Hallucinations

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.

AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection

Factuality of Large Language Models in the Year 2024

DiffusionGPT: LLM-Driven Text-to-Image Generation System

Deficiency of Large Language Models in Finance: An Empirical Examination of Hallucination

A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions

AutoHall: Automated Hallucination Dataset Generation for Large Language Models

Chain-of-Verification Reduces Hallucination in Large Language Models

Exploring the Relationship between LLM Hallucinations and Prompt Linguistic Nuances: Readability, Formality, and Concreteness