Related papers: NM-DEKL$^3_\infty$: A Three-Layer Non-Monotone Evo…
Modern neural networks (NNs), trained on extensive raw sentence data, construct distributed representations by compressing individual words into dense, continuous, high-dimensional vectors. These representations are expected to capture…
Using the Triple Helix model of university-industry-government relations, one can measure the extent to which innovation has become systemic instead of assuming the existence of national (or regional) systems of innovations on a priori…
Representing knowledge as high-dimensional vectors in a continuous semantic vector space can help overcome the brittleness and incompleteness of traditional knowledge bases. We present a method for performing deductive reasoning directly in…
The unique capabilities of Large Language Models (LLMs), such as the natural language text generation ability, position them as strong candidates for providing explanation for recommendations. However, despite the size of the LLM, most…
Modern deep learning models have demonstrated outstanding performance on discovering the underlying mechanisms when both visual appearance and intrinsic relations (e.g., causal structure) data are sufficient, such as Disentangled…
Conversational semantic parsing over tables requires knowledge acquiring and reasoning abilities, which have not been well explored by current state-of-the-art approaches. Motivated by this fact, we propose a knowledge-aware semantic parser…
Understanding how large language models (LLMs) acquire, retain, and apply knowledge remains an open challenge. This paper introduces a novel framework, K-(CSA)^2, which categorizes LLM knowledge along two dimensions: correctness and…
This work addresses the 3D situated reasoning task which aims to answer questions given egocentric observations in a 3D environment. The task remains challenging as it requires comprehensive 3D perception and complex reasoning skills.…
Mathematical knowledge exists in many forms, ranging from informal textbooks and lecture notes to large formal proof libraries, yet moving between these representations remains difficult. Informal texts hide dependencies, while formal…
Understanding how Large Language Models (LLMs) perform logical reasoning internally remains a fundamental challenge. While prior mechanistic studies focus on identifying taskspecific circuits, they leave open the question of what…
The logico-pluralist LogiKEy knowledge engineering methodology and framework is applied to the modelling of a theory of legal balancing in which legal knowledge (cases and laws) is encoded by utilising context-dependent value preferences.…
The behaviour of systems characterised by a closed interaction of software components with the environment is inevitably subject to perturbations and uncertainties. In this paper we propose a general framework for the specification and…
Synthesizing high-quality training data is crucial for enhancing domain models' reasoning abilities. Existing methods face limitations in long-tail knowledge coverage, effectiveness verification, and interpretability. Knowledge-graph-based…
Large Vision-Language Models (LVLMs) are gradually becoming the foundation for many artificial intelligence applications. However, understanding their internal working mechanisms has continued to puzzle researchers, which in turn limits the…
As reasoning LLMs increasingly trade tokens for accuracy through deliberation, search, and self-correction, a single accuracy score can no longer tell whether those tokens buy useful reasoning, recovery from hard instances, or unnecessary…
Named entity recognition is one of the core tasks in NLP. Although many improvements have been made on this task during the last years, the state-of-the-art systems do not explicitly take into account the recursive nature of language.…
Decoder-only transformers have become the standard architecture for large language models (LLMs) due to their strong performance. Recent studies suggest that, in pre-trained LLMs, early, middle, and late layers may serve distinct roles:…
Uncertainty decomposition refers to the task of decomposing the total uncertainty of a predictive model into aleatoric (data) uncertainty, resulting from inherent randomness in the data-generating process, and epistemic (model) uncertainty,…
Semantic data and knowledge infrastructures must reconcile two fundamentally different forms of representation: natural language, in which most knowledge is created and communicated, and formal semantic models, which enable…
This paper describes an architecture that combines the complementary strengths of declarative programming and probabilistic graphical models to enable robots to represent, reason with, and learn from, qualitative and quantitative…