Search Results for author:
Found 11 papers, 9 papers with code
Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP
Retrieval-augmented in-context learning has emerged as a powerful approach for addressing knowledge-intensive tasks using frozen language models (LM) and retrieval models (RM).
Evaluating Human-Language Model Interaction
Many real-world applications of language models (LMs), such as code autocomplete and writing assistance, involve human-LM interaction.
Contrastive Decoding: Open-ended Text Generation as Optimization
We propose contrastive decoding (CD), a more reliable search objective that returns the difference between likelihood under a large LM (called the expert, e. g. OPT-13b) and a small LM (called the amateur, e. g. OPT-125m).
Diffusion-LM Improves Controllable Text Generation
Controlling the behavior of language models (LMs) without re-training is a major open problem in natural language generation.
Ensembles and Cocktails: Robust Finetuning for Natural Language Generation
When finetuning a pretrained language model for natural language generation tasks, one is currently faced with a tradeoff.
On the Opportunities and Risks of Foundation Models
AI is undergoing a paradigm shift with the rise of models (e. g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks.
Prefix-Tuning: Optimizing Continuous Prompts for Generation
Fine-tuning is the de facto way to leverage large pretrained language models to perform downstream tasks.
Decoding Methods for Neural Narrative Generation
Narrative generation is an open-ended NLP task in which a model generates a story given a prompt.
Posterior Control of Blackbox Generation
In this work, we consider augmenting neural generation models with discrete control states learned through a structured latent-variable approach.
Specializing Word Embeddings (for Parsing) by Information Bottleneck
Pre-trained word embeddings like ELMo and BERT contain rich syntactic and semantic information, resulting in state-of-the-art performance on various tasks.
A Generative Model for Punctuation in Dependency Trees
When the tree's yield is rendered as a written sentence, a string rewriting mechanism transduces the underlying marks into "surface" marks, which are part of the observed (surface) string but should not be regarded as part of the tree.
