58 citations · 262 across the 18 of their papers we have counts for
20 papers
RealMath-Eval: Why SOTA Judges Struggle with Real Human Reasoning
Yiteng Mao, Kenan Xu, Yijia Lyu +3
While Large Language Models (LLMs) have achieved near-perfect performance in \emph{solving} high-school mathematics, their ability to \emph{evaluate} the diverse reasoning processe…
RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation
Fengji Zhang, Bei Chen, Yue Zhang +6
The task of repository-level code completion is to continue writing the unfinished code based on a broader context of the repository. While for automated code completion tools, it…
Exploring Distributional Shifts in Large Language Models for Code Analysis
Shushan Arakelyan, Rocktim Jyoti Das, Yi Mao +1
We systematically study how three large language models with code capabilities - CodeT5, Codex, and ChatGPT - generalize to out-of-domain data. We consider two fundamental applicat…
Generation-Augmented Query Expansion For Code Retrieval
Dong Li, Yelong Shen, Ruoming Jin +3
Pre-trained language models have achieved promising success in code retrieval tasks, where a natural language documentation query is given to find the most relevant existing code s…
HyperTuning: Toward Adapting Large Language Models without Back-propagation
Jason Phang, Yi Mao, Pengcheng He +1
Fine-tuning large language models for different tasks can be costly and inefficient, and even methods that reduce the number of tuned parameters still require full gradient-based o…
Explanations from Large Language Models Make Small Reasoners Better
Shiyang Li, Jianshu Chen, Yelong Shen +9
Integrating free-text explanations to in-context learning of large language models (LLM) is shown to elicit strong reasoning capabilities along with reasonable explanations. In thi…
OmniTab: Pretraining with Natural and Synthetic Data for Few-shot Table-based Question Answering
Zhengbao Jiang, Yi Mao, Pengcheng He +2
The information in tables can be an important complement to text, making table-based question answering (QA) systems of great value. The intrinsic complexity of handling tables oft…
An End-to-End Dialogue Summarization System for Sales Calls
Abedelkadir Asi, Song Wang, Roy Eisenstadt +4
Summarizing sales calls is a routine task performed manually by salespeople. We present a production system which combines generative models fine-tuned for customer-agent setting,…
DialogVED: A Pre-trained Latent Variable Encoder-Decoder Model for Dialog Response Generation
Wei Chen, Yeyun Gong, Song Wang +9
Dialog response generation in open domain is an important research topic where the main challenge is to generate relevant and diverse responses. In this paper, we propose a new dia…
Knowledge-Grounded Dialogue Generation with a Unified Knowledge Representation
Yu Li, Baolin Peng, Yelong Shen +4
Knowledge-grounded dialogue systems are challenging to build due to the lack of training data and heterogeneous knowledge sources. Existing systems perform poorly on unseen topics…
A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation
Tianyu Liu, Yizhe Zhang, Chris Brockett +4
Large pretrained generative models like GPT-3 often suffer from hallucinating non-existent or incorrect content, which undermines their potential merits in real applications. Exist…
Finetuning Pretrained Transformers into RNNs
Jungo Kasai, Hao Peng, Yizhe Zhang +6
Transformers have outperformed recurrent neural networks (RNNs) in natural language generation. But this comes with a significant computational cost, as the attention mechanism's c…
Exploiting Structured Knowledge in Text via Graph-Guided Representation Learning
Tao Shen, Yi Mao, Pengcheng He +3
In this work, we aim at equipping pre-trained language models with structured knowledge. We present two self-supervised tasks learning over raw text with the guidance from knowledg…
Conditional Self-Attention for Query-based Summarization
Yujia Xie, Tianyi Zhou, Yi Mao +1
Self-attention mechanisms have achieved great success on a variety of NLP tasks due to its flexibility of capturing dependency between arbitrary positions in a sequence. For proble…
X-SQL: reinforce schema representation with context
Pengcheng He, Yi Mao, Kaushik Chakrabarti +1
In this work, we present X-SQL, a new network architecture for the problem of parsing natural language to SQL query. X-SQL proposes to enhance the structural schema representation…
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…
Statistical Translation, Heat Kernels and Expected Distances
Joshua Dillon, Yi Mao, Guy Lebanon +1
High dimensional structured data such as text and images is often poorly understood and misrepresented in statistical modeling. The standard histogram representation suffers from h…
Domain Knowledge Uncertainty and Probabilistic Parameter Constraints
Yi Mao, Guy Lebanon
Incorporating domain knowledge into the modeling process is an effective way to improve learning accuracy. However, as it is provided by humans, domain knowledge can only be specif…
Linguistic Geometries for Unsupervised Dimensionality Reduction
Yi Mao, Krishnakumar Balasubramanian, Guy Lebanon
Text documents are complex high dimensional objects. To effectively visualize such data it is important to reduce its dimensionality and visualize the low dimensional embedding as…