Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback

Abstract

Large language models (LLMs), such as ChatGPT, are able to generate human-like, fluent responses for many downstream tasks, e.g., task-oriented dialog and question answering. However, applying LLMs to real-world, mission-critical applications remains challenging mainly due to their tendency to generate hallucinations and their inability to use external knowledge. This paper proposes a LLM-Augmenter system, which augments a black-box LLM with a set of plug-and-play modules. Our system makes the LLM generate responses grounded in external knowledge, e.g., stored in task-specific databases. It also iteratively revises LLM prompts to improve model responses using feedback generated by utility functions, e.g., the factuality score of a LLM-generated response. The effectiveness of LLM-Augmenter is empirically validated on two types of scenarios, task-oriented dialog and open-domain question answering. LLM-Augmenter significantly reduces ChatGPT's hallucinations without sacrificing the fluency and informativeness of its responses. We make the source code and models publicly available.

arXiv comment15 pages

Cited by in corpus (14)

• Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models
• Factuality Challenges in the Era of Large Language Models
• Understanding Large-Language Model (LLM)-powered Human-Robot Interaction
• Woodpecker: Hallucination Correction for Multimodal Large Language Models
• Abstractive Text Summarization: State of the Art, Challenges, and Improvements
• LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers
• C2Ideas: Supporting Creative Interior Color Design Ideation with Large Language Model
• Hallucination Detection in Foundation Models for Decision-Making: A Flexible Definition and Review of the State of the Art
• An Evaluation on Large Language Model Outputs: Discourse and Memorization
• Domain-specific ChatBots for Science using Embeddings
• ShennongAlpha: an AI-driven sharing and collaboration platform for intelligent curation, acquisition, and translation of natural medicinal material knowledge
• Large Language Models to the Rescue: Reducing the Complexity in Scientific Workflow Development Using ChatGPT
• Gender Bias Detection in Court Decisions: A Brazilian Case Study
• Hallucinations in LLMs: A Lifecycle-Based Survey of Causes, Detection, Mitigation, and Prevention