A research proposal can describe an established mechanism correctly while claiming to introduce it. We study whether providing the earlier paper corrects such contribution claims. Three controlled experiments compare proposals generated with a contribution-bearing prior and a same-topic control. Providing the prior yields no clear aggregate reduction in unsupported novelty. Human analysis of 175 interpretable exposed proposals finds that 137 recognize the prior's relevance, but 61 correctly attribute the established contribution. Of 71 proposed remaining distinctions, 37 are covered by the same prior. We introduce Research Idea Novelty Inspection (RINI), which audits contribution claims against evidence, checks the remaining distinction, and applies local revisions. Five human annotators evaluate 1,080 original-revision pairs across three methods. On the same 240 originals judged to require correction, successful repair is 11.7% for Self-Revision, 39.1% for Retrieve-and-Revise, and 72.2% for RINI, with research tasks weighted equally. The improvement over same-evidence direct revision is 33.0 percentage points. The revised proposals retain their research questions and technical methods. These results motivate explicit contribution attribution when using literature to generate and revise research proposals.
Self-Conditioning is proposed, an unsupervised information-theoretic estimator that compares the likelihood of a review under its production context with its likelihood when that context is augmented with hints extracted from the review itself, and how that context is augmented with hints extracted from the review itse...
Matthieu Dubois, Pablo Piantanida, François Yvon· 0 citations
The Lit2Test benchmark centers on a six-field contract organized around a falsifying outcome, so that every proposal precommits the observation that would prove it wrong, making its quality decidable in the first place rather than merely arguable.
Zi-Yue Wang, Aomufei Yuan, Yi-Ran Yao et al.· 2 citations
It is shown that prior scores, even when included only as context metadata, anchor judgments and systematically shift ratings toward their values, and effective mitigation must be validated for the intended model and task or domain.
A. Kapetanović, Kemal Altwlkany, Andro Merćep et al.· 1 citation
This article argues that “AI use” is too blunt a category for judging what happens when a student writes a humanities paper with a large language model. Taking the most intensive case, a paper built with AI from research to final review, it follows the changing relation between student, model, sources, and draft. In re...
Joshua Leonardo Lupowitz· Tiempo devorado· 0 citations
Automated ideation systems are often evaluated on the novelty of the ideas they produce, and that judgment is increasingly delegated to large language models. Such judges are typically built ad hoc and validated, if at all, on human-authored papers rather than on the generated ideas they are meant to score. So, how do...
Noy Sternlicht, Simra Shahid, P. Jansen et al.· 0 citations
This work introduces DocCite, to its knowledge the first benchmark for systems that verify and correct page-level citations in document images, and proposes AtomCite, an agentic framework that parses an answer into claims, checks each claim against the image of its cited page, and applies a deterministic repair policy.
Chen Qian, Yi-Meng Wang, Yu Chen et al.· 0 citations