Related papers: From Binary Groundedness to Support Relations: Tow…

In an era increasingly dominated by digital platforms, the spread of misinformation poses a significant challenge, highlighting the need for solutions capable of assessing information veracity. Our research contributes to the field of…

Calls for new metrics, technical standards and governance mechanisms to guide the adoption of Artificial Intelligence (AI) in institutions and public administration are now commonplace. Yet, most research and policy efforts aimed at…

Building machines that can understand text like humans is an AI-complete problem. A great deal of research has already gone into this, with astounding results, allowing everyday people to discuss with their telephones, or have their reading…

Retrieval-augmented generation (RAG) improves large language model reliability by grounding generated responses in external evidence. However, RAG performance depends on the relevance of retrieved passages, the quality of evidence ranking,…

Qualitative relationships describe how increasing or decreasing one property (e.g. altitude) affects another (e.g. temperature). They are an important aspect of natural language question answering and are crucial for building chatbots or…

Foundation models, such as large language models (LLMs), have been widely recognised as transformative AI technologies due to their capabilities to understand and generate content, including plans with reasoning capabilities. Foundation…

The increasing prevalence of AI-generated content alongside human-written text underscores the need for reliable discrimination methods. To address this challenge, we propose a novel framework with textual embeddings from Pre-trained…

Generative search engines and deep research LLM agents promise trustworthy, source-grounded synthesis, yet users regularly encounter overconfidence, weak sourcing, and confusing citation practices. We introduce DeepTRACE, a novel…

Large language models (LLMs) produce seemingly meaningful outputs, yet they are trained on text alone without direct interaction with the world. This leads to a modern variant of the classical symbol grounding problem in AI: can LLMs'…

Intelligent assistants that follow commands or answer simple questions, such as Siri and Google search, are among the most economically important applications of AI. Future conversational AI assistants promise even greater capabilities and…

Retrieval augmented generation mitigates limitations of large language models in factual consistency and knowledge updating by introducing external knowledge. However, practical applications still suffer from semantic misalignment between…

In the wake of responsible AI, interpretability methods, which attempt to provide an explanation for the predictions of neural models have seen rapid progress. In this work, we are concerned with explanations that are applicable to natural…

Collaborative dialogue relies on participants incrementally establishing common ground, yet in asymmetric settings they may believe they agree while referring to different entities. We introduce a perspectivist annotation scheme for the…

Incorporating personas information allows diverse and engaging responses in dialogue response generation. Unfortunately, prior works have primarily focused on self personas and have overlooked the value of partner personas. Moreover, in…

Common ground plays a critical role in situated spoken dialogs, where interlocutors must establish and maintain shared references to entities, events, and relations to sustain coherent interaction in a shared space and over time. With the…

Answering open-ended questions remains challenging for AI systems because it requires synthesis, judgment, and exploration beyond factual retrieval, and users often refine answers through multiple iterations rather than accepting a single…

Generative AI can convert uncertainty into hypersuasive, authoritative-seeming verdicts, displacing the justificatory work on which democratic epistemic agency depends. As a corrective, I propose a Brouwer-inspired assertibility constraint…

The emergence of human-like abilities of AI systems for content generation in domains such as text, audio, and vision has prompted the development of classifiers to determine whether content originated from a human or a machine. Implicit in…

Explainable AI (XAI) interfaces seek to make large language models more transparent, yet explanation alone does not produce understanding. Explaining a system's behavior is not the same as being able to engage with it, to probe and…

Textual explanations have proved to help improve user satisfaction on machine-made recommendations. However, current mainstream solutions loosely connect the learning of explanation with the learning of recommendation: for example, they are…