Causal inference in natural language processing: Estimation, prediction, interpretation and beyond
A fundamental goal of scientific research is to learn about causal relationships. However,
despite its critical role in the life and social sciences, causality has not had the same …
despite its critical role in the life and social sciences, causality has not had the same …
Deep learning for text style transfer: A survey
Text style transfer is an important task in natural language generation, which aims to control
certain attributes in the generated text, such as politeness, emotion, humor, and many …
certain attributes in the generated text, such as politeness, emotion, humor, and many …
A recipe for arbitrary text style transfer with large language models
In this paper, we leverage large language models (LMs) to perform zero-shot text style
transfer. We present a prompting method that we call augmented zero-shot learning, which …
transfer. We present a prompting method that we call augmented zero-shot learning, which …
In-context vectors: Making in context learning more effective and controllable through latent space steering
Large language models (LLMs) demonstrate emergent in-context learning capabilities,
where they adapt to new tasks based on example demonstrations. However, in-context …
where they adapt to new tasks based on example demonstrations. However, in-context …
Rewritelm: An instruction-tuned large language model for text rewriting
Large Language Models (LLMs) have demonstrated impressive capabilities in creative tasks
such as storytelling and E-mail generation. However, as LLMs are primarily trained on final …
such as storytelling and E-mail generation. However, as LLMs are primarily trained on final …
Causal-structure driven augmentations for text ood generalization
The reliance of text classifiers on spurious correlations can lead to poor generalization at
deployment, raising concerns about their use in safety-critical domains such as healthcare …
deployment, raising concerns about their use in safety-critical domains such as healthcare …
Frmt: A benchmark for few-shot region-aware machine translation
We present FRMT, a new dataset and evaluation benchmark for Few-shot Region-aware
Machine Translation, a type of style-targeted translation. The dataset consists of professional …
Machine Translation, a type of style-targeted translation. The dataset consists of professional …
Impact of large language models on generating software specifications
Software specifications are essential for ensuring the reliability of software systems. Existing
specification extraction approaches, however, suffer from limited generalizability and require …
specification extraction approaches, however, suffer from limited generalizability and require …
Story centaur: Large language model few shot learning as a creative writing tool
B Swanson, K Mathewson, B Pietrzak… - Proceedings of the …, 2021 - aclanthology.org
Few shot learning with large language models has the potential to give individuals without
formal machine learning training the access to a wide range of text to text models. We …
formal machine learning training the access to a wide range of text to text models. We …
Counterfactual generation with identifiability guarantees
Counterfactual generation lies at the core of various machine learning tasks, including
image translation and controllable text generation. This generation process usually requires …
image translation and controllable text generation. This generation process usually requires …