Related papers: Scalable XML Collaborative Editing with Undo short…
Knowledge editing has become a promising approach for efficiently and precisely updating knowledge embedded in large language models (LLMs). In this work, we focus on Same-Subject Editing, which involves modifying multiple attributes of a…
Large language models (LLMs) and classical machine learning methods offer complementary strengths for predictive modeling, yet their fundamentally different representations and training paradigms hinder effective integration: LLMs rely on…
Replication ensures data availability in fault-prone distributed systems. The celebrated CAP theorem stipulates that replicas cannot guarantee both strong consistency and availability under network partitions. A popular alternative, adopted…
Conflict-Free Replicated Data Types (CRDTs) are used in a range of fields for their coordination-free replication with strong eventual consistency. By prioritising availability over consistency under partition, peers accumulate events in…
Visual Document Retrieval (VDR) is an emerging research area that focuses on encoding and retrieving document images directly, bypassing the dependence on Optical Character Recognition (OCR) for document search. A recent advance in VDR was…
This paper proposes Commutative Event Sourcing as a simple and reliable mechanism for model synchronisation, bidirectional model to model transformations, incremental updates, and collaborative editing. Commutative Event Sourcing is a…
Data integrity is the fundamental for data authentication. A major problem for XML data authentication is that signed XML data can be copied to another document but still keep signature valid. This is caused by XML data integrity…
XSLT is an increasingly popular language for processing XML data. It is widely supported by application platform software. However, little optimization effort has been made inside the current XSLT processing engines. Evaluating a very…
Mechanistic interpretability seeks to understand how Large Language Models (LLMs) represent and process information. Recent approaches based on dictionary learning and transcoders enable representing model computation in terms of sparse,…
Learning policy from offline datasets through offline reinforcement learning (RL) holds promise for scaling data-driven decision-making while avoiding unsafe and costly online interactions. However, real-world data collected from sensors or…
Retrieval-augmented language models can better adapt to changes in world state and incorporate long-tail knowledge. However, most existing methods retrieve only short contiguous chunks from a retrieval corpus, limiting holistic…
In today's Web and social network environments, query workloads include ad hoc and OLAP queries, as well as iterative algorithms that analyze data relationships (e.g., link analysis, clustering, learning). Modern DBMSs support ad hoc and…
Large Language Models (LLMs) need to adapt to the continuous changes in data, tasks, and user preferences. Due to their massive size and the high costs associated with training, LLMs are not suitable for frequent retraining. However,…
Vertical-domain large language models (LLMs) play a crucial role in specialized scenarios such as finance, healthcare, and law; however, their training often relies on large-scale annotated data and substantial computational resources,…
All 26 neural network merge strategies we tested including weight averaging, SLERP, TIES, DARE, Fisher merging, and evolutionary approaches -- fail the algebraic properties (commutativity, associativity, idempotency) required for…
As real-world knowledge evolves, the information embedded within large language models (LLMs) can become outdated, inadequate, or erroneous. Model editing has emerged as a prominent approach for updating LLMs' knowledge with minimal…
The XTR (conteXtual Token Retrieval) algorithm is a modification to ColBERT retrieval that avoids the costly step of fully gathering and reranking the candidates' embeddings by imputing their missing similarity scores from the initial token…
Interactive image restoration aims to generate restored images by adjusting a controlling coefficient which determines the restoration level. Previous works are restricted in modulating image with a single coefficient. However, real images…
Generative retrieval (GR) reformulates the Information Retrieval (IR) task as the generation of document identifiers (docIDs). Despite its promise, existing GR models exhibit poor generalization to newly added documents, often failing to…
***** This design is a duplicate of a Causal Length Set (see notes in the comments). We leave nonetheless the original paper here because the proofs are referred to in another submission.***** The 2P-Set Conflict-Free Replicated Data Type…