Related papers: Interscript: A dataset for interactive learning of…
Human feedback data is a critical component in developing language models. However, collecting this feedback is costly and ultimately not scalable. Inspired by the way human interlocutors provide spontaneous unsolicited feedback to each…
Interactive sentiment analysis is an emerging, yet challenging, subtask of the sentiment analysis problem. It aims to discover the affective state and sentimental change of each person in a conversation. Existing sentiment analysis…
The ability to generate sentiment-controlled feedback in response to multimodal inputs comprising text and images addresses a critical gap in human-computer interaction. This capability allows systems to provide empathetic, accurate, and…
The ability to combine linguistic guidance from others with direct experience is central to human development, enabling safe and rapid learning in new environments. How do people integrate these two sources of knowledge, and how might AI…
Evaluating developer satisfaction with conversational AI assistants at scale is critical but challenging. User studies provide rich insights, but are unscalable, while large-scale quantitative signals from logs or in-product ratings are…
One challenge for dialogue agents is recognizing feelings in the conversation partner and replying accordingly, a key communicative skill. While it is straightforward for humans to recognize and acknowledge others' feelings in a…
Instruction tuning is crucial for enabling Large Language Models (LLMs) to solve real-world tasks. Prior work has shown the effectiveness of instruction-tuning data synthesized solely from LLMs, raising a fundamental question: Do we still…
Software is used in critical applications in our day-to-day life and it is important to ensure its correctness. One popular approach to assess correctness is to evaluate software on tests. If a test fails, it indicates a fault in the…
Imitation learning has shown success in many tasks by learning from expert demonstrations. However, most existing work relies on large-scale demonstrations from technical professionals and close monitoring of the training process. These are…
Idioms are figurative expressions whose meanings often cannot be inferred from their individual words, making them difficult to process computationally and posing challenges for human experimental studies. This survey reviews datasets…
Building on prior research on Generative AI (GenAI) and related tools for programming education, we developed SCRIPT, a chatbot based on ChatGPT-4o-mini, to support novice learners. SCRIPT allows for open-ended interactions and structured…
The knowledge of scripts, common chains of events in stereotypical scenarios, is a valuable asset for task-oriented natural language understanding systems. We propose the Goal-Oriented Script Construction task, where a model produces a…
Script learning studies how stereotypical events unfold, enabling machines to reason about narratives with implicit information. Previous works mostly consider a script as a linear sequence of events while ignoring the potential branches…
Inter-personal relationship is the basis of human society. In order to automatically identify the relations between persons from texts, we need annotated data for training systems. However, there is a lack of a massive amount of such data…
Recent advancements in dialogue generation have broadened the scope of human-bot interactions, enabling not only contextually appropriate responses but also the analysis of human affect and sensitivity. While prior work has suggested that…
In this paper, we have defined a novel task of affective feedback synthesis that deals with generating feedback for input text & corresponding image in a similar way as humans respond towards the multimodal data. A feedback synthesis system…
In recent years, instruction tuning has gained increasing attention and emerged as a crucial technique to enhance the capabilities of Large Language Models (LLMs). To construct high-quality instruction datasets, many instruction processing…
We ran a study on engagement and achievement for a first year undergraduate programming module which used an online learning environment containing tasks which generate automated feedback. Students could also access human feedback from…
In an information-seeking conversation, a user may ask questions that are under-specified or unanswerable. An ideal agent would interact by initiating different response types according to the available knowledge sources. However, most…
Contextual commonsense inference is the task of generating various types of explanations around the events in a dyadic dialogue, including cause, motivation, emotional reaction, and others. Producing a coherent and non-trivial explanation…