982 citations · 1.2k across the 14 of their papers we have counts for
11 papers · 1 filter
Statistical Rejection Sampling Improves Preference Optimization
Tianqi Liu, Yao Zhao, Rishabh Joshi +4
Improving the alignment of language models with human preferences remains an active research challenge. Previous approaches have primarily utilized Reinforcement Learning from Huma…
SLiC-HF: Sequence Likelihood Calibration with Human Feedback
Yao Zhao, Rishabh Joshi, Tianqi Liu +3
Learning from human feedback has been shown to be effective at aligning language models with human preferences. Past work has often relied on Reinforcement Learning from Human Feed…
Improving the Robustness of Summarization Models by Detecting and Removing Input Noise
Kundan Krishna, Yao Zhao, Jie Ren +4
The evaluation of abstractive summarization models typically uses test data that is identically distributed as training data. In real-world practice, documents to be summarized may…
Calibrating Sequence likelihood Improves Conditional Language Generation
Yao Zhao, Misha Khalman, Rishabh Joshi +3
Conditional language models are predominantly trained with maximum likelihood estimation (MLE), giving probability mass to sparsely observed target sequences. While MLE trained mod…
Out-of-Distribution Detection and Selective Generation for Conditional Language Models
Jie Ren, Jiaming Luo, Yao Zhao +4
Machine learning algorithms typically assume independent and identically distributed samples in training and at test time. Much work has shown that high-performing ML classifiers c…
Investigating Efficiently Extending Transformers for Long Input Summarization
Jason Phang, Yao Zhao, Peter J. Liu
While large pretrained Transformer models have proven highly capable at tackling natural language tasks, handling long sequence inputs continues to be a significant challenge. One…
TALM: Tool Augmented Language Models
Aaron Parisi, Yao Zhao, Noah Fiedel
Transformer based language models (LMs) demonstrate increasing performance with scale across a wide variety of tasks. Scale alone however cannot enable models to solve tasks that r…
A Well-Composed Text is Half Done! Composition Sampling for Diverse Conditional Generation
Shashi Narayan, Gonçalo Simões, Yao Zhao +4
We propose Composition Sampling, a simple but effective method to generate diverse outputs for conditional generation of higher quality compared to previous stochastic decoding str…
Planning with Learned Entity Prompts for Abstractive Summarization
Shashi Narayan, Yao Zhao, Joshua Maynez +3
We introduce a simple but flexible mechanism to learn an intermediate plan to ground the generation of abstractive summaries. Specifically, we prepend (or prompt) target summaries…
SEAL: Segment-wise Extractive-Abstractive Long-form Text Summarization
Yao Zhao, Mohammad Saleh, Peter J. Liu
Most prior work in the sequence-to-sequence paradigm focused on datasets with input sequence lengths in the hundreds of tokens due to the computational constraints of common RNN an…
PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization
Jingqing Zhang, Yao Zhao, Mohammad Saleh +1
Recent work pre-training Transformers with self-supervised objectives on large text corpora has shown great success when fine-tuned on downstream NLP tasks including text summariza…