Pith. sign in

REVIEW 7 cited by

QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2104.06378 v5 pith:RMFBT6KB submitted 2021-04-13 cs.CL cs.LG

classification cs.CLcs.LG
keywords contextknowledgereasoningjointmodelsqa-gnnansweringchallenges
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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 from large KGs, and (ii) perform joint reasoning over the QA context and KG. In this work, we propose a new model, QA-GNN, which addresses the above challenges through two key innovations: (i) relevance scoring, where we use LMs to estimate the importance of KG nodes relative to the given QA context, and (ii) joint reasoning, where we connect the QA context and KG to form a joint graph, and mutually update their representations through graph neural networks. We evaluate our model on QA benchmarks in the commonsense (CommonsenseQA, OpenBookQA) and biomedical (MedQA-USMLE) domains. QA-GNN outperforms existing LM and LM+KG models, and exhibits capabilities to perform interpretable and structured reasoning, e.g., correctly handling negation in questions.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Bridging the Question-Answer Gap in Retrieval-Augmented Generation: Hypothetical Prompt Embeddings

    cs.IR 2026-07 conditional novelty 6.0 of 10

    Precomputing hypothetical question embeddings for each text chunk at indexing time shifts retrieval to question–question matching and improves context precision and claim recall in RAG.

  2. Poisson-Gamma Modeling of Inter-Relational Dependencies in Dynamic Knowledge Graphs

    cs.LG 2026-07 conditional novelty 6.0 of 10

    A Gamma-Markov multi-relational Poisson model with an explicit relation-transition kernel improves sparse dynamic KG link prediction and recovers interpretable inter-relation dynamics.

  3. Youtu-GraphRAG: Vertically Unified Agents for Graph Retrieval-Augmented Complex Reasoning

    cs.IR 2025-08 conditional novelty 6.0 of 10

    A schema-bounded agentic framework unifies graph construction and retrieval, reporting SOTA accuracy and up to 90.71% token-cost savings across six benchmarks, plus a new anonymized QA dataset.

  4. IMoRe: Implicit Program-Guided Reasoning for Human Motion Q&A

    cs.CV 2025-08 conditional novelty 6.0 of 10

    IMoRe couples a MAC-style memory network with program-function embeddings and multi-level ViT motion features to reach state-of-the-art accuracy on Babel-QA and a new HuMMan-QA benchmark.

  5. Explainable Knowledge Graph Retrieval-Augmented Generation (KG-RAG) with KG-SMILE

    cs.AI 2025-09 reject novelty 4.0 of 10

    KG-SMILE applies perturbation and linear regression to a knowledge graph to attribute which entities and relations drive a GraphRAG system's answers.

  6. T-CPDL: A Temporal Causal Probabilistic Description Logic for Developing Logic-RAG Agent

    cs.AI 2025-06 reject novelty 4.0 of 10

    T-CPDL combines temporal, causal, and probabilistic operators into a Description Logic intended to support logic-enhanced RAG, but the preprint supplies only a syntax sketch and unverified theorems.

  7. Aligning Knowledge Graphs and Language Models for Factual Accuracy

    cs.CL 2025-07 conditional novelty 3.0 of 10

    ALIGNed-LLM aligns knowledge graph entity embeddings with language model text embeddings through a trainable projection layer, improving question answering accuracy on KG-derived datasets.

Pith tools