2.1k citations · 2.8k across the 18 of their papers we have counts for
21 papers
Multilingual Machine Translation with Open Large Language Models at Practical Scale: An Empirical Study
Menglong Cui, Pengzhi Gao, Wei Liu +2
Large language models (LLMs) have shown continuously improving multilingual capabilities, and even small-scale open-source models have demonstrated rapid performance enhancement. I…
Naive Bayes-based Context Extension for Large Language Models
Jianlin Su, Murtadha Ahmed, Wenbo +3
Large Language Models (LLMs) have shown promising in-context learning abilities. However, conventional In-Context Learning (ICL) approaches are often impeded by length limitations…
PaLM 2 Technical Report
Rohan Anil, Andrew M. Dai, Orhan Firat +125
We introduce PaLM 2, a new state-of-the-art language model that has better multilingual and reasoning capabilities and is more compute-efficient than its predecessor PaLM. PaLM 2 i…
Natural Language to Code Generation in Interactive Data Science Notebooks
Pengcheng Yin, Wen-Ding Li, Kefan Xiao +9
Computational notebooks, such as Jupyter notebooks, are interactive computing environments that are ubiquitous among data scientists to perform data wrangling and analytic tasks. T…
Learning Math Reasoning from Self-Sampled Correct and Partially-Correct Solutions
Ansong Ni, Jeevana Priya Inala, Chenglong Wang +4
Pretrained language models have shown superior performance on many natural language processing tasks, yet they still struggle at multi-step formal reasoning tasks like grade school…
PaLM: Scaling Language Modeling with Pathways
Aakanksha Chowdhery, Sharan Narang, Jacob Devlin +64
Large language models have been shown to achieve remarkable performance across a variety of natural language tasks using few-shot learning, which drastically reduces the number of…
Synchromesh: Reliable code generation from pre-trained language models
Gabriel Poesia, Oleksandr Polozov, Vu Le +4
Large pre-trained language models have been used to generate code,providing a flexible interface for synthesizing programs from natural language specifications. However, they often…
KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers
Chia-Hsuan Lee, Oleksandr Polozov, Matthew Richardson
The goal of database question answering is to enable natural language querying of real-life relational databases in diverse application domains. Recently, large-scale datasets such…
Programming Puzzles
Tal Schuster, Ashwin Kalyan, Oleksandr Polozov +1
We introduce a new type of programming challenge called programming puzzles, as an objective and comprehensive evaluation of program synthesis, and release an open-source dataset o…
Structure-Grounded Pretraining for Text-to-SQL
Xiang Deng, Ahmed Hassan Awadallah, Christopher Meek +3
Learning to capture text-table alignment is essential for tasks like text-to-SQL. A model needs to correctly recognize natural language references to columns and values and to grou…
Neuro-Symbolic Visual Reasoning: Disentangling "Visual" from "Reasoning"
Saeed Amizadeh, Hamid Palangi, Oleksandr Polozov +2
Visual reasoning tasks such as visual question answering (VQA) require an interplay of visual perception with reasoning about the question semantics grounded in perception. However…
RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers
Bailin Wang, Richard Shin, Xiaodong Liu +2
When translating natural language questions into SQL queries to answer questions from a database, contemporary semantic parsing models struggle to generalize to unseen database sch…
Program Synthesis and Semantic Parsing with Learned Code Idioms
Richard Shin, Miltiadis Allamanis, Marc Brockschmidt +1
Program synthesis of general-purpose source code from natural language specifications is challenging due to the need to reason about high-level patterns in the target program and l…
Are My Invariants Valid? A Learning Approach
Vincent J. Hellendoorn, Premkumar T. Devanbu, Oleksandr Polozov +1
Ensuring that a program operates correctly is a difficult task in large, complex systems. Enshrining invariants -- desired properties of correct execution -- in code or comments ca…
IncSQL: Training Incremental Text-to-SQL Parsers with Non-Deterministic Oracles
Tianze Shi, Kedar Tatwawadi, Kaushik Chakrabarti +3
We present a sequence-to-action parsing approach for the natural language to SQL task that incrementally fills the slots of a SQL query with feasible actions from a pre-defined inv…
Robust Text-to-SQL Generation with Execution-Guided Decoding
Chenglong Wang, Kedar Tatwawadi, Marc Brockschmidt +4
We consider the problem of neural semantic parsing, which translates natural language questions into executable SQL queries. We introduce a new mechanism, execution guidance, to le…
Generative Code Modeling with Graphs
Marc Brockschmidt, Miltiadis Allamanis, Alexander L. Gaunt +1
Generative models for source code are an interesting structured prediction problem, requiring to reason about both hard syntactic and semantic constraints as well as about natural,…
Neural-Guided Deductive Search for Real-Time Program Synthesis from Examples
Ashwin Kalyan, Abhishek Mohta, Oleksandr Polozov +3
Synthesizing user-intended programs from a small number of input-output examples is a challenging problem with several important applications like spreadsheet manipulation, data wr…
FlashProfile: A Framework for Synthesizing Data Profiles
Saswat Padhi, Prateek Jain, Daniel Perelman +3
We address the problem of learning a syntactic profile for a collection of strings, i.e. a set of regex-like patterns that succinctly describe the syntactic variations in the strin…
Interactive Program Synthesis
Vu Le, Daniel Perelman, Oleksandr Polozov +3
Program synthesis from incomplete specifications (e.g. input-output examples) has gained popularity and found real-world applications, primarily due to its ease-of-use. Since this…
Learning Syntactic Program Transformations from Examples
Reudismam Rolim, Gustavo Soares, Loris D'Antoni +5
IDEs, such as Visual Studio, automate common transformations, such as Rename and Extract Method refactorings. However, extending these catalogs of transformations is complex and ti…