83 citations · 168 across the 17 of their papers we have counts for
17 papers
Can Language Models Solve Graph Problems in Natural Language?
Heng Wang, Shangbin Feng, Tianxing He +3
Large language models (LLMs) are increasingly adopted for a variety of tasks with implicit graphical structures, such as planning in robotics, multi-hop question answering or knowl…
Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models
Shangbin Feng, Weijia Shi, Yuyang Bai +3
By design, large language models (LLMs) are static general-purpose models, expensive to retrain or update frequently. As they are increasingly adopted for knowledge-intensive tasks…
On the Blind Spots of Model-Based Evaluation Metrics for Text Generation
Tianxing He, Jingyu Zhang, Tianle Wang +4
In this work, we explore a useful but often neglected methodology for robustness analysis of text generation evaluation metrics: stress tests with synthetic data. Basically, we des…
PCFG-based Natural Language Interface Improves Generalization for Controlled Text Generation
Jingyu Zhang, James Glass, Tianxing He
Existing work on controlled text generation (CTG) assumes a control interface of categorical attributes. In this work, we propose a natural language (NL) interface, where we craft…
Controlling the Focus of Pretrained Language Generation Models
Jiabao Ji, Yoon Kim, James Glass +1
The finetuning of pretrained transformer-based language generation models are typically conducted in an end-to-end manner, where the model learns to attend to relevant parts of the…
Revisiting Latent-Space Interpolation via a Quantitative Evaluation Framework
Lu Mi, Tianxing He, Core Francisco Park +3
Latent-space interpolation is commonly used to demonstrate the generalization ability of deep latent variable models. Various algorithms have been proposed to calculate the best tr…
An Empirical Study on Few-shot Knowledge Probing for Pretrained Language Models
Tianxing He, Kyunghyun Cho, James Glass
Prompt-based knowledge probing for 1-hop relations has been used to measure how much world knowledge is stored in pretrained language models. Existing work uses considerable amount…
Joint Energy-based Model Training for Better Calibrated Natural Language Understanding Models
Tianxing He, Bryan McCann, Caiming Xiong +1
In this work, we explore joint energy-based model (EBM) training during the finetuning of pretrained text encoders (e.g., Roberta) for natural language understanding (NLU) tasks. O…
A Systematic Characterization of Sampling Algorithms for Open-ended Language Generation
Moin Nadeem, Tianxing He, Kyunghyun Cho +1
This work studies the widely adopted ancestral sampling algorithms for auto-regressive language models, which is not widely studied in the literature. We use the quality-diversity…
AutoKG: Constructing Virtual Knowledge Graphs from Unstructured Documents for Question Answering
Seunghak Yu, Tianxing He, James Glass
Knowledge graphs (KGs) have the advantage of providing fine-grained detail for question-answering systems. Unfortunately, building a reliable KG is time-consuming and expensive as…
Analyzing the Forgetting Problem in the Pretrain-Finetuning of Dialogue Response Models
Tianxing He, Jun Liu, Kyunghyun Cho +4
In this work, we study how the finetuning stage in the pretrain-finetune framework changes the behavior of a pretrained neural language generator. We focus on the transformer encod…
From Data Quality to Model Quality: an Exploratory Study on Deep Learning
Tianxing He, Shengcheng Yu, Ziyuan Wang +2
Nowadays, people strive to improve the accuracy of deep learning models. However, very little work has focused on the quality of data sets. In fact, data quality determines model q…
Why gradient clipping accelerates training: A theoretical justification for adaptivity
Jingzhao Zhang, Tianxing He, Suvrit Sra +1
We provide a theoretical explanation for the effectiveness of gradient clipping in training deep neural networks. The key ingredient is a new smoothness condition derived from prac…
Exposure Bias versus Self-Recovery: Are Distortions Really Incremental for Autoregressive Text Generation?
Tianxing He, Jingzhao Zhang, Zhiming Zhou +1
Exposure bias has been regarded as a central problem for auto-regressive language models (LM). It claims that teacher forcing would cause the test-time generation to be incremental…
Negative Training for Neural Dialogue Response Generation
Tianxing He, James Glass
Although deep learning models have brought tremendous advancements to the field of open-domain dialogue response generation, recent research results have revealed that the trained…
Detecting egregious responses in neural sequence-to-sequence models
Tianxing He, James Glass
In this work, we attempt to answer a critical question: whether there exists some input sequence that will cause a well-trained discrete-space neural network sequence-to-sequence (…
On Training Bi-directional Neural Network Language Model with Noise Contrastive Estimation
Tianxing He, Yu Zhang, Jasha Droppo +1
We propose to train bi-directional neural network language model(NNLM) with noise contrastive estimation(NCE). Experiments are conducted on a rescore task on the PTB data set. It i…