Papers › Knowledge Graph Prompting for Multi-Document Question Answering

Knowledge Graph Prompting for Multi-Document Question Answering

22 Aug 2023arXiv:2308.11730archive 2025-07-28

Yu Wang, Nedim Lipka, Ryan A. Rossi, Alexa Siu, Ruiyi Zhang, Tyler Derr

The `pre-train, prompt, predict' paradigm of large language models (LLMs) has achieved remarkable success in open-domain question answering (OD-QA). However, few works explore this paradigm in the scenario of multi-document question answering (MD-QA), a task demanding a thorough understanding of the logical associations among the contents and structures of different documents. To fill this crucial gap, we propose a Knowledge Graph Prompting (KGP) method to formulate the right context in prompting LLMs for MD-QA, which consists of a graph construction module and a graph traversal module. For graph construction, we create a knowledge graph (KG) over multiple documents with nodes symbolizing passages or document structures (e.g., pages/tables), and edges denoting the semantic/lexical similarity between passages or intra-document structural relations. For graph traversal, we design an LLM-based graph traversal agent that navigates across nodes and gathers supporting passages assisting LLMs in MD-QA. The constructed graph serves as the global ruler that regulates the transitional space among passages and reduces retrieval latency. Concurrently, the graph traversal agent acts as a local navigator that gathers pertinent context to progressively approach the question and guarantee retrieval quality. Extensive experiments underscore the efficacy of KGP for MD-QA, signifying the potential of leveraging graphs in enhancing the prompt design for LLMs. Our code: https://github.com/YuWVandy/KG-LLM-MDQA.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2308.11730")

Code

Syntology Ran 15 of 17 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 15 ran with no contract checked.

By repository: official repository: 17 samples from 1 repository, 15 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

yuwvandy/kg-llm-mdqa officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

17 samples harvested; 15 ran; 0 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

15ran
2unverified

Licence: 17 of the 17 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from yuwvandy/kg-llm-mdqa. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

Dataset_collate yuwvandy/kg-llm-mdqa/DPR/loader.py official repository ran no licence file found · pointer only · bcb6a2f9dffc4de8 · report
check_answer yuwvandy/kg-llm-mdqa/DPR/evaluation.py official repository ran no licence file found · pointer only · 25de4cd985d9cf87 · report
collate_tokens yuwvandy/kg-llm-mdqa/DPR/loader.py official repository ran no licence file found · pointer only · 1935b354c2dfc484 · report
diG_ratio_nei_overlap yuwvandy/kg-llm-mdqa/Data-Collect/count_nei_overlap.py official repository ran no licence file found · pointer only · 181d05538fbeb8a1 · report
has_answer yuwvandy/kg-llm-mdqa/DPR/evaluation.py official repository ran no licence file found · pointer only · 2075373a61e75fd7 · report
load_dataset yuwvandy/kg-llm-mdqa/DPR/dataset.py official repository ran no licence file found · pointer only · b5110e3368d3de74 · report
load_dataset_inf yuwvandy/kg-llm-mdqa/DPR/dataset.py official repository ran no licence file found · pointer only · eecdb8aefda2aec2 · report
load_saved yuwvandy/kg-llm-mdqa/DPR/utils.py official repository ran no licence file found · pointer only · 69c2c7b48e030046 · report
move_to_cuda yuwvandy/kg-llm-mdqa/DPR/utils.py official repository ran no licence file found · pointer only · 0be1ea343ffa7c85 · report
mp_loss yuwvandy/kg-llm-mdqa/DPR/learn.py official repository ran no licence file found · pointer only · 27c848a2b411a83e · report
multiG_ratio_nei_overlap yuwvandy/kg-llm-mdqa/Data-Collect/count_nei_overlap.py official repository ran no licence file found · pointer only · 976d0ff530b8e0c1 · report
normalize_answer yuwvandy/kg-llm-mdqa/DPR/evaluation.py official repository ran fingerprinted no licence file found · pointer only · 4cca112e5e6da5dc · report
run yuwvandy/kg-llm-mdqa/DPR/main_eval.py official repository ran no licence file found · pointer only · cd4656b6c628c145 · report
run yuwvandy/kg-llm-mdqa/Data-Collect/mdr_encode.py official repository ran no licence file found · pointer only · 29f0e538be5cfceb · report
wat_annotations yuwvandy/kg-llm-mdqa/Data-Collect/graph_construct.py official repository ran no licence file found · pointer only · 0e5b1c99eaeb69b8 · report
wat_entity_linking yuwvandy/kg-llm-mdqa/Data-Collect/graph_construct.py official repository unverified no licence file found · pointer only · 4dbe24f676f0e199 · report
wiki_kw_extract_chunk yuwvandy/kg-llm-mdqa/Data-Collect/graph_construct.py official repository unverified no licence file found · pointer only · 720ae0d197ca6652 · report

Tasks

Open-Domain Question AnsweringQuestion AnsweringRetrievalgraph construction

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections