CiteBench: A bench- mark for scientific citation text generation

Martin Funkquist, Ilia Kuznetsov, Yufang Hou, Iryna Gurevych · 2023 · DOI 10.18653/v1/2023.emnlp-main.455

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

open at publisher browse 1 citing papers

representative citing papers

cs.AI · 2026-06-09 · unverdicted · novelty 7.0

A new benchmark and clean-room harness show frontier AI agents reach only 0.337 factual F1 when synthesizing conclusions from scientific evidence.

Showing 1 of 1 citing paper.

Can AI Agents Synthesize Scientific Conclusions? cs.AI · 2026-06-09 · unverdicted · none · ref 40
A new benchmark and clean-room harness show frontier AI agents reach only 0.337 factual F1 when synthesizing conclusions from scientific evidence.