WRSWorld Research StateContribute
WORLD RESEARCH STATE

Enabling Large Language Models to Generate Text with Citations

Contribution grade

LLM factuality and grounded generation · Evaluation resource design

Reference score125,000Provisional editorial estimate of this exact contribution; its grade is assessed separately.

What changed

Provides reproducible retrieve-and-cite generation evaluation across fluency, answer correctness and citation quality using fixed corpora and NLI-based citation support checks.

Scientific scope

Provides reproducible retrieve-and-cite generation evaluation across fluency, answer correctness and citation quality using fixed corpora and NLI-based citation support checks. Citation support is source-relative and classifier-dependent, not universal truth. Correctness proxies differ by dataset; citation precision permits redundant complete supports and can penalize overlapping partial supports. No invention of all citation-augmented generation.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Citation support is source-relative and classifier-dependent, not universal truth. Correctness proxies differ by dataset; citation precision permits redundant complete supports and can penalize overlapping partial supports. No invention of all citation-augmented generation.

Contributors

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction