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

Large language models (LLMs) have experienced notable advancements ingenerating coherent and contextually relevant responses. However,hallucinations - incorrect or unfounded claims - are still prevalent, promptingthe creation of automated metrics to detect these in LLM outputs. Ourcontributions include: introducing ChainPoll, an innovative hallucinationdetection method that excels compared to its counterparts, and unveilingRealHall, a refined collection of benchmark datasets to assess hallucinationdetection metrics from recent studies. While creating RealHall, we assessedtasks and datasets from previous hallucination detection studies and observedthat many are not suitable for the potent LLMs currently in use. Overcomingthis, we opted for four datasets challenging for modern LLMs and pertinent toreal-world scenarios. Using RealHall, we conducted a comprehensive comparisonof ChainPoll with numerous hallucination metrics from recent studies. Ourfindings indicate that ChainPoll outperforms in all RealHall benchmarks,achieving an overall AUROC of 0.781. This surpasses the next best theoreticalmethod by 11% and exceeds industry standards by over 23%. Additionally,ChainPoll is cost-effective and offers greater transparency than other metrics.We introduce two novel metrics to assess LLM hallucinations: Adherence andCorrectness. Adherence is relevant to Retrieval Augmented Generation workflows,evaluating an LLM's analytical capabilities within given documents andcontexts. In contrast, Correctness identifies logical and reasoning errors.

Chainpoll: A high efficacy method for LLM hallucination detection