Search papers, labs, and topics across Lattice.
Affiliation:, University of Toronto, Reviewerly
3
0
5
4
QueryRoute is introduced, a benchmark that freezes the expensive artifacts needed to study this inference-time decision problem reproducibly: original queries, generated variants, ranked lists under multiple retrievers, retrieval scores, and per-query oracle labels.
Current LLM detection methods in peer review are fooled by hybrid human-AI workflows, mistaking AI-written text for AI-originated ideas.
Denoising diffusion models can significantly outperform discriminative methods in learning-to-rank, suggesting a new path for improving information retrieval.