Investigating Answerability of LLMs for Long-Form Question Answering

These new tools could make AI vision systems less biased

Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers

Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks

Llama 2: Open Foundation and Fine-Tuned Chat Models

Language models and linguistic theories beyond words

Large language models encode clinical knowledge

OpenELM/OpenELM_Paper.pdf at paper · CarperAI/OpenELM · GitHub

Large-scale Text-to-Image Generation Models for Visual Artists' Creative Works

Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias

Towards Measuring the Representation of Subjective Global Opinions in Language Models

Speed Is All You Need: On-Device Acceleration of Large Diffusion Models via GPU-Aware Optimizations

Opportunities and Risks of LLMs for Scalable Deliberation with Polis

ZeRO++: Extremely Efficient Collective Communication for Giant Model Training - Microsoft Research

Gorilla: Large Language Model Connected with Massive APIs

ChemCrow: Augmenting large-language models with chemistry tools

Demystifying GPT Self-Repair for Code Generation

LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion

FinGPT: Open-Source Financial Large Language Models

The Curse of Recursion: Training on Generated Data Makes Models Forget

LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day

FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance

DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text

Cross-Lingual Supervision improves Large Language Models Pre-training

Deliberate then Generate: Enhanced Prompting Framework for Text Generation

Entailment as Robust Self-Learner

Researchers unveil first Chat-GPT-designed robot

SelFee: Iterative Self-Revising LLM Empowered by Self-Feedback Generation

Faith and Fate: Limits of Transformers on Compositionality

SQL-PaLM: Improved Large Language ModelAdaptation for Text-to-SQL