arXiv:2407. 11821v2 Announce Type: replace Abstract: Statistical information is ubiquitous but drawing valid conclusions from it is prohibitively hard.
arXiv:2504. 03635v4 Announce Type: replace Abstract: Reasoning is a core capability of language models (LMs), yet it remains unclear how much model capacity is necessary to support reasoning during pretraining.
arXiv:2607. 07422v1 Announce Type: new Abstract: Logical Multi-Hop Query Answering over Knowledge Graphs (KGs) can be formulated as querying, with an implicit completeness assumption.
arXiv:2508. 06706v2 Announce Type: replace Abstract: Rule-based methods for knowledge graph completion provide explainable results, but often require tens of thousands of rules to achieve competitive performance.
The paper introduces LitEm, a neural regression model that allows transductive knowledge graph embedding models to predict numerical attributes. LitEm achieves top or near‑top performance on most attributes across datasets such as FB15K‑237, YAGO15K, DB15K, and Mutagenesis. A co‑training framework further improves link prediction for bilinear models while enabling them to predict numerical attributes, demonstrating literal‑aware encoding of attribute information.
arXiv:2608.30652v1 Announce Type: new Abstract: Embedding methods have become popular due to their scalability on link prediction and/or triple classification tasks on Knowledge Graphs (KGs). Embeddi...
FedV-KGQA is a framework for multi-hop question answering over knowledge graphs that are vertically partitioned across different organizations. It allows entities to be shared while each silo retains disjoint sets of relations, using local graph enrichment and knowledge graph embeddings so that raw triples and relation parameters never leave the silo. The system includes a topic entity anchoring mechanism to ground questions in the correct graph neighborhood without runtime inter-silo communication, and it achieves performance close to centralized systems on three benchmarks, including 3-hop reasoning and robustness to embedding perturbations.
arXiv:2609.39786v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly combined with knowledge graphs (KGs) to ground reasoning in structured evidence. However, most LLM-based...
The paper investigates how Large Language Models can be used to approximate domain expert priors for Bayesian Networks by extracting probabilistic knowledge about real‑world events. Experiments on eighty publicly available networks across domains such as healthcare and finance show that LLM‑derived conditional probabilities outperform random, uniform, and next‑token baselines. The authors also demonstrate that these LLM‑generated priors can refine data‑driven distributions, especially when data is scarce, and provide the first comprehensive baseline for evaluating LLM performance in probabilistic knowledge extraction.
SLogic introduces a subgraph-informed approach to logical rule learning for knowledge graph completion, assigning query-dependent scores to rules instead of a single global weight. The framework uses a context-aware scoring function that evaluates the importance of a rule based on the local subgraph around the query’s head entity, aligning with the specificity principle of commonsense reasoning. Experiments on benchmark datasets demonstrate that SLogic performs competitively with other rule-based methods while producing human-readable, query-specific explanations.
arXiv:2606. 19264v1 Announce Type: new Abstract: The knowledge encoded in large language models (LLMs) can serve as a substrate for structured reasoning over variables describing a complex world, but accessing this knowledge in a probabilistically coherent manner poses a difficult inference problem.
arXiv:2606. 16603v1 Announce Type: cross Abstract: LLM-based agents have demonstrated strong capabilities in data-intensive analytical tasks, yet their outputs are rarely verifiable: a reliance on linear text trajectories makes their reasoning difficult to audit.
arXiv:2609.15007v1 Announce Type: cross Abstract: Large language models are increasingly used as natural-language interfaces to structured data, yet they remain unreliable when answers require consis...