Papers › UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with...

UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models

16 Jan 2022arXiv:2201.05966archive 2025-07-28

Tianbao Xie, Chen Henry Wu, Peng Shi, Ruiqi Zhong, Torsten Scholak, Michihiro Yasunaga, Chien-Sheng Wu, Ming Zhong, Pengcheng Yin, Sida I. Wang, Victor Zhong, Bailin Wang, Chengzu Li, Connor Boyle, Ansong Ni, Ziyu Yao, Dragomir Radev, Caiming Xiong, Lingpeng Kong, Rui Zhang, Noah A. Smith, Luke Zettlemoyer, Tao Yu

Structured knowledge grounding (SKG) leverages structured knowledge to complete user requests, such as semantic parsing over databases and question answering over knowledge bases. Since the inputs and outputs of SKG tasks are heterogeneous, they have been studied separately by different communities, which limits systematic and compatible research on SKG. In this paper, we overcome this limitation by proposing the UnifiedSKG framework, which unifies 21 SKG tasks into a text-to-text format, aiming to promote systematic SKG research, instead of being exclusive to a single task, domain, or dataset. We use UnifiedSKG to benchmark T5 with different sizes and show that T5, with simple modifications when necessary, achieves state-of-the-art performance on almost all of the 21 tasks. We further demonstrate that multi-task prefix-tuning improves the performance on most tasks, largely improving the overall performance. UnifiedSKG also facilitates the investigation of zero-shot and few-shot learning, and we show that T0, GPT-3, and Codex struggle in zero-shot and few-shot learning for SKG. We also use UnifiedSKG to conduct a series of controlled experiments on structured knowledge encoding variants across SKG tasks. UnifiedSKG is easily extensible to more tasks, and it is open-sourced at https://github.com/hkunlp/unifiedskg.

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="2201.05966")

Code

Syntology Ran 1 of 5 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 1 ran · our draft was wrong.

By repository: official repository: 5 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

hkunlp/unifiedskg officialmentioned in papermentioned on GitHubpytorchApache-2.0 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

5 samples harvested; 1 ran; 0 honoured the contract we drafted; 4 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.

1ran · our draft was wrong
4unverified

Licence: 0 of the 5 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 hkunlp/unifiedskg. “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.

shift_tokens_right hkunlp/unifiedskg/models/prompt/modeling_bart.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · a315b8fc32a18efe · report
aggregate_prompt hkunlp/unifiedskg/models/unified/combined_prefixtuning.py official repository unverified Apache-2.0 (permissive) · ff9289c16a83589c · report
compute_interaction_metric hkunlp/unifiedskg/metrics/sparc/interaction_scores.py official repository unverified Apache-2.0 (permissive) · eb8d0541d7792310 · report
evaluate hkunlp/unifiedskg/metrics/sparc/interaction_scores.py official repository unverified Apache-2.0 (permissive) · e8a3b4f10de70271 · report
load_tf_weights_in_t5 hkunlp/unifiedskg/models/adapter/modeling_t5.py official repository unverified Apache-2.0 (permissive) · 136abfa3e8ce028d · report

Tasks

Few-Shot LearningQuestion AnsweringSemantic ParsingTable-based Fact VerificationTask-Oriented Dialogue Systems

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Parsing WikiTableQuestions T5-3b(UnifiedSKG) Accuracy (Dev) 50.65 #19 of 22 Archive leaderboard report
Semantic Parsing WikiTableQuestions T5-3b(UnifiedSKG) Accuracy (Test) 49.29 #19 of 22 Archive leaderboard report
Table-based Fact Verification TabFact T5-3b(UnifiedSKG) Test 83.68 #9 of 15 Archive leaderboard report
Table-based Fact Verification TabFact T5-3b(UnifiedSKG) Val 83.97 #9 of 15 Archive leaderboard report
Task-Oriented Dialogue Systems KVRET T5-3b(UnifiedSKG) Entity F1 70.07 #1 of 10 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

AdafactorAdamAttentionAttention DropoutBPECosine AnnealingDense ConnectionsDropoutGPT-3Gated Linear UnitInverse Square Root ScheduleLayer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionResidual ConnectionSentencePieceSoftmaxT5Weight Decay

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