Fine-grained Hallucination Detection and Editing for Language Models
· 2 min read
Fine-grained Hallucination Detection and Editing for Language Models
Provides a taxonomy of different types of hallucinations.
· 1 min read
Weaviate Paper Reviews
Long-Context Retrieval Models with Monarch Mixer
· 2 min read
Long-Context Retrieval Models with Monarch Mixer
32k context length retreival models with sub-quadratic attention mechanism.
· 1 min read
How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs
· One min read
How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs
Using persuasion ot jailbreak LLM's.
· 1 min read
Improving Text Embeddings with Large Language Models
· 3 min read
Improving Text Embeddings with Large Language Models
Presents a 7B parameter embedding model.
· 2 min read
Discovering the Hidden Vocabulary of DALLE-2
· 2 min read
Discovering the Hidden Vocabulary of DALLE-2
text2image diffusion models learn and use a secret language.
· 1 min read
Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs
· 2 min read
Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs
Compares finetuning vs RAG for improvement on a specific domain.
· 2 min read