English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In the era of large language models (LLMs), hallucination (i.e., the tendencyto generate factually incorrect content) poses great challenge to trustworthyand reliable deployment of LLMs in real-world applications. To tackle the LLMhallucination, three key questions should be well studied: how to detecthallucinations (detection), why do LLMs hallucinate (source), and what can bedone to mitigate them (mitigation). To address these challenges, this workpresents a systematic empirical study on LLM hallucination, focused on the thethree aspects of hallucination detection, source and mitigation. Specially, weconstruct a new hallucination benchmark HaluEval 2.0, and designs a simple yeteffective detection method for LLM hallucination. Furthermore, we zoom into thedifferent training or utilization stages of LLMs and extensively analyze thepotential factors that lead to the LLM hallucination. Finally, we implement andexamine a series of widely used techniques to mitigate the hallucinations inLLMs. Our work has led to several important findings to understand thehallucination origin and mitigate the hallucinations in LLMs. Our code and datacan be accessed at https://github.com/RUCAIBox/HaluEval-2.0.

The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models