Related papers: Neural Scalable Symbolic Search Framework for Comp…
The problem of answering questions using knowledge from pre-trained language models (LMs) and knowledge graphs (KGs) presents two challenges: given a QA context (question and answer choice), methods need to (i) identify relevant knowledge…
Generative LLMs typically improve Named Entity Recognition (NER) performance through instruction tuning. They excel at generating entities by semantic pattern matching but lack an explicit, verifiable reasoning mechanism. This "cognitive…
Knowledge graphs (KGs) model facts about the world, they consist of nodes (entities such as companies and people) that are connected by edges (relations such as founderOf). Facts encoded in KGs are frequently used by search applications to…
Personal Artificial Intelligence is currently hindered by the fragmentation of user data across isolated silos. While Retrieval-Augmented Generation offers a partial remedy, its reliance on unstructured vector similarity fails to capture…
This paper proposes a novel hybrid neuro-symbolic framework for the optimal and scalable deployment of component-based applications in the Cloud. The challenge of efficiently mapping application components to virtual machines (VMs) across…
Critic-free methods like GRPO reduce memory demands by estimating advantages from multiple rollouts but tend to converge slowly, as critical learning signals are diluted by an abundance of uninformative samples and tokens. To tackle this…
Code localization is a cornerstone of autonomous software engineering. Recent advancements have achieved impressive performance on real-world issue benchmarks. However, we identify a critical yet overlooked bias: these benchmarks are…
Temporal Knowledge Graph Question Answering (TKGQA) is challenging because it requires multi-hop reasoning under complex temporal constraints. Recent LLM-based approaches have improved semantic modeling for this task, but many still rely on…
Visual reasoning over structured data such as tables is a critical capability for modern vision-language models (VLMs), yet current benchmarks remain limited in scale, diversity, or reasoning depth, especially when it comes to rendered…
Answering complex questions over textual resources remains a challenge, particularly when dealing with nuanced relationships between multiple entities expressed within natural-language sentences. To this end, curated knowledge bases (KBs)…
Complex Logical Query Answering (CLQA) involves intricate multi-hop logical reasoning over large-scale and potentially incomplete Knowledge Graphs (KGs). Although existing CLQA algorithms achieve high accuracy in answering such queries,…
Answering complex logical queries on incomplete knowledge graphs (KGs) with missing edges is a fundamental and important task for knowledge graph reasoning. The query embedding method is proposed to answer these queries by jointly encoding…
Answering first-order logic (FOL) queries over incomplete knowledge graphs (KGs) is difficult, especially for complex query structures that compose projection, intersection, union, and negation. We propose ROG, a retrieval-augmented…
We investigate a relatively underexplored class of hybrid neurosymbolic models integrating symbolic learning with neural reasoning to construct data generators meeting formal correctness criteria. In \textit{Symbolic Neural Generators}…
We introduce a structured quantum search algorithm that leverages entanglement maps and a fixed-point method to minimize oracle query complexity in unsorted datasets. By partitioning qubits into rows based on their entanglement order, the…
Chart Question Answering (CQA) aims at answering questions based on the visual chart content, which plays an important role in chart sumarization, business data analysis, and data report generation. CQA is a challenging multi-modal task…
The rapid evolution of Natural Language Processing (NLP) has favoured major languages such as English, leaving a significant gap for many others due to limited resources. This is especially evident in the context of data annotation, a task…
Many vision and language tasks require commonsense reasoning beyond data-driven image and natural language processing. Here we adopt Visual Question Answering (VQA) as an example task, where a system is expected to answer a question in…
Document Visual Question Answering (DocVQA) requires models to jointly understand textual semantics, spatial layout, and visual features. Current methods struggle with explicit spatial relationship modeling, inefficiency with…
This paper tackles the problem of the semantic gap between a document and a query within an ad-hoc information retrieval task. In this context, knowledge bases (KBs) have already been acknowledged as valuable means since they allow the…