SABET-QA: Temporal Knowledge Graph Question Answering

MGIT: Multi-Granularity implicit temporal framework for knowledge graph question answering

A Multi-Granularity Implicit Temporal (MGIT) framework that enhances temporal representation and reasoning by modeling implicit temporal dependencies across different granularities is proposed, highlighting its effectiveness in capturing implicit temporal information and enhancing multi-granularity temporal reasoning.

Repair Before Reinforce: Context-Augmented Knowledge Graph Reasoning for Multi-Hop Question Answering

Question-answering often requires reasoning across multiple connected facts rather than retrieving a single isolated relation. Knowledge graphs (KGs) provide a structured way to represent such facts, but training large language models (LLMs) only on isolated KG head-relation-tail triples may limit their ability to learn the surrounding context needed for multi-hop reasoning. In this work, we propose a context-augmented training framework for multi-hop question-answering. Although generally applicable, we validate the framework in the context of disease-specific KGs, extracted using a reliable KG extraction framework called GraphMERT, for Gastroparesis and Diabetes. For each primary KG triple, we attach supporting triples extracted from the same source text chunk to form a context graph (CG). This creates two supervision settings: KG-grounded supervision, which uses only the target KG triple or path, and CG-grounded supervision, which uses the target KG triple or path together with supporting context triples. We train the Qwen3-14B model using supervised fine-tuning (SFT) under both settings, producing KGModel and CGModel variants. To strengthen the lower-hop factual foundation of the models, we introduce an LLM-judged, history-aware adaptive repair pipeline that identifies unresolved one-hop failures, continually fine-tunes on targeted repair examples, and removes or quarantines problematic noisy triples. This repair stage enables the models to reach 100% accuracy on the cleaned retained one-hop validation sets. Finally, we employ reinforcement learning (RL) using lower-hop question-answer items and evaluate generalization on harder 3-hop, 4-hop, and 5-hop tasks. Across both diseases, context-augmented supervision consistently improves multi-hop performance over KG-only supervision. RL initialized from repaired SFT checkpoints yields larger and more stable gains.

Temporal Knowledge Graph Forecasting via Constrained Large Language Models

FITTER: Vocabulary-Agnostic Cross-Domain Inference on Temporal Knowledge Graphs

FITTER consistently outperforms inductive baselines without retraining, indicating that vocabulary-agnostic structural learning is a viable foundation for inference over the heterogeneous knowledge graphs of the Semantic Web.

SelfGraphRAG: Bridging the Supervision Gap in Graph-Based RAG with Synthetic QA Generation

SelfGraphRAG, a framework that generates question-answer pairs directly from knowledge graph structure and uses them to train a query-conditioned graph retriever, suggests that knowledge graph structure can provide useful supervision for training graph retrievers when labeled data are unavailable.

DocTrace: Towards Traceable Long Document VQA via Hierarchical Evidence Graph Reasoning

This paper proposes DocTrace, a hierarchical framework that progressively performs evidence localization, structured document parsing, and evidence graph reasoning to enable explicit evidence provenance, and develops a two-stage training framework.