Enoki is a collection of models and datasets for efficient, fine-grained hallucination detection and fact extraction.
s-nlp
university
AI & ML interests
Natural Language Processing
Recent Activity
Papers
Enoki: Efficient Multi-Level Hallucination Detection
PersonalAI 2.0: Enhancing knowledge graph traversal/retrieval with planning mechanism for Personalized LLM Agents
Models and datasets from the paper: "How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?" https://arxiv.org/abs/2502.14502
-
How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?
Paper • 2502.14502 • Published • 93 -
s-nlp/Llama-3.1-8B-Instruct-TriviaQA-HighlyKnown
Viewer • Updated • 91k • 59 -
s-nlp/Llama-3.1-8B-Instruct-DBpedia-HighlyKnown
Viewer • Updated • 21k • 69 -
s-nlp/Mistral-7b-0.3-Instruct-TriviaQA-HighlyKnown
Viewer • Updated • 91k • 29
Enoki is a collection of models and datasets for efficient, fine-grained hallucination detection and fact extraction.
Data and models from NAACL 2025 paper "SynthDetoxM: Modern LLMs are Few-Shot Parallel Detoxification Data Annotators" by Moskovskiy et al.
Models and datasets from the paper: "How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?" https://arxiv.org/abs/2502.14502
-
How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?
Paper • 2502.14502 • Published • 93 -
s-nlp/Llama-3.1-8B-Instruct-TriviaQA-HighlyKnown
Viewer • Updated • 91k • 59 -
s-nlp/Llama-3.1-8B-Instruct-DBpedia-HighlyKnown
Viewer • Updated • 21k • 69 -
s-nlp/Mistral-7b-0.3-Instruct-TriviaQA-HighlyKnown
Viewer • Updated • 91k • 29
Models and datasets from the paper: "LLMs to Replace Crowdsourcing For Parallel Data Creation? The Case of Text Detoxification" by Moskovskiy et al.