Sensitive Neuron Dropout (SeND): A Novel Training Protocol for Mitigating Hallucinations in Large Language Models
This research paper introduces Sensitive Neuron Dropout (SeND), a novel training protocol designed to mitigate hallucinations in Large Language Models (LLMs) by reducing variance in factual certainty during the training process.
Self-Highlighted Hesitation (SH2): A Method for Improving the Truthfulness of Large Language Model Decoding
The SH2 method improves the truthfulness of large language models by identifying and highlighting key tokens in the input text, forcing the model to hesitate and consider these tokens more carefully during decoding.
Enhancing Factual Accuracy of Large Language Models through Adaptive Retrieval Augmentation
Rowen, a novel framework that enhances large language models (LLMs) with an adaptive retrieval augmentation process to effectively mitigate hallucinated outputs.
Mitigating Hallucinations in Large Language Models via Conformal Abstention
Large language models can confidently generate responses that are incorrect or nonsensical (hallucinations). This work proposes a principled procedure to determine when the model should abstain from responding, instead of hallucinating, by leveraging the model's self-consistency as a measure of confidence.
Mitigating Hallucinations in Large Language Models through Targeted Interventions
Effective strategies for mitigating hallucinations in large language models through targeted interventions in specific model components.
Mitigating Hallucinations in Large Language Models through Diversity-Aware Active Learning for Text Summarization
This paper proposes an active learning framework to effectively and efficiently mitigate hallucinations in large language models (LLMs) for text summarization by selecting diverse hallucination samples for annotation and finetuning.
© 2024 by Linnk AI