Search Results for author:
Found 30 papers, 11 papers with code
LiPO: Listwise Preference Optimization through Learning-to-Rank
In this work, we formulate the LM alignment as a listwise ranking problem and describe the Listwise Preference Optimization (LiPO) framework, where the policy can potentially learn more effectively from a ranked list of plausible responses given the prompt.
Self-Evaluation Improves Selective Generation in Large Language Models
Safe deployment of large language models (LLMs) may benefit from a reliable method for assessing their generated content to determine when to abstain or to selectively generate.
Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models
To do so, we investigate a simple self-training method based on expectation-maximization, which we call ReST$^{EM}$, where we (1) generate samples from the model and filter them using binary feedback, (2) fine-tune the model on these samples, and (3) repeat this process a few times.
Frontier Language Models are not Robust to Adversarial Arithmetic, or "What do I need to say so you agree 2+2=5?
We introduce and study the problem of adversarial arithmetic, which provides a simple yet challenging testbed for language model alignment.
Improving Large Language Model Fine-tuning for Solving Math Problems
With these methods, we present a thorough empirical study on a series of PaLM 2 models and find: (1) The quality and style of the step-by-step solutions used for fine-tuning can make a significant impact on the model performance; (2) While solution re-ranking and majority voting are both effective for improving the model performance when used separately, they can also be used together for an even greater performance boost; (3) Multi-task fine-tuning that sequentially separates the solution generation and evaluation tasks can offer improved performance compared with the solution fine-tuning baseline.
Small-scale proxies for large-scale Transformer training instabilities
In this work, we seek ways to reproduce and study training stability and instability at smaller scales.
Statistical Rejection Sampling Improves Preference Optimization
DPO's lack of a reward model constrains its ability to sample preference pairs from the optimal policy, and SLiC is restricted to sampling preference pairs only from the SFT policy.
SLiC-HF: Sequence Likelihood Calibration with Human Feedback
Past work has often relied on Reinforcement Learning from Human Feedback (RLHF), which optimizes the language model using reward scores assigned from a reward model trained on human preference data.
Improving the Robustness of Summarization Models by Detecting and Removing Input Noise
We present a large empirical study quantifying the sometimes severe loss in performance (up to 12 ROUGE-1 points) from different types of input noise for a range of datasets and model sizes.
Calibrating Sequence likelihood Improves Conditional Language Generation
Conditional language models are predominantly trained with maximum likelihood estimation (MLE), giving probability mass to sparsely observed target sequences.
Ranked #1 on
Abstractive Text Summarization
on CNN / Daily Mail
abstractive question answering
Abstractive Text Summarization
+5
Out-of-Distribution Detection and Selective Generation for Conditional Language Models
Furthermore, the space of potential low-quality outputs is larger as arbitrary text can be generated and it is important to know when to trust the generated output.
Abstractive Text Summarization
Out-of-Distribution Detection
+1
Investigating Efficiently Extending Transformers for Long Input Summarization
While large pretrained Transformer models have proven highly capable at tackling natural language tasks, handling long sequence inputs continues to be a significant challenge.
Ranked #2 on
Long-range modeling
on SCROLLS
(GovRep metric)
SMART: Sentences as Basic Units for Text Evaluation
Specifically, We treat sentences as basic units of matching instead of tokens, and use a sentence matching function to soft-match candidate and reference sentences.
SEAL: Segment-wise Extractive-Abstractive Long-form Text Summarization
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 and Transformer architectures.
PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization
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 summarization.
Ranked #1 on
Abstractive Text Summarization
on AESLC
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP).
Ranked #1 on
Sentiment Analysis
on SST-2 Binary classification
SummAE: Zero-Shot Abstractive Text Summarization using Length-Agnostic Auto-Encoders
We show results for extractive and human baselines to demonstrate a large abstractive gap in performance.
Likelihood Ratios for Out-of-Distribution Detection
We propose a likelihood ratio method for deep generative models which effectively corrects for these confounding background statistics.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Assessing The Factual Accuracy of Generated Text
We propose a model-based metric to estimate the factual accuracy of generated text that is complementary to typical scoring schemes like ROUGE (Recall-Oriented Understudy for Gisting Evaluation) and BLEU (Bilingual Evaluation Understudy).
Using Ontologies To Improve Performance In Massively Multi-label Prediction Models
Massively multi-label prediction/classification problems arise in environments like health-care or biology where very precise predictions are useful.
Using Ontologies To Improve Performance In Massively Multi-label Prediction
Massively multi-label prediction/classification problems arise in environments like health-care or biology where it is useful to make very precise predictions.
MeanSum: A Neural Model for Unsupervised Multi-document Abstractive Summarization
Our proposed model consists of an auto-encoder where the mean of the representations of the input reviews decodes to a reasonable summary-review while not relying on any review-specific features.
Unsupervised Neural Multi-Document Abstractive Summarization of Reviews
Our proposed model consists of an auto-encoder trained so that the mean of the representations of the input reviews decodes to a reasonable summary-review.
Learning to Write Notes in Electronic Health Records
Clinicians spend a significant amount of time inputting free-form textual notes into Electronic Health Records (EHR) systems.
Generating Wikipedia by Summarizing Long Sequences
We show that generating English Wikipedia articles can be approached as a multi- document summarization of source documents.
Scalable and accurate deep learning for electronic health records
Predictive modeling with electronic health record (EHR) data is anticipated to drive personalized medicine and improve healthcare quality.
Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs
On the task of sentiment analysis with the Yelp and SST data sets, we show that CD is able to reliably identify words and phrases of contrasting sentiment, and how they are combined to yield the LSTM's final prediction.
Get To The Point: Summarization with Pointer-Generator Networks
Neural sequence-to-sequence models have provided a viable new approach for abstractive text summarization (meaning they are not restricted to simply selecting and rearranging passages from the original text).
Ranked #12 on
Extractive Text Summarization
on CNN / Daily Mail
Online and Linear-Time Attention by Enforcing Monotonic Alignments
Recurrent neural network models with an attention mechanism have proven to be extremely effective on a wide variety of sequence-to-sequence problems.
Ranked #20 on
Speech Recognition
on TIMIT
Unsupervised Pretraining for Sequence to Sequence Learning
We apply this method to challenging benchmarks in machine translation and abstractive summarization and find that it significantly improves the subsequent supervised models.
