safe.llm

Reflexion: Language Agents with Verbal Reinforcement Learning

CYBERSECEVAL 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models

WizardLM: Empowering Large Language Models to Follow Complex Instructions

Evaluating LLM Chatbot Conversations with Athina AI

How to Use a Custom Grading Criteria to Evaluate LLM Responses (LLM-as-a-Judge)

How to evaluate your Llama Index query engine using Ragas evals + Athina AI

If you're using Llama Index to work with advanced retrieval strategies, you're going to need a great evaluation setup. Here's how you can use Athina's SDK to run Ragas evals on your Llama Index RAG pipeline.

Reflexion: Language Agents with Verbal Reinforcement Learning

Prompt Injection: Different Attacks and Defensive Techniques

Overview of Prompt Engineering Techniques

Prompt Engineering is an emerging field and the techniques are evolving every day. This article breaks down prompt engineering into a list of techniques.

Prompt Injection: Different Attacks and Defensive Techniques

CYBERSECEVAL 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models

From Noise to Clarity: Unraveling the Adversarial Suffix of Large Language Model Attacks via Translation of Text Embeddings

How to Use a Custom Grading Criteria to Evaluate LLM Responses (LLM-as-a-Judge)

Ever: Mitigating Hallucination in Large Language Models through Real-Time Verification and Rectification

The EVER (Real-Time Verification and Rectification) framework is designed to dynamically mitigate hallucinations during text generation by ensuring the accuracy and trustworthiness of each sentence before proceeding.

Factuality of Large Language Models in the Year 2024