相关论文: Identifying & Interactively Refining Ambiguous Use…
Users often ask dialogue systems ambiguous questions that require clarification. We show that current language models rarely ask users to clarify ambiguous questions and instead provide incorrect answers. To address this, we introduce CLAM:…
The requirements engineering process is a crucial stage of the software development life cycle. It involves various stakeholders from different professional backgrounds, particularly in the requirements elicitation phase. Each stakeholder…
The main goal of modeling human conversation is to create agents which can interact with people in both open-ended and goal-oriented scenarios. End-to-end trained neural dialog systems are an important line of research for such generalized…
The goal-oriented document-grounded dialogue aims at responding to the user query based on the dialogue context and supporting document. Existing studies tackle this problem by decomposing it into two sub-tasks: knowledge identification and…
Pervasive personal communication technologies offer the potential for important social benefits for individual users, but also the potential for significant social difficulties and costs. In research on face-to-face social interaction,…
Concerns that interacting with generative AI homogenizes human cognition are largely based on evidence from text-based interactions, potentially conflating the effects of AI systems with those of written communication. This study examines…
This study examines the role of vagueness in the design process and its strategic management for the effective human-AI interaction. While vagueness in the generation of design ideas promotes diverse interpretations and prevents fixation,…
Humans possess multimodal literacy, allowing them to actively integrate information from various modalities to form reasoning. Faced with challenges like lexical ambiguity in text, we supplement this with other modalities, such as thumbnail…
The Visual Dialogue task requires an agent to engage in a conversation about an image with a human. It represents an extension of the Visual Question Answering task in that the agent needs to answer a question about an image, but it needs…
Large language models generate complex, open-ended outputs: instead of outputting a class label they write summaries, generate dialogue, or produce working code. In order to asses the reliability of these open-ended generation systems, we…
Existing benchmarks used to evaluate the performance of end-to-end neural dialog systems lack a key component: natural variation present in human conversations. Most datasets are constructed through crowdsourcing, where the crowd workers…
Automated dialogue or conversational systems are anthropomorphised by developers and personified by users. While a degree of anthropomorphism may be inevitable due to the choice of medium, conscious and unconscious design choices can guide…
Story visualization aims to generate a sequence of images to narrate each sentence in a multi-sentence story, where the images should be realistic and keep global consistency across dynamic scenes and characters. Current works face the…
AI alignment is about ensuring AI systems only pursue goals and activities that are beneficial to humans. Most of the current approach to AI alignment is to learn what humans value from their behavioural data. This paper proposes a…
As language and visual understanding by machines progresses rapidly, we are observing an increasing interest in holistic architectures that tightly interlink both modalities in a joint learning and inference process. This trend has allowed…
Dialogue systems have many applications such as customer support or question answering. Typically they have been limited to shallow single turn interactions. However more advanced applications such as career coaching or planning a trip…
Generative AI tools such as ChatGPT now provide novice programmers with unprecedented access to instant, personalized support. While this holds clear promise, their influence on students' metacognitive processes remains underexplored.…
Where early work on dialogue in Computational Linguistics put much emphasis on dialogue structure and its relation to the mental states of the dialogue participants (e.g., Allen 1979, Grosz & Sidner 1986), current work mostly reduces…
The widespread adoption of large language and vision models in real-world applications has made urgent the need to address hallucinations -- instances where models produce incorrect or nonsensical outputs. These errors can propagate…
Accurate multi-turn intent classification is essential for advancing conversational AI systems. However, challenges such as the scarcity of comprehensive datasets and the complexity of contextual dependencies across dialogue turns hinder…