Related papers: Improving the recall of decentralised linked data …
Existing large language models (LLMs) face challenges of following complex instructions, especially when multiple constraints are present and organized in paralleling, chaining, and branching structures. One intuitive solution, namely…
Offline reinforcement learning (RL) is a compelling paradigm to extend RL's practical utility by leveraging pre-collected, static datasets, thereby avoiding the limitations associated with collecting online interactions. The major…
Rank-revealing matrix decompositions provide an essential tool in spectral analysis of matrices, including the Singular Value Decomposition (SVD) and related low-rank approximation techniques. QR with Column Pivoting (QRCP) is usually…
Pseudo-relevance feedback (PRF) is a classical approach to address lexical mismatch by enriching the query using first-pass retrieval. Moreover, recent work on generative-relevance feedback (GRF) shows that query expansion models using text…
In this paper we analyse the functional requirements of linked data citation and identify a minimal set of operations and primitives needed to realize such task. Citing linked data implies solving a series of data provenance issues and…
Deep Learning (DL), especially with Large Language Models (LLMs), brings benefits to various areas. However, DL training systems usually yield prominent idling GPU resources due to many factors, such as resource allocation and collective…
Retrieval-augmented language models (RALMs) have recently shown great potential in mitigating the limitations of implicit knowledge in LLMs, such as untimely updating of the latest expertise and unreliable retention of long-tail knowledge.…
Network slicing promises to provision diversified services with distinct requirements in one infrastructure. Deep reinforcement learning (e.g., deep $\mathcal{Q}$-learning, DQL) is assumed to be an appropriate algorithm to solve the…
Transformer-based language models excel at both recall (retrieving memorized facts) and reasoning (performing multi-step inference), but whether these abilities rely on distinct internal mechanisms remains unclear. Distinguishing recall…
As systems are getting more autonomous with the development of artificial intelligence, it is important to discover the causal knowledge from observational sensory inputs. By encoding a series of cause-effect relations between events,…
Inference-time scaling has attracted much attention which significantly enhance the performance of Large Language Models (LLMs) in complex reasoning tasks by increasing the length of Chain-of-Thought. These longer intermediate reasoning…
Pseudo-relevance feedback (PRF) has proven to be an effective query reformulation technique to improve retrieval accuracy. It aims to alleviate the mismatch of linguistic expressions between a query and its potential relevant documents.…
This work is done as part of a research master's thesis project. The goal is to generate SPARQL queries based on user-supplied keywords to query RDF graphs. To do this, we first transformed the input ontology into an RDF graph that reflects…
Deep networks allow to obtain outstanding results in semantic segmentation, however they need to be trained in a single shot with a large amount of data. Continual learning settings where new classes are learned in incremental steps and…
With an increase in Geospatial Linked Open Data being adopted and published over the web, there is a need to develop intuitive interfaces and systems for seamless and efficient exploratory analysis of such rich heterogeneous multi-modal…
Reasoning over knowledge graphs is traditionally built upon a hierarchy of languages in the Semantic Web Stack. Starting from the Resource Description Framework (RDF) for knowledge graphs, more advanced constructs have been introduced…
We unveil that internal representations in large language models (LLMs) serve as reliable proxies of learned knowledge, and propose RECALL, a novel representation-aware model merging framework for continual learning without access to…
Machine unlearning for LLMs aims to remove sensitive or copyrighted data from trained models. However, the true efficacy of current unlearning methods remains uncertain. Standard evaluation metrics rely on benign queries that often mistake…
Class incremental learning (CIL) requires an agent to learn distinct tasks consecutively with knowledge retention against forgetting. Problems impeding the practical applications of CIL methods are twofold: (1) non-i.i.d batch streams and…
Residual learning has recently surfaced as an effective means of constructing very deep neural networks for object recognition. However, current incarnations of residual networks do not allow for the modeling and integration of complex…