64 citations · 439 across the 25 of their papers we have counts for
9 papers · 1 filter
One Embedder, Any Task: Instruction-Finetuned Text Embeddings
Hongjin Su, Weijia Shi, Jungo Kasai +7
We introduce INSTRUCTOR, a new method for computing text embeddings given task instructions: every text input is embedded together with instructions explaining the use case (e.g.,…
Coder Reviewer Reranking for Code Generation
Tianyi Zhang, Tao Yu, Tatsunori B. Hashimoto +4
Sampling diverse programs from a code language model and reranking with model likelihood is a popular method for code generation but it is prone to preferring degenerate solutions.…
DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation
Yuhang Lai, Chengxi Li, Yiming Wang +7
We introduce DS-1000, a code generation benchmark with a thousand data science problems spanning seven Python libraries, such as NumPy and Pandas. Compared to prior works, DS-1000…
Augmenting Multi-Turn Text-to-SQL Datasets with Self-Play
Qi Liu, Zihuiwen Ye, Tao Yu +2
The task of context-dependent text-to-SQL aims to convert multi-turn user utterances to formal SQL queries. This is a challenging task due to both the scarcity of training data fro…
NL2INTERFACE: Interactive Visualization Interface Generation from Natural Language Queries
Yiru Chen, Ryan Li, Austin Mac +3
We develop NL2INTERFACE to explore the potential of generating usable interactive multi-visualization interfaces from natural language queries. With NL2INTERFACE, users can directl…
Selective Annotation Makes Language Models Better Few-Shot Learners
Hongjin Su, Jungo Kasai, Chen Henry Wu +8
Many recent approaches to natural language tasks are built on the remarkable abilities of large language models. Large language models can perform in-context learning, where they l…
N-Grammer: Augmenting Transformers with latent n-grams
Aurko Roy, Rohan Anil, Guangda Lai +13
Transformer models have recently emerged as one of the foundational models in natural language processing, and as a byproduct, there is significant recent interest and investment i…
Random Laplacian Features for Learning with Hyperbolic Space
Tao Yu, Christopher De Sa
Due to its geometric properties, hyperbolic space can support high-fidelity embeddings of tree- and graph-structured data, upon which various hyperbolic networks have been develope…
UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models
Tianbao Xie, Chen Henry Wu, Peng Shi +20
Structured knowledge grounding (SKG) leverages structured knowledge to complete user requests, such as semantic parsing over databases and question answering over knowledge bases.…