Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2604.26971

T2S-Metrics: Unified Library for Evaluating SPARQL Queries Generated From Natural Language

Yousouf Taghzouti·Tao Jiang·Camille Juigné·Benjamin Navet·Fabien Gandon·Franck Michel·Louis-Felix Nothias
View original source ↗Read source document ↗Export metadata ↓

Abstract

The evaluation of Question Answering (QA) systems over Knowledge Graphs has historically suffered from fragmentation, inconsistency, and limited reproducibility. While significant progress has been made in semantic parsing and SPARQL query generation, evaluation methodologies remain diverse, ad hoc, and often incomparable across studies. Existing benchmarks typically focus on a small subset of metrics, such as query exact match or answer-level F1, neglecting syntactic validity, semantic faithfulness, execution correctness, results ranking quality, and computational efficiency. In this paper, we present t2s-metrics, an open-source, extensible, and unified evaluation library designed specifically for SPARQL query comparison and execution-based assessment. t2s-metrics provides a broad and extensible set of over 20 evaluation metrics, collected from the literature and practical evaluation needs, spanning lexical, syntactic, semantic, structural, execution-based and ranking-based dimensions. These include query-based metrics such as token-level Precision, Recall, and F1; BLEU, ROUGE, METEOR, and CodeBLEU variants; variable-normalized metrics (SP-BLEU, SP-F1); graph-and URI-based exact match metrics; as well as answer set-based metrics such as F1-QALD and Jaccard similarity; ranking metrics including MRR, NDCG, P@k, and Hit@k; and LLM-as-a-Judge metrics. Taking inspiration from the ir-metrics library for Information Retrieval, t2s-metrics provides a modular abstraction layer that decouples metric specification from implementation, enabling consistent, transparent, and reproducible evaluation of SPARQLbased QA systems. We argue that t2s-metrics constitutes a necessary step toward systematic, standardized evaluation in question answering over knowledge graphs and facilitates deeper diagnostic insights into system behavior beyond answer correctness.

Explore related subjects

cs.IR

Keep this discovery

BibTeXRIS

Yousouf Taghzouti, Tao Jiang, Camille Juigné, Benjamin Navet, Fabien Gandon, Franck Michel, Louis-Felix Nothias. 2026-04-22. T2S-Metrics: Unified Library for Evaluating SPARQL Queries Generated From Natural Language. https://arxiv.org/abs/2604.26971

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

UniRec: Cross-stage Multi-Task Fusion with Preference Alignment for Cascaded Recommender Systems

Industrial recommender systems use cascaded stages with different objectives, feature spaces, and latency constraints. Optimizing pre-ranking and ranking separately can create cross-stage inconsistency: upstream models may filter out items preferred by downstream rankers, and independently tuned downstream fusion can offset upstream improvements. Existing multi-task fusion methods focus on multi-objective fusion within the ranking stage, and cross-stage methods typically only add a downstream score factor to upstream ranking. Joint optimization of fusion modules across both stages remains largely unexplored. We propose UniRec, a Unified Cross-stage Recommendation Fusion model. First, the two fusion agents partially share input embeddings and are trained in a single computation graph, so gradients from either stage propagate through the shared representation and influence the other. Second, we introduce a dual-axis preference alignment objective: a vertical cross-stage consistency term transfers downstream pairwise preferences to the upstream fusion score, and a horizontal compact aggregation term reorganizes dozens of pairwise objectives over heterogeneous prior signals into bidirectional preference evidence. Third, we find that unconstrained end-to-end fusion optimization can exploit imbalances in item attribute distributions, over-concentrating on high-reward regions at the cost of other objectives. We therefore add an attribute group-relative regularization that computes advantages within attribute groups and normalizes the policy over the same groups, so uniformly promoting an entire high-reward group yields no optimization gain. Offline, UniRec consistently outperforms single-stage fusion and cross-stage coordination baselines. Online A/B tests show a 0.616\% gain in app usage duration. UniRec is fully deployed on the Kuaishou platform.

cs.IR↗
arXiv2026

VikingRAG: Accurate and Token-efficient Retrieval-augmented Generation over Structured Documents

State-of-the-art retrieval-augmented generation (RAG) methods exploit document structures to acquire sufficient evidence, but often incur substantial token costs. To reduce structural-context tokens without compromising high RAG accuracy, we present {\sf VikingRAG}, a directory-aware semantic data management system that tightly integrates semantic and structural access to support structural-context-efficient, evidence-gap-driven multi-round retrieval. To further reduce token overhead of multi-round interaction, we materialize agentic multi-round retrieval traces as experience edges, and reuse these edges for similar queries, avoiding repeated multi-round exploration. To additionally reduce token costs when agentic multi-round retrieval is unnecessary, we introduce an adaptive escalation strategy that answers from one-round experience-augmented retrieval when the evidence is sufficient, and invokes agentic multi-round retrieval only otherwise. Experiments on real datasets show that the base system {\sf VikingRAG} matches high accuracy of state-of-the-art methods while consuming only 11.6\%--51.9\% of their tokens. With retrieval-trace reuse and adaptive escalation, token costs drop to 5.1\%--32.5\% while maintaining competitive accuracy and practical document-storage performance, showing the utility of this work for emerging AI knowledge bases.

cs.IR↗
arXiv2026

TimelyRAG: Semantic-Temporal Hybrid Retrieval for Time-Critical Question Answering in Overlapping-Evolving Documents

Although large language models (LLMs) and retrieval-augmented generation (RAG) have advanced open-domain question answering (QA), they remain unreliable when documents evolve through amendments. Existing time-sensitive retrieval methods address only the disjoint-evolving environment, where each update is an independent snapshot. However, laws, policies, and regulations often operate in overlapping-evolving environments, where amendments override earlier clauses while preserving most content, creating strong semantic overlap across versions. We propose TimelyRAG, a retriever-agnostic framework that incorporates temporal distance into ranking to align queries with version-appropriate documents. We also introduce TimelyQABench, the first benchmark for regulation-heavy domains with overlapping-evolving challenges. Experiments show consistent gains, up to +28.6% in nDCG@10, highlighting the importance of temporal reasoning for reliable QA over evolving documents. All resources are available at https://github.com/kaist-dmlab/TimelyRAG.

cs.IR↗