Related papers: Interscript: A dataset for interactive learning of…
User feedback is becoming an increasingly important source of information for requirements engineering, user interface design, and software engineering in general. Nowadays, user feedback is largely available and easily accessible in social…
Once language models (LMs) are deployed, they can interact with users long-term, ideally evolving based on their feedback. Asking for direct user feedback can be disruptive; thus, we study harvesting implicit user feedback from user-LM…
The driving interaction-a critical yet complex aspect of daily driving-lies at the core of autonomous driving research. However, real-world driving scenarios sparsely capture rich interaction events, limiting the availability of…
We introduce MCScript2.0, a machine comprehension corpus for the end-to-end evaluation of script knowledge. MCScript2.0 contains approx. 20,000 questions on approx. 3,500 texts, crowdsourced based on a new collection process that results in…
Although there has been substantial research in software analytics for effort estimation in traditional software projects, little work has been done for estimation in agile projects, especially estimating user stories or issues. Story…
The rise of capabilities expressed by large language models has been quickly followed by the integration of the same complex systems into application level logic. Algorithms, programs, systems, and companies are built around structured…
A source code difference (diff) indicates changes made by comparing new and old source codes, and it can be utilized in code reviews to help developers understand the changes made to the code. Although many diff generation methods have been…
Automatically generating scripts (i.e. sequences of key steps described in text) from video demonstrations and reasoning about the subsequent steps are crucial to the modern AI virtual assistants to guide humans to complete everyday tasks,…
Learning from human preferences is important for language models to match human needs and to align with human and social values. Prior works have achieved remarkable successes by learning from human feedback to understand and follow…
Most research on question answering focuses on the pre-deployment stage; i.e., building an accurate model for deployment. In this paper, we ask the question: Can we improve QA systems further \emph{post-}deployment based on user…
Humans rely more and more on systems with AI components. The AI community typically treats human inputs as a given and optimizes AI models only. This thinking is one-sided and it neglects the fact that humans can learn, too. In this work,…
Data storytelling workflows ask learners to integrate analytical, design, and narrative skills, but instructors rarely have the capacity to provide detailed feedback at each step. Computational and AI-assisted storytelling offers…
Progress in Machine Learning is often driven by the availability of large datasets, and consistent evaluation metrics for comparing modeling approaches. To this end, we present a repository of conversational datasets consisting of hundreds…
Language models can be used to provide interactive, personalized student feedback in educational settings. However, real-world deployment faces three key challenges: privacy concerns, limited computational resources, and the need for…
Building a socially intelligent agent involves many challenges, one of which is to teach the agent to speak guided by its value like a human. However, value-driven chatbots are still understudied in the area of dialogue systems. Most…
Speech style editing refers to modifying the stylistic properties of speech while preserving its linguistic content and speaker identity. However, most existing approaches depend on explicit labels or reference audio, which limits both…
We introduce DynaSent ('Dynamic Sentiment'), a new English-language benchmark task for ternary (positive/negative/neutral) sentiment analysis. DynaSent combines naturally occurring sentences with sentences created using the open-source…
Large Language Models (LLMs) and generative search systems are increasingly used for information seeking by diverse populations with varying preferences for knowledge sourcing and presentation. While users can customize LLM behavior through…
Distribution shift is a major source of failure for machine learning models. However, evaluating model reliability under distribution shift can be challenging, especially since it may be difficult to acquire counterfactual examples that…
Since most software systems provide their users with interactive features, building user interfaces (UI) is one of the core software engineering tasks. It consists in designing, implementing and testing ever more sophisticated and versatile…