Search papers, labs, and topics across Lattice.
Affiliation:
7
0
7
9
EviQE is proposed, which aggregates documents retrieved by multiple reformulators, selects a compact evidence set, and uses it for one grounded expansion step, which separates evidence selection from generation and treats reformulators as complementary retrieval perspectives.
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.
A unified toolkit that streamlines the detection of AI-generated content across multiple modalities, making it easier for researchers to benchmark and compare detection algorithms.
LLM-powered query reformulation, a hot topic in IR, often fails to translate gains from lexical to neural retrieval, and bigger models don't always help.
Current LLM detection methods in peer review are fooled by hybrid human-AI workflows, mistaking AI-written text for AI-originated ideas.
Stop prompting LLMs to blindly rewrite queries – ReFormeR distills query transformations into reusable patterns that actually improve retrieval.
Denoising diffusion models can significantly outperform discriminative methods in learning-to-rank, suggesting a new path for improving information retrieval.
