paper-with-me

Graph Question Answering

1개 벤치마크 · 논문 140편 · 이 태스크의 논문 보기 →

Benchmarks

GQA

결과 2개

Most implemented

Papers

The Answer Path and the Grounding Instruction in LLM Question Answering over Knowledge Graphs

2026-09-09 · Arquimedes Canedo arxiv

A graph retrieval-augmented generation pipeline chooses which triples to put in the prompt, a syntax to write them in, an order to write them in, and a sentence telling the model what to do with them. We vary all four ov…

Graph Question AnsweringKnowledge Graphs

Query-Side Attacks on GNN-Based KGQA: Tracing Failures from Entity Linking to Answer Generation

2026-08-26 · Pankaj Kumar, Subhankar Mishra arxiv

GNN-based Knowledge Graph Question Answering (KGQA) pipelines process queries through four discrete stages: entity linking, subgraph retrieval, GNN reasoning, and answer generation. Standard robustness evaluations confla…

Graph Question AnsweringAnswer GenerationEntity Linking

Compositional Chain-of-Relations for Faithful Knowledge Graph Question Answering with Large Language Models

2026-08-24 · Chenhui Liu, Jianpeng Zhou, Jiahai Wang arxiv

Knowledge graph question answering (KGQA) is a key task for evaluating KG-augmented Large Language Models (LLMs), and complex KGQA that requires multi-hop reasoning is especially challenging. Solving a complex query invo…

Graph Question Answering

SABET-QA: Temporal Knowledge Graph Question Answering

2026-08-20 · Brahim Touayouch, Mirette Moawad, Dmitry Akulov arxiv

Question Answering over Temporal Knowledge Graphs (TKGQA) requires reasoning over time-sensitive facts, yet existing embedding-based methods struggle with multi-step queries due to single-pass reasoning pipelines. We pro…

Graph Question AnsweringKnowledge Graphs

MissDiag: Diagnostic Evaluation of Incomplete-Knowledge Robustness in KGQA and KG-RAG

2026-08-19 · Hang Wang, Hang Dong, Lu Liu, Chuanru Ren arxiv

Knowledge graph question answering (KGQA) and knowledge-graph-based retrieval-augmented generation (KG-RAG) aim to ground answers in explicit graph evidence, but real-world knowledge graphs are often sparse, outdated, an…

Graph Question AnsweringKnowledge Graphs

MARS: Multi-hop Adaptive Retrieval and SPARQL Generation for KGQA

2026-07-16 · Nikit Srivastava, Daniel Vollmers, René Speck, Nikolaos Karalis 외 arxiv

Large language models (LLMs) have demonstrated strong reasoning performance, but their tendency to hallucinate limits their reliability in knowledge-intensive tasks requiring up-to-date and grounded information. Combinin…

Graph Question AnsweringKnowledge Graphs

전체 140편 보기 →