59 citations · 238 across the 20 of their papers we have counts for
21 papers
QualityFlow: An Agentic Workflow for Program Synthesis Controlled by LLM Quality Checks
Yaojie Hu, Qiang Zhou, Qihong Chen +6
We introduce QualityFlow, a dynamic agentic workflow for program synthesis. Given the English description of a programming problem and a set of unit tests, the model's goal is to s…
Reasoning in Token Economies: Budget-Aware Evaluation of LLM Reasoning Strategies
Junlin Wang, Siddhartha Jain, Dejiao Zhang +3
A diverse array of reasoning strategies has been proposed to elicit the capabilities of large language models. However, in this paper, we point out that traditional evaluations whi…
Repoformer: Selective Retrieval for Repository-Level Code Completion
Di Wu, Wasi Uddin Ahmad, Dejiao Zhang +2
Recent advances in retrieval-augmented generation (RAG) have initiated a new era in repository-level code completion. However, the invariable use of retrieval in existing methods e…
Code Representation Learning At Scale
Dejiao Zhang, Wasi Ahmad, Ming Tan +5
Recent studies have shown that code language models at scale demonstrate significant performance gains on downstream tasks, i.e., code generation. However, most of the existing wor…
Exploring Continual Learning for Code Generation Models
Prateek Yadav, Qing Sun, Hantian Ding +9
Large-scale code generation models such as Codex and CodeT5 have achieved impressive performance. However, libraries are upgraded or deprecated very frequently and re-training larg…
ContraCLM: Contrastive Learning For Causal Language Model
Nihal Jain, Dejiao Zhang, Wasi Uddin Ahmad +9
Despite exciting progress in causal language models, the expressiveness of the representations is largely limited due to poor discrimination ability. To remedy this issue, we prese…
Learning Dialogue Representations from Consecutive Utterances
Zhihan Zhou, Dejiao Zhang, Wei Xiao +4
Learning high-quality dialogue representations is essential for solving a variety of dialogue-oriented tasks, especially considering that dialogue systems often suffer from data sc…
QaNER: Prompting Question Answering Models for Few-shot Named Entity Recognition
Andy T. Liu, Wei Xiao, Henghui Zhu +3
Recently, prompt-based learning for pre-trained language models has succeeded in few-shot Named Entity Recognition (NER) by exploiting prompts as task guidance to increase label ef…
Knowledge Enhanced Pretrained Language Models: A Compreshensive Survey
Xiaokai Wei, Shen Wang, Dejiao Zhang +2
Pretrained Language Models (PLM) have established a new paradigm through learning informative contextualized representations on large-scale text corpus. This new paradigm has revol…
Virtual Augmentation Supported Contrastive Learning of Sentence Representations
Dejiao Zhang, Wei Xiao, Henghui Zhu +2
Despite profound successes, contrastive representation learning relies on carefully designed data augmentations using domain specific knowledge. This challenge is magnified in natu…
Lifelong Pretraining: Continually Adapting Language Models to Emerging Corpora
Xisen Jin, Dejiao Zhang, Henghui Zhu +5
Pretrained language models (PTLMs) are typically learned over a large, static corpus and further fine-tuned for various downstream tasks. However, when deployed in the real world,…
Pairwise Supervised Contrastive Learning of Sentence Representations
Dejiao Zhang, Shang-Wen Li, Wei Xiao +4
Many recent successes in sentence representation learning have been achieved by simply fine-tuning on the Natural Language Inference (NLI) datasets with triplet loss or siamese los…
Improving Factual Consistency of Abstractive Summarization via Question Answering
Feng Nan, Cicero Nogueira dos Santos, Henghui Zhu +7
A commonly observed problem with the state-of-the art abstractive summarization models is that the generated summaries can be factually inconsistent with the input documents. The f…
Supporting Clustering with Contrastive Learning
Dejiao Zhang, Feng Nan, Xiaokai Wei +6
Unsupervised clustering aims at discovering the semantic categories of data according to some distance measured in the representation space. However, different categories often ove…
Entity-level Factual Consistency of Abstractive Text Summarization
Feng Nan, Ramesh Nallapati, Zhiguo Wang +5
A key challenge for abstractive summarization is ensuring factual consistency of the generated summary with respect to the original document. For example, state-of-the-art models t…
Answering Ambiguous Questions through Generative Evidence Fusion and Round-Trip Prediction
Yifan Gao, Henghui Zhu, Patrick Ng +7
In open-domain question answering, questions are highly likely to be ambiguous because users may not know the scope of relevant topics when formulating them. Therefore, a system ne…
Deep Unsupervised Clustering Using Mixture of Autoencoders
Dejiao Zhang, Yifan Sun, Brian Eriksson +1
Unsupervised clustering is one of the most fundamental challenges in machine learning. A popular hypothesis is that data are generated from a union of low-dimensional nonlinear man…
Subspace Clustering using Ensembles of -Subspaces
John Lipor, David Hong, Yan Shuo Tan +1
Subspace clustering is the unsupervised grouping of points lying near a union of low-dimensional linear subspaces. Algorithms based directly on geometric properties of such data te…
Convergence of a Grassmannian Gradient Descent Algorithm for Subspace Estimation From Undersampled Data
Dejiao Zhang, Laura Balzano
Subspace learning and matrix factorization problems have great many applications in science and engineering, and efficient algorithms are critical as dataset sizes continue to grow…
Global Convergence of a Grassmannian Gradient Descent Algorithm for Subspace Estimation
Dejiao Zhang, Laura Balzano
It has been observed in a variety of contexts that gradient descent methods have great success in solving low-rank matrix factorization problems, despite the relevant problem formu…
Iterative Grassmannian Optimization for Robust Image Alignment
Jun He, Dejiao Zhang, Laura Balzano +1
Robust high-dimensional data processing has witnessed an exciting development in recent years, as theoretical results have shown that it is possible using convex programming to opt…