A comprehensive paper list of Large Language Model for Table Understanding
🌟 We will be presenting a tutorial on “Large Language Models for Tabular Data” at the upcoming SIGIR’24 conference. See you in D.C. !😊
- Fuse: a reproducible, extendable, internet-scale corpus of spreadsheets. [Paper] [Dataset]
- ToTTo: A Controlled Table-To-Text Generation Dataset. [Paper] [Dataset]
- Table pre-training: A survey on model architectures, pre-training objectives, and downstream tasks. [Paper]
- Large Language Model for Table Processing: A Survey. [Paper]
- A Survey of Table Reasoning with Large Language Models. [Paper]
- Large Language Models (LLMs) on Tabular Data: Prediction, Generation, and Understanding - A Survey [Paper]
- Tabular Representation, Noisy Operators, and Impacts on Table Structure Understanding Tasks in LLMs. [Paper]
- GPT4Table: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study. [Paper]
- DBCopilot: Scaling Natural Language Querying to Massive Databases. [Paper]
- Table-to-text generation by structure-aware seq2seq learning. [Paper]
- Data-to-text generation with content selection and planning. [Paper]
- Tables as Images? Exploring the Strengths and Limitations of LLMs on Multimodal Representations of Tabular Data. [Paper]
- Assessing GPT4-V on Structured Reasoning Tasks. [Paper]
- Multimodal Table Understanding. [Paper]
- TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy. [Paper]
- Vision Language Models for Spreadsheet Understanding: Challenges and Opportunities. [Paper]
- Large Language Models are few(1)-shot Table Reasoners. [Paper]
- TaPas: Weakly Supervised Table Parsing via Pre-training. [Paper]
- TAPEX: Table Pre-training via Learning a Neural SQL Executor. [Paper]
- An inner table retriever for robust table question answering. [Paper]
- LI-RAGE: Late interaction retrieval augmented generation with explicit signals for open-domain table question answering. [Paper]
- DB-GPT: Empowering Database Interactions with Private Large Language Models. [Paper]
- TaPas: Weakly Supervised Table Parsing via Pre-training. [Paper]
- TURL: table understanding through representation learning. [Paper]
- TABBIE: Pretrained Representations of Tabular Data. [Paper]
- StructGPT: A General Framework for Large Language Model to Reason over Structured Data. [Paper]
- TAPEX: Table Pre-Training via Learning a Neural SQL Executor. [Paper]
- Tablegpt: Table-tuned gpt for diverse table tasks. [Paper]
- TableLlama: Towards Open Large Generalist Models for Tables. [Paper]
- TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios. [Paper]
- Tables as Images? Exploring the Strengths and Limitations of LLMs on Multimodal Representations of Tabular Data. [Paper]
- My Database User Is a Large Language Model. [Paper]
- LLM-Enhanced Data Management. [Paper]
- DB-GPT: Empowering Database Interactions with Private Large Language Models. [Paper]
- Table Retrieval May Not Necessitate Table-specific Model Design. [Paper]
- CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets. [Paper]
- Self-refine: Iterative refinement with self-feedback. [Paper]
- DIN-SQL: Decomposed InContext Learning of Text-to-SQL with Self-Correction. [Paper]
- Chain-of-table: Evolving tables in the reasoning chain for table understanding. [Paper]
- Large Language Models Are Versatile Decomposers: Decomposing Evidence and Questions for Table-based Reasoning. [Paper]
- ReAct: Synergizing Reasoning and Acting in Language Models. [Paper]
- StructGPT: A General Framework for Large Language Model to Reason over Structured Data. [Paper]
- TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning. [Paper]
- Self-Consistency Improves Chain of Thought Reasoning in Language Models. [Paper]
- SheetCopilot: Bringing Software Productivity to the Next Level through Large Language Models. [Paper]
- ReAcTable: Enhancing ReAct for Table Question Answering. [Paper]
- Binding Language Models in Symbolic Languages. [Paper]
- Data-Copilot: Bridging Billions of Data and Humans with Autonomous Workflow. [Paper]
- TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Tasks. [Paper]