20 results for “graph-driven reasoning”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
A graph-driven reasoning framework is proposed to automate compliance checks for geometry-intensive regulations in BIM.
The paper introduces GraphARC, a new benchmark for abstract reasoning on graph-structured data, demonstrating that current state-of-the-art language models struggle with full graph transformation task…
Improves accuracy and reduces generation length of large language models
Sjoerd Vink, Suyang Li, Brian Montambault, Michael Behrisch +2 more
This paper introduces ZipLine, a system for integrative analysis of multivariate graphs through a unified predicate language and learning algorithm.
The paper proposes a solution to the lack of compositionality in graph query languages GQL and SQL/PGQ.
Zerui Chen, Qinggang Zhang, Zhishang Xiang, Zhimin Wei +4 more
LegalGraphRAG introduces a multi-agent, hierarchical graph retrieval-augmented generation framework to overcome the limitations of traditional RAG in legal domains, achieving state-of-the-art reliable…
Haoxiang Cheng, Yunfei Wang, Chao Chen, Kewei Cheng +4 more
The paper proposes GRiD, a novel framework that uses a two-phase training strategy (supervised pre-training and RL fine-tuning) to discover complex, graph-like rules for knowledge graph reasoning, ove…
This paper presents TypoNet, a system that constructs and validates a symbolic model of a production-scale WAN from network artifacts using large language models for translation and a solver for relia…
Maëlic Neau, Salim Baloch, Jakob Suchan, Zoe Falomir +1 more
The paper proposes a model-agnostic framework to improve scene graph generation models under annotation sparsity by capturing visual commonsense knowledge.
The paper introduces graph linear notation as an alternative definition for finite graphs, simplifying graph illustration and isomorphism comparison.
Peter Belcak, Greg Heinrich, Saurav Muralidharan, Shizhe Diao +1 more
The paper introduces agentic reasoning caching, a method to efficiently apply solutions to new problems using language models.
PlanarBench introduces a novel benchmark to test LLM spatial reasoning by requiring them to draw planar graphs as ASCII art from an edge list, finding that edge count is a stronger difficulty predicto…
The paper evaluates LLM reasoning on Boolean satisfiability (SAT) problems, concluding that conventional metrics are misleading and proposing a paired-formula protocol with Accurate Differentiation Ra…
The paper proposes a neuro-symbolic framework to construct highly consistent knowledge graphs for complex question answering by performing ontology-grounded corrections in a post-extraction stage.