Skip to main content
Search

# Forward-Citation Supervision

1 related articles

Subscribe to updates
  1. arXiv

    Research ideation stalls at step one: forward-citation supervision lifts an 8B model to 0.452 graded recall on held-out NLP papers

    In automated research ideation, the step of finding a limitation that later work can actually pick up has lacked a direct supervision signal. ActLim-Bench links each source paper's limitation to the later citing work that adopted it as motivation and tried to address it, yielding 18,279 evidence-linked triples. ActLim-8B, post-trained in three stages on that signal, reaches 0.452 graded recall on a temporally held-out 2024–2025 NLP test set against 0.262 for the strongest zero-shot baseline, and transfers from NLP-only training to computer vision at 0.314 versus 0.252.

You’re all caught up