Pith. sign in

REVIEW 4 cited by

Graph Reasoning for Question Answering with Triplet Retrieval

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2305.18742 v1 pith:MXMAUHK2 submitted 2023-05-30 cs.CL

Shiyang Li , Yifan Gao , Haoming Jiang , Qingyu Yin , Zheng Li , Xifeng Yan , Chao Zhang , Bing Yin This is my paper · ORCID
classification cs.CL
keywords answeringlocalquestionquestionsthengraphknowledgelanguage
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Answering complex questions often requires reasoning over knowledge graphs (KGs). State-of-the-art methods often utilize entities in questions to retrieve local subgraphs, which are then fed into KG encoder, e.g. graph neural networks (GNNs), to model their local structures and integrated into language models for question answering. However, this paradigm constrains retrieved knowledge in local subgraphs and discards more diverse triplets buried in KGs that are disconnected but useful for question answering. In this paper, we propose a simple yet effective method to first retrieve the most relevant triplets from KGs and then rerank them, which are then concatenated with questions to be fed into language models. Extensive results on both CommonsenseQA and OpenbookQA datasets show that our method can outperform state-of-the-art up to 4.6% absolute accuracy.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

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

  1. KAMR: Grounding Generation via Knowledge-Aligned Multi-hop Retrieval

    cs.IR 2026-07 conditional novelty 6.0 of 10

    Partial-alignment contrastive pretraining plus anchor-then-expand graph retrieval improves multi-hop KG evidence recovery and downstream QA over strong dense and graph RAG baselines.

  2. GPR: Empowering Generation with Graph-Pretrained Retriever

    cs.IR 2025-05 conditional novelty 5.0 of 10

    GPR pretrains a two-tower retriever on knowledge graphs using LLM-generated questions from masked triplets and a soft-preference triplet loss, improving KGQA accuracy across datasets and LLMs.

  3. DistRAG: Towards Distance-Based Spatial Reasoning in LLMs

    cs.CL 2025-06 conditional novelty 4.0 of 10

    Retrieving distance facts from a spatial graph improves LLM answers to direct and nearest-city distance questions, while complex distance-comparison questions remain unsolved.

  4. KARE-RAG: Knowledge-Aware Refinement and Enhancement for RAG

    cs.CL 2025-06 conditional novelty 4.0 of 10

    Training RAG generators on contrastive knowledge-graph pairs with weighted DPO improves average exact-match by 1.8 to 4.2 points across three model sizes.

Pith tools