Madian Khabsa

Keeping Notes: Conditional Natural Language Generation with a Scratchpad Encoder

2019

We introduce the Scratchpad Mechanism, a novel addition to the sequence-to-sequence (seq2seq) neural network architecture and demonstrate its effectiveness in improving the overall fluency of seq2seq models for natural language generation tasks. By enabling the …

Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

2023 · arXiv (Cornell University)

We introduce Llama Guard, an LLM-based input-output safeguard model geared towards Human-AI conversation use cases. Our model incorporates a safety risk taxonomy, a valuable tool for categorizing a specific set of safety risks found in …

Entailment as Few-Shot Learner

2021 · arXiv (Cornell University)

Large pre-trained language models (LMs) have demonstrated remarkable ability as few-shot learners. However, their success hinges largely on scaling model parameters to a degree that makes it challenging to train and serve. In this paper, …

Llama 2: Open Foundation and Fine-Tuned Chat Models

2023 · arXiv (Cornell University)

In this work, we develop and release Llama 2, a collection of pretrained and fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama 2-Chat, …