Codex |
Evaluating Large Language Models Trained on Code |
Code Generation |
- |
arXiv 21 |
GPT-3 |
Language Models are Few-Shot Learners |
LLM, in-context learning |
- |
NeurIPS 20 |
BERT |
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding |
Pre-training |
Model |
NAACL 19 |
SpreadsheetCoder |
SpreadsheetCoder: Formula Prediction from Semi-structured Context |
Spreadsheet formula prediction |
Code |
ICML 21 |
TURL |
TURL: Table Understanding through Representation Learning |
Table Pre-training |
Code |
VLDB 20 |
TaPEx |
TAPEX: Table Pre-training via Learning a Neural SQL Executor |
Table Pre-training |
Code |
ICLR 22 |
TaBERT |
TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data |
Table Pre-training |
Code |
ACL 20 |
TaPas |
TaPas: Weakly Supervised Table Parsing via Pre-training |
Table Pre-training |
Code |
ACL 20 |
TABBIE |
TABBIE: Pretrained Representations of Tabular Data |
Table Pre-training |
Code |
ACL 21 |
RESDSQL |
RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQL |
text-to-SQL fine-tuning |
Code |
AAAI 23 |
FLAN |
Finetuned Language Models Are Zero-Shot Learners |
Instruction-tuning |
Code |
ICLR 22 |
Chain-of-thought |
Chain-of-thought prompting elicits reasoning in large language models |
Step-by-step Reasoning |
- |
NeurIPS 22 |
Least-to-most |
Least-to-most prompting enables complex reasoning in large language models |
Prompting, Decompose |
- |
ICLR 23 |
Self-consistency |
Self-consistency improves chain of thought reasoning in language models |
Reason with votes |
- |
ICLR 23 |
Table-GPT |
Table-GPT: Table-tuned GPT for Diverse Table Tasks |
Table Instruction-tuning |
- |
arXiv 23 |
TableLlama |
TableLlama: Towards Open Large Generalist Models for Tables |
Table Instruction-tuning |
Model |
arXiv 23 |
UnifiedSKG |
UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models |
Table Instruction-tuning |
Code |
EMNLP 22 |
Code Llama |
Code Llama: Open Foundation Models for Code |
Code |
Code |
arXiv 23 |
Magicoder |
Magicoder: Source Code Is All You Need |
Code Instruction-tuning |
Code Model |
arXiv 23 |
Lemur |
Lemur: Harmonizing Natural Language and Code for Language Agents |
Code Instruction-tuning |
Code Model |
ICLR 24 |
ReAct |
ReAct: Synergizing Reasoning and Acting in Language Models |
Agent Framework |
Code |
ICLR 23 |
Dater |
Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning |
Prompting, Decomposing |
Code |
SIGIR 23 |
StructGPT |
StructGPT: A General Framework for Large Language Model to Reason over Structured Data |
Prompting, Structured Knowledge |
Code |
EMNLP 23 |
DAIL-SQL |
Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation |
Prompting, text-to-SQL |
Code |
arXiv 23 |
C3 |
C3: Zero-shot Text-to-SQL with ChatGPT |
Prompting |
Code |
arXiv 23 |
DIN-SQL |
DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction |
Prompting, Decompose |
Code |
NeurIPS 23 |
Prompt Design Strategies |
Enhancing Text-to-SQL Capabilities of Large Language Models: A Study on Prompt Design Strategies |
Prompting, text-to-SQL |
Code |
EMNLP 23 |
Binder |
Binding Language Models in Symbolic Languages |
Prompting |
Code |
ICLR 23 |
Data-Copilot |
Data-Copilot: Bridging Billions of Data and Humans with Autonomous Workflow |
Agent, Data Visualization |
Code |
arXiv 23 |
SheetCopilot |
SheetCopilot: Bringing Software Productivity to the Next Level through Large Language Models |
Agent, Spreadsheet |
Code |
NeurIPS 23 |
ReAcTable |
ReAcTable: Enhancing ReAct for Table Question Answering |
Agent, ReAct |
Code |
arXiv 23 |
TAP4LLM |
TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning |
Table Augmentation |
|
arXiv 23 |
DB-GPT |
DB-GPT: Empowering Database Interactions with Private Large Language Models |
Industry Framework |
Code |
arXiv 23 |
DPR |
Dense Passage Retrieval for Open-Domain Question Answering |
Retrieval-Augmented Generation |
Code |
EMNLP 20 |
ITR |
An Inner Table Retriever for Robust Table Question Answering |
Retrieval |
Code |
ACL 23 |
LI-RAGE |
LI-RAGE: Late Interaction Retrieval Augmented Generation with Explicit Signals for Open-Domain Table Question Answering |
RAG + Table |
Code |
ACL 23 |