Small LMs reach 77.1% accuracy at comparative forecasting of research idea success on benchmarks after supervised fine-tuning, with RLVR yielding interpretable reasoning at 71.35%.
ScholarEval: Research Idea Evaluation Grounded in Literature
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
SciAtlas builds a large-scale multi-disciplinary academic knowledge graph and a neuro-symbolic retrieval system to support automated scientific research tasks such as literature review and idea positioning.
citing papers explorer
-
Teaching Language Models to Forecast Research Success Through Comparative Idea Evaluation
Small LMs reach 77.1% accuracy at comparative forecasting of research idea success on benchmarks after supervised fine-tuning, with RLVR yielding interpretable reasoning at 71.35%.
-
SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research
SciAtlas builds a large-scale multi-disciplinary academic knowledge graph and a neuro-symbolic retrieval system to support automated scientific research tasks such as literature review and idea positioning.