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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Ensuring faithfulness to context in large language models (LLMs) andretrieval-augmented generation (RAG) systems is crucial for reliable deploymentin real-world applications, as incorrect or unsupported information can erodeuser trust. Despite advancements on standard benchmarks, faithfulnesshallucination-where models generate responses misaligned with the providedcontext-remains a significant challenge. In this work, we introduce FaithEval,a novel and comprehensive benchmark tailored to evaluate the faithfulness ofLLMs in contextual scenarios across three diverse tasks: unanswerable,inconsistent, and counterfactual contexts. These tasks simulate real-worldchallenges where retrieval mechanisms may surface incomplete, contradictory, orfabricated information. FaithEval comprises 4.9K high-quality problems intotal, validated through a rigorous four-stage context construction andvalidation framework, employing both LLM-based auto-evaluation and humanvalidation. Our extensive study across a wide range of open-source andproprietary models reveals that even state-of-the-art models often struggle toremain faithful to the given context, and that larger models do not necessarilyexhibit improved faithfulness.Project is available at:https://github.com/SalesforceAIResearch/FaithEval.

FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"