Papers › ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering...

ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models

13 Oct 2023arXiv:2310.08975archive 2025-07-28

Haoran Luo, Haihong E, Zichen Tang, Shiyao Peng, Yikai Guo, Wentai Zhang, Chenghao Ma, Guanting Dong, Meina Song, Wei Lin, Yifan Zhu, Luu Anh Tuan

Knowledge Base Question Answering (KBQA) aims to answer natural language questions over large-scale knowledge bases (KBs), which can be summarized into two crucial steps: knowledge retrieval and semantic parsing. However, three core challenges remain: inefficient knowledge retrieval, mistakes of retrieval adversely impacting semantic parsing, and the complexity of previous KBQA methods. To tackle these challenges, we introduce ChatKBQA, a novel and simple generate-then-retrieve KBQA framework, which proposes first generating the logical form with fine-tuned LLMs, then retrieving and replacing entities and relations with an unsupervised retrieval method, to improve both generation and retrieval more directly. Experimental results show that ChatKBQA achieves new state-of-the-art performance on standard KBQA datasets, WebQSP, and CWQ. This work can also be regarded as a new paradigm for combining LLMs with knowledge graphs (KGs) for interpretable and knowledge-required question answering. Our code is publicly available.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 16 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 11 ran (7 with no instrument failure; 4 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 11 samples that ran has no recorded date.

lhrlab/chatkbqa officialmentioned in papermentioned on GitHubpytorchMITSyntology: 16 samples, 11 ran (4 instrument-failed) · 5 unverified 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

16 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
1ran · violated contract
4ran · our draft was wrong
4ran
5unverified

Licence: 4 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from lhrlab/chatkbqa. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

lhrlab/chatkbqa official repository 16 samples, 11 ran (4 instrument-failed) · 5 unverified
to_list in 62 papers config.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 9df40357afea56cc · report fixture: signature tensor:Tensor/2/float · returned list · level recorded, date not recorded
date_post_process eval_final.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 7c96e3db8ff7299a · report fixture: signature date_string:str/0/str · returned str · level recorded 2026-09-22
extract_entities in 6 papers components/expr_parser.py ran fingerprinted MIT (permissive) · e73dc55f0b4f1aed · report fixture: signature expr:str/0/str · returned list · level recorded 2026-09-24
extract_relations components/expr_parser.py ran fingerprinted MIT (permissive) · eb0198ee05eaa775 · report fixture: signature expr:str/0/str · returned list · level recorded 2026-09-24
httpPort Freebase-Setup/virtuoso.py ran · honoured contract fingerprinted MIT (permissive) · 2bc45468ebfe2d61 · report fixture: signature port:int/0/int · returned int · level recorded 2026-09-25
is_number in 70 papers eval_final.py ran · violated contract MIT (permissive) here; the stored copy is pointer only · b2feca00ae40a160 · report fixture: signature t:str/0/str · returned bool · level recorded 2026-09-22
isqlPort Freebase-Setup/virtuoso.py ran · honoured contract fingerprinted MIT (permissive) · f42bcb1c173e1a09 · report fixture: signature port:int/0/int · returned int · level recorded 2026-09-25
prepare_dataloader in 7 papers run_generator_final.py ran MIT (permissive) · 7600856fdde258c1 · report fixture: signature args:Args/0/? · returned list · level recorded 2026-09-24
run in 143 papers Freebase-Setup/virtuoso.py ran · our draft was wrong MIT (permissive) · acd5c28102430f1b · report fixture: signature command:str/0/str · returned bytes · level recorded 2026-09-25
tokenize_s_expr components/expr_parser.py ran fingerprinted MIT (permissive) · 75b1fc99101be3e8 · report fixture: signature expr:str/0/str · returned list · level recorded 2026-09-24
type_checker eval_final.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 038bd5a70277091b · report fixture: signature token:str/0/str · returned str · level recorded 2026-09-22
convert_cwq_sparql_instance parse_sparql_cwq.py unverified MIT (permissive) · 6f0de9ba1399e587 · report
convert_parse_instance parse_sparql_webqsp.py unverified MIT (permissive) · b6fede6aafdf9760 · report
convert_webqsp_sparql_instance parse_sparql_webqsp.py unverified MIT (permissive) · 0632af12ebb615dc · report
get_model_class in 12 papers config.py unverified MIT (permissive) · e267b92fe2e9c426 · report
load_untrained_model config.py unverified MIT (permissive) · e8cde2d16a8c1b7c · report

Tasks

Knowledge Base Question AnsweringKnowledge GraphsQuestion AnsweringRetrievalSemantic Parsing

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Knowledge Base Question Answering ComplexWebQuestions ChatKBQA Accuracy 76.8 #1 of 6 Archive leaderboard report
Knowledge Base Question Answering ComplexWebQuestions ChatKBQA F1 81.3 #1 of 6 Archive leaderboard report
Knowledge Base Question Answering ComplexWebQuestions ChatKBQA Hits@1 86.0 #1 of 6 Archive leaderboard report
Knowledge Base Question Answering WebQuestionsSP ChatKBQA Accuracy 77.8 #1 of 8 Archive leaderboard report
Knowledge Base Question Answering WebQuestionsSP ChatKBQA F1 83.5 #1 of 8 Archive leaderboard report
Knowledge Base Question Answering WebQuestionsSP ChatKBQA Hits@1 86.4 #1 of 8 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

BASE

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