The authors release the Wikidata Query Logs dataset containing 335k real question-query pairs constructed via an agent-based de-anonymization process from query service logs.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Scoring functions are sub-optimal for all utility-fairness trade-offs in ranking under a generic fairness formulation, but semi-greedy post-processing can approach the performance of exhaustive post-processing.
GRISP fine-tunes a small language model on skeleton generation and list-wise re-ranking to iteratively complete SPARQL queries over knowledge graphs, reporting better benchmark results than prior methods.
citing papers explorer
-
The Wikidata Query Logs Dataset
The authors release the Wikidata Query Logs dataset containing 335k real question-query pairs constructed via an agent-based de-anonymization process from query service logs.
-
Scoring Is Not Enough: Addressing Gaps in Utility-fairness Trade-offs for Ranking
Scoring functions are sub-optimal for all utility-fairness trade-offs in ranking under a generic fairness formulation, but semi-greedy post-processing can approach the performance of exhaustive post-processing.
-
GRISP: Guided Recurrent IRI Selection over SPARQL Skeletons
GRISP fine-tunes a small language model on skeleton generation and list-wise re-ranking to iteratively complete SPARQL queries over knowledge graphs, reporting better benchmark results than prior methods.