mlsanityData to 7 Oct 2026

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

arXiv 2201.05966 ↗First posted 16 Jan 2022cs.CLcited by 231

Not on the map. Why?

Cited by 28 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

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.

Key facts. Cited by 231 papers in the map (data through 7 Oct 2026). Builds on 85 of its 120 references that are in the map. First posted on arXiv 16 Jan 2022.

Builds on

85 of 120 references.

References · 85

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  4. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  5. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  6. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  7. 2021Program Synthesis with Large Language Modelscited by 3,509
  8. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  9. 2020Big Bird: Transformers for Longer Sequencescited by 1,673
  10. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,462
  11. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,255
  12. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
38 more
  1. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
  2. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 679
  3. 2020Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillationcited by 591
  4. 2021Datasets: A Community Library for Natural Language Processingcited by 526
  5. 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 509
  6. 2020UnifiedQA: Crossing Format Boundaries With a Single QA Systemcited by 475
  7. 2020TAPAS: Weakly Supervised Table Parsing via Pre-trainingcited by 432
  8. 2019TabFact: A Large-scale Dataset for Table-based Fact Verificationcited by 425
  9. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 420
  10. 2018The Web as a Knowledge-base for Answering Complex Questionscited by 409
  11. 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 402
  12. 2020TaBERT: Pretraining for Joint Understanding of Textual and Tabular Datacited by 395
  13. 2021QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answeringcited by 386
  14. 2020A Simple Language Model for Task-Oriented Dialoguecited by 331
  15. 2019K-BERT: Enabling Language Representation with Knowledge Graphcited by 303
  16. 2020ToTTo: A Controlled Table-To-Text Generation Datasetcited by 267
  17. 2020HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Datacited by 263
  18. 2017The E2E Dataset: New Challenges For End-to-End Generationcited by 252
  19. 2018The Natural Language Decathlon: Multitask Learning as Question Answeringcited by 235
  20. 2021SPoT: Better Frozen Model Adaptation through Soft Prompt Transfercited by 235
  21. 2021TAPEX: Table Pre-training via Learning a Neural SQL Executorcited by 233
  22. 2019KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoningcited by 216
  23. 2021Muppet: Massive Multi-task Representations with Pre-Finetuningcited by 192
  24. 2019CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databasescited by 180
  25. 2021MultiModalQA: Complex Question Answering over Text, Tables and Imagescited by 177
  26. 2021FeTaQA: Free-form Table Question Answeringcited by 174
  27. 2020Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Basescited by 169
  28. 2021Constrained Language Models Yield Few-Shot Semantic Parserscited by 162
  29. 2021ExT5: Towards Extreme Multi-Task Scaling for Transfer Learningcited by 161
  30. 2020MTOP: A Comprehensive Multilingual Task-Oriented Semantic Parsing Benchmarkcited by 156
  31. 2020Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both?cited by 147
  32. 2020DART: Open-Domain Structured Data Record to Text Generationcited by 144
  33. 2021CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLPcited by 142
  34. 2019SParC: Cross-Domain Semantic Parsing in Contextcited by 141
  35. 2017Key-Value Retrieval Networks for Task-Oriented Dialoguecited by 137
  36. 2021Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collectionscited by 128
  37. 2017RobustFill: Neural Program Learning under Noisy I/Ocited by 124
  38. 2020Semantic Evaluation for Text-to-SQL with Distilled Test Suitescited by 123

50 most cited of 85 All 85 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 76; 2023: 82; 2024: 49; 2025: 20; 2026: 4.

231 papers.

Sort:

By area:

  1. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  2. 2023A Survey of Large Language Modelscited by 2,537
  3. 2022Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Taskscited by 858
  4. 2023Instruction Tuning with GPT-4cited by 676
  5. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
  6. 2023A Comprehensive Overview of Large Language Modelscited by 639
  7. 2023Instruction Tuning for Large Language Models: A Surveycited by 617
  8. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 339
  9. 2022UL2: Unifying Language Learning Paradigmscited by 292
  10. 2023AlignScore: Evaluating Factual Consistency with a Unified Alignment Functioncited by 284
  11. 2022OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalizationcited by 235
  12. 2023Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graphcited by 235
38 more
  1. 2022FOLIO: Natural Language Reasoning with First-Order Logiccited by 233
  2. 2023LEVER: Learning to Verify Language-to-Code Generation with Executioncited by 228
  3. 2022A Contrastive Framework for Neural Text Generationcited by 224
  4. 2022Binding Language Models in Symbolic Languagescited by 224
  5. 2022LinkBERT: Pretraining Language Models with Document Linkscited by 209
  6. 2024Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuningcited by 174
  7. 2023MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQLcited by 158
  8. 2023OpenAgents: An Open Platform for Language Agents in the Wildcited by 136
  9. 2023TableLlama: Towards Open Large Generalist Models for Tablescited by 136
  10. 2024GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoningcited by 128
  11. 2022Retrieval-Augmented Multimodal Language Modelingcited by 125
  12. 2022Natural Language to Code Translation with Executioncited by 122
  13. 2023Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sourcescited by 121
  14. 2022MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Datacited by 120
  15. 2022Large Language Models are few(1)-shot Table Reasonerscited by 116
  16. 2023Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Studycited by 116
  17. 2023Large Language Models as Analogical Reasonerscited by 107
  18. 2022PromptCap: Prompt-Guided Task-Aware Image Captioningcited by 104
  19. 2024Large Language Models Meet NLP: A Surveycited by 102
  20. 2022State-of-the-art generalisation research in NLP: A taxonomy and reviewcited by 97
  21. 2023Memory-Efficient Fine-Tuning of Compressed Large Language Models via sub-4-bit Integer Quantizationcited by 97
  22. 2023Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsingcited by 93
  23. 2024KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graphcited by 90
  24. 2022Natural Language to Code Generation in Interactive Data Science Notebookscited by 86
  25. 2022RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQLcited by 85
  26. 2023Exploring the Impact of Instruction Data Scaling on Large Language Models: An Empirical Study on Real-World Use Casescited by 85
  27. 2023Retrieving Multimodal Information for Augmented Generation: A Surveycited by 84
  28. 2022DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Basescited by 83
  29. 2022A Survey of Knowledge Enhanced Pre-trained Language Modelscited by 76
  30. 2024TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarioscited by 76
  31. 2022ProGen: Progressive Zero-shot Dataset Generation via In-context Feedbackcited by 67
  32. 2022UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognitioncited by 61
  33. 2022TIARA: Multi-grained Retrieval for Robust Question Answering over Large Knowledge Basescited by 59
  34. 2022Don't Generate, Discriminate: A Proposal for Grounding Language Models to Real-World Environmentscited by 57
  35. 2024DA-Code: Agent Data Science Code Generation Benchmark for Large Language Modelscited by 57
  36. 2024Synthesizing Text-to-SQL Data from Weak and Strong LLMscited by 53
  37. 2022A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directionscited by 51
  38. 2022Multi-VALUE: A Framework for Cross-Dialectal English NLPcited by 51

50 most cited of 231 All 231 (JSON)