimization (SAM). By studying a two-layer CNN, we prove that SAM learns easy and difficult features more uniformly, particularly in early epochs. That is, SAM is less susceptible to simplicity bias compared to GD. Based on this observation, we propose USEFUL, an algorithm that clusters examples based on the network output early in training and upsamples examples with no easy features to alleviate the pitfalls of the simplicity bias. We show empirically that modifying the training data distribution in this way effectively improves the generalization performance on the original data distribution when training with (S)GD by mimicking the training dynamics of SAM. Notably, we demonstrate that our method can be combined with SAM and existing data augmentation strategies to achieve, to the best of our knowledge, state-of-the-art performance for training ResNet18 on CIFAR10, STL10, CINIC10, Tiny-ImageNet; ResNet34 on CIFAR100; and VGG19 and DenseNet121 on CIFAR10.

Active Level Set Estimation for Continuous Search Space with Theoretical Guarantee

A common problem encountered in many real-world applications is level set estimation where the goal is to determine the region in the function domain where the function is above or below a given threshold. When the function is black-box and expensive to evaluate, the level sets need to be found in a minimum set of function evaluations. Existing methods often assume a discrete search space with a finite set of data points for function evaluations and estimating the level sets. When applied to a continuous search space, these methods often need to first discretize the space which leads to poor results while needing high computational time. While some methods cater for the continuous setting, they still lack a proper guarantee for theoretical convergence. To address this problem, we propose a novel algorithm that does not need any discretization and can directly work in continuous search spaces. Our method suggests points by constructing an acquisition function that is defined as a measure of confidence of the function being higher or lower than the given threshold. A theoretical analysis for the convergence of the algorithm to an accurate solution is provided. On multiple synthetic and real-world datasets, our algorithm successfully outperforms state-of-the-art methods.