Related papers: App-Aware Response Synthesis for User Reviews
We introduce AccurateRAG -- a novel framework for constructing high-performance question-answering applications based on retrieval-augmented generation (RAG). Our framework offers a pipeline for development efficiency with tools for raw…
Presenting users with diverse responses from foundation models is crucial for enhancing user experience and accommodating varying preferences. However, generating multiple high-quality and diverse responses without sacrificing accuracy…
App reviews reflect various user requirements that can aid in planning maintenance tasks. Recently, proposed approaches for automatically classifying user reviews rely on machine learning algorithms. A previous study demonstrated that…
The modern software development landscape has seen a shift in focus toward mobile applications as tablets and smartphones near ubiquitous adoption. Due to this trend, the complexity of these apps has been increasing, making development and…
Information Retrieval (IR) evaluation involves far more complexity than merely presenting performance measures in a table. Researchers often need to compare multiple models across various dimensions, such as the Precision-Recall trade-off…
The complex nature of intelligent systems motivates work on supporting users during interaction, for example through explanations. However, as of yet, there is little empirical evidence in regard to specific problems users face when…
Today, most large-scale conversational AI agents (e.g. Alexa, Siri, or Google Assistant) are built using manually annotated data to train the different components of the system. Typically, the accuracy of the ML models in these components…
Thanks to unprecedented language understanding and generation capabilities of large language model (LLM), Retrieval-augmented Code Generation (RaCG) has recently been widely utilized among software developers. While this has increased…
When provided with sufficient explanatory context, smaller Language Models have been shown to exhibit strong reasoning ability on challenging short-answer question-answering tasks where the questions are unseen in training. We evaluate two…
Although text-to-audio generation has made remarkable progress in realism and diversity, the development of evaluation metrics has not kept pace. Widely-adopted approaches, typically based on embedding similarity like CLAPScore, effectively…
The sequential recommendation (SR) task aims to predict the next item based on users' historical interaction sequences. Typically trained on historical data, SR models often struggle to adapt to real-time preference shifts during inference…
Interacting with a speech interface to query a Question Answering (QA) system is becoming increasingly popular. Typically, QA systems rely on passage retrieval to select candidate contexts and reading comprehension to extract the final…
Meta titles and descriptions strongly shape engagement in search and recommendation platforms, yet optimizing them remains challenging. Search engine ranking models are black box environments, explicit labels are unavailable, and feedback…
Aligning large language models with human objectives is paramount, yet common approaches including RLHF suffer from unstable and resource-intensive training. In response to this challenge, we introduce ARGS, Alignment as Reward-Guided…
Mobile software apps ("apps") are one of the prevailing digital technologies that our modern life heavily depends on. A key issue in the development of apps is how to design gender-inclusive apps. Apps that do not consider gender inclusion,…
In this work, we develop new self-learning techniques with an attention-based sequence-to-sequence (seq2seq) model for automatic speech recognition (ASR). For untranscribed speech data, the hypothesis from an ASR system must be used as a…
Recent advancements in language modeling have enabled the translation of natural language into code, and the use of execution feedback to improve code generation. However, these methods often rely heavily on pre-existing test cases, which…
The modern software development landscape has seen a shift in focus toward mobile applications as smartphones and tablets near ubiquitous adoption. Due to this trend, the complexity of these "apps" has been increasing, making development…
Bandit algorithms are widely used in sequential decision problems to maximize the cumulative reward. One potential application is mobile health, where the goal is to promote the user's health through personalized interventions based on user…
Choosing optimal maskers for existing soundscapes to effect a desired perceptual change via soundscape augmentation is non-trivial due to extensive varieties of maskers and a dearth of benchmark datasets with which to compare and develop…