Evelyn Duesterwald

Praveen Venkateswaran, Evelyn Duesterwald, Vatche Isahagian

Dialogue State Tracking (DST), a key component of task-oriented conversation systems, represents user intentions by determining the values of pre-defined slots in an ongoing dialogue. Existing approaches use hand-crafted templates and additional slot information to fine-tune and prompt large pre-trained language models and elicit slot values from the dialogue context. Significant manual effort and domain knowledge is required to design effective prompts, limiting the generalizability of these approaches to new domains and tasks. In this work, we propose DiSTRICT, a generalizable in-context tuning approach for DST that retrieves highly relevant training examples for a given dialogue to fine-tune the model without any hand-crafted templates. Experiments with the MultiWOZ benchmark datasets show that DiSTRICT outperforms existing approaches in various zero-shot and few-shot settings using a much smaller model, thereby providing an important advantage for real-world deployments that often have limited resource availability.

Michael Desmond, Evelyn Duesterwald, Vatche Isahagian et al.

Most business process automation is still developed using traditional automation technologies such as workflow engines. These systems provide domain specific languages that require both business knowledge and programming skills to effectively use. As such, business users often lack adequate programming skills to fully leverage these code oriented environments. We propose a paradigm for the construction of business automations using natural language. The approach applies a large language model to translate business rules and automations described in natural language, into a domain specific language interpretable by a business rule engine. We compare the performance of various language model configurations, across various target domains, and explore the use of constrained decoding to ensure syntactically correct generation of output.

Matthew Halpern, Behzad Boroujerdian, Todd Mummert et al.

Today's cloud service architectures follow a "one size fits all" deployment strategy where the same service version instantiation is provided to the end users. However, consumers are broad and different applications have different accuracy and responsiveness requirements, which as we demonstrate renders the "one size fits all" approach inefficient in practice. We use a production-grade speech recognition engine, which serves several thousands of users, and an open source computer vision based system, to explain our point. To overcome the limitations of the "one size fits all" approach, we recommend Tolerance Tiers where each MLaaS tier exposes an accuracy/responsiveness characteristic, and consumers can programmatically select a tier. We evaluate our proposal on the CPU-based automatic speech recognition (ASR) engine and cutting-edge neural networks for image classification deployed on both CPUs and GPUs. The results show that our proposed approach provides an MLaaS cloud service architecture that can be tuned by the end API user or consumer to outperform the conventional "one size fits all" approach.

Ben Elder, Evelyn Duesterwald, Vinod Muthusamy

A typical approach developers follow to influence an LLM's behavior in an application is through careful manipulation of the prompt, such as by adding or modifying instructions. However, merely adding more instructions provides little assurance that they will actually be followed. We introduce Instruction Boosting as a post-generation method to increase the reliability of LLM prompt instructions. We show that Instruction Boosting improves the instruction following rate by up to 7 points for two instructions and up to 4 points for ten instructions. To demonstrate these results we introduce SCALEDIF, a benchmark with a scaled instruction volume of up to ten instructions per data sample. We also present an analysis of the commonly observed trend that performance degrades as more instructions are added. We show that an important factor contributing to this trend is the degree of tension and conflict that arises as the number of instructions is increased. We contribute a quantitative conflict scoring tool that explains the observed performance trends and provides feedback to developers on the impact that additional prompt instructions have on a model's performance.

Michael Desmond, Zahra Ashktorab, Michelle Brachman et al.

Labeling data is an important step in the supervised machine learning lifecycle. It is a laborious human activity comprised of repeated decision making: the human labeler decides which of several potential labels to apply to each example. Prior work has shown that providing AI assistance can improve the accuracy of binary decision tasks. However, the role of AI assistance in more complex data-labeling scenarios with a larger set of labels has not yet been explored. We designed an AI labeling assistant that uses a semi-supervised learning algorithm to predict the most probable labels for each example. We leverage these predictions to provide assistance in two ways: (i) providing a label recommendation and (ii) reducing the labeler's decision space by focusing their attention on only the most probable labels. We conducted a user study (n=54) to evaluate an AI-assisted interface for data labeling in this context. Our results highlight that the AI assistance improves both labeler accuracy and speed, especially when the labeler finds the correct label in the reduced label space. We discuss findings related to the presentation of AI assistance and design implications for intelligent labeling interfaces.

Matthew Arnold, Jeffrey Boston, Michael Desmond et al.

Today's AI deployments often require significant human involvement and skill in the operational stages of the model lifecycle, including pre-release testing, monitoring, problem diagnosis and model improvements. We present a set of enabling technologies that can be used to increase the level of automation in AI operations, thus lowering the human effort required. Since a common source of human involvement is the need to assess the performance of deployed models, we focus on technologies for performance prediction and KPI analysis and show how they can be used to improve automation in the key stages of a typical AI operations pipeline.

Evelyn Duesterwald, Anupama Murthi, Ganesh Venkataraman et al.

Adversarial training shows promise as an approach for training models that are robust towards adversarial perturbation. In this paper, we explore some of the practical challenges of adversarial training. We present a sensitivity analysis that illustrates that the effectiveness of adversarial training hinges on the settings of a few salient hyperparameters. We show that the robustness surface that emerges across these salient parameters can be surprisingly complex and that therefore no effective one-size-fits-all parameter settings exist. We then demonstrate that we can use the same salient hyperparameters as tuning knob to navigate the tension that can arise between robustness and accuracy. Based on these findings, we present a practical approach that leverages hyperparameter optimization techniques for tuning adversarial training to maximize robustness while keeping the loss in accuracy within a defined budget.