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 emerged as versatile tools in various dailyapplications. However, they are fraught with issues that undermine theirutility and trustworthiness. These include the incorporation of erroneousreferences (citation), the generation of hallucinated information(correctness), and the inclusion of superfluous or omission of crucial details(fluency). To ameliorate these concerns, this study makes several keycontributions. First, we build a dataset to train a critic model capable ofevaluating the citation, correctness, and fluency of responses generated byLLMs in QA systems. Second, we propose an automated feedback mechanism thatleverages the critic model to offer real-time feedback on heterogeneous aspectsof generated text. Third, we introduce a feedback learning loop that uses thiscritic model to iteratively improve the performance of the LLM responsible forresponse generation. Experimental results demonstrate the efficacy of ourapproach, showing substantial improvements in citation and fluency metrics forChatGPT, including a 4% precision increase in citation and an approximately 8%enhancement in the MAUVE metric for fluency, while maintaining high levels ofcorrectness.

Towards Reliable and Fluent Large Language Models: Incorporating Feedback Learning Loops in QA Systems