相关论文: Compositional Model Checking of Consensus Protocol…
Blockchains use consensus protocols to reach agreement, e.g., on the ordering of transactions. DAG-based consensus protocols are increasingly adopted by blockchain companies to reduce energy consumption and enhance security. These protocols…
Human annotation remains the foundation of reliable and interpretable data in Natural Language Processing (NLP). As annotation and evaluation tasks continue to expand, from categorical labelling to segmentation, subjective judgment, and…
We present Alias Refinement Types (ART), a new approach to the verification of correctness properties of linked data structures. While there are many techniques for checking that a heap-manipulating program adheres to its specification,…
Humans understand new combinations of words encountered if they are combinations of words recognized from different contexts, an ability called Compositional Generalization. The COGS benchmark (Kim and Linzen, 2020) arXiv:2010.05465 reports…
With the ever-increasing demands on Question Answering (QA) systems for IT operations and maintenance, an efficient and supervised fine-tunable framework is necessary to ensure the data security, private deployment and continuous upgrading.…
Test-time adaptation (TTA) aims to transfer knowledge from a source model to unknown test data with potential distribution shifts in an online manner. Many existing TTA methods rely on entropy as a confidence metric to optimize the model.…
Question answering (QA) over tables and text has gained much popularity over the years. Multi-hop table-text QA requires multiple hops between the table and text, making it a challenging QA task. Although several works have attempted to…
The reconstruction of sparse signals from a limited set of measurements poses a significant challenge as it necessitates a solution to an underdetermined system of linear equations. Compressed sensing (CS) deals with sparse signal…
ZooKeeper is a coordination service, widely used as a backbone of various distributed systems. Though its reliability is of critical importance, testing is insufficient for an industrial-strength system of the size and complexity of…
A data integration system provides transparent access to different data sources by suitably combining their data, and providing the user with a unified view of them, called global schema. However, source data are generally not under the…
Retrieval-Augmented Generation (RAG) has become a standard approach for enhancing large language models (LLMs) with external knowledge, mitigating hallucinations, and improving factuality. However, existing systems rely on generating…
Massively multilingual language models enable cross-lingual generalization but underperform on low-resource and unseen languages. While adapter-based fine-tuning offers a parameter-efficient solution, training language-specific adapters at…
Preference alignment has emerged as an effective strategy to enhance the performance of Multimodal Large Language Models (MLLMs) following supervised fine-tuning. While existing preference alignment methods predominantly target…
The Improved Partial Area-Analytical Calculation (IPA-AC) method represents a leading meshfree discretization strategy for peridynamic models, distinguished by its rigorous geometric treatment of boundary intersections via dual corrections…
There are two popular general approaches for the analysis and visualization of a contingency table and a compositional data set: Correspondence analysis (CA) and log ratio analysis (LRA). LRA includes two independently well developed…
Operating LLMs as coordinated multi-agent research systems over multi-hour runs surfaces failure modes that single-shot evaluation cannot: upstream providers throttle without warning, sub-agents drift the task to fit accessible tools,…
Large Language Models (LLMs) are increasingly vulnerable to sophisticated multi-turn manipulation attacks, where adversaries strategically build context through seemingly benign conversational turns to circumvent safety measures and elicit…
The assurance of quality of service properties is an important aspect of service-oriented software engineering. Notations for so-called service level agreements (SLAs), such as the Web Service Level Agreement (WSLA) language, provide a…
Single Page Applications (SPAs) are different than hypertext-based web applications in that their workflow is not defined by explicit links, but rather implicitly by changes of their widgets' states. The workflow may hence be hard to track.…
Despite impressive capabilities, LLMs' successes often rely on pattern-matching behaviors, yet these are also linked to OOD generalization failures in compositional tasks. However, behavioral studies commonly employ task setups that allow…