ReformIR adaptively prioritizes reformulations and documents with a surrogate model guided by ranker feedback to boost recall while suppressing drift under fixed reranking budgets.
Voorhees, and Ian Soboroff
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
dataset 1
citation-polarity summary
representative citing papers
DITTO uses RL with verbal feedback to train LLMs for human behavior simulation, reporting 36% average gains over base models and outperforming GPT-5.4 on 6 of 10 SOUL benchmark tasks.
MIRA is a new benchmark for multi-category integrated retrieval built from real queries on a social science platform, with LLM assistance for topic descriptions and relevance labeling across four item categories.
Synthetically formalizing information needs into topics with descriptions and narratives improves LLM relevance assessor agreement with humans and reduces over-labeling of relevant documents on TREC Deep Learning and Robust04.
Introduces the LLM ORDER BY semantic operator with algorithmic improvements, a semantic-aware external merge sort, and a budget-aware optimizer that selects near-optimal access paths for LLM-based ordering.
RecNextEval is a reference implementation that applies time-window splits for temporal next-batch recommendation evaluation to minimize data leakage.
citing papers explorer
-
When More Reformulations Hurt: Avoiding Drift using Ranker Feedback
ReformIR adaptively prioritizes reformulations and documents with a surrogate model guided by ranker feedback to boost recall while suppressing drift under fixed reranking budgets.
-
Reinforcing Human Behavior Simulation via Verbal Feedback
DITTO uses RL with verbal feedback to train LLMs for human behavior simulation, reporting 36% average gains over base models and outperforming GPT-5.4 on 6 of 10 SOUL benchmark tasks.
-
MIRA: An LLM-Assisted Benchmark for Multi-Category Integrated Retrieval
MIRA is a new benchmark for multi-category integrated retrieval built from real queries on a social science platform, with LLM assistance for topic descriptions and relevance labeling across four item categories.
-
Formalized Information Needs Improve Large-Language-Model Relevance Judgments
Synthetically formalizing information needs into topics with descriptions and narratives improves LLM relevance assessor agreement with humans and reduces over-labeling of relevant documents on TREC Deep Learning and Robust04.
-
Access Paths for Efficient Ordering with Large Language Models
Introduces the LLM ORDER BY semantic operator with algorithmic improvements, a semantic-aware external merge sort, and a budget-aware optimizer that selects near-optimal access paths for LLM-based ordering.
-
RecNextEval: A Reference Implementation for Temporal Next-Batch Recommendation Evaluation
RecNextEval is a reference implementation that applies time-window splits for temporal next-batch recommendation evaluation to minimize data leakage.