GS-QA is a new benchmark of 2,800 QA pairs on 28 templates using OSM and Wikipedia data to evaluate LLMs on spatial predicates, multi-source reasoning, and diverse answer types including distances and counts.
Title resolution pending
5 Pith papers cite this work, alongside 154 external citations. Polarity classification is still indexing.
5
Pith papers citing it
154
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
MCompassRAG adds topic metadata to chunk representations and uses LLM distillation to train a lightweight topic-aware retriever, reporting 8.24% average information efficiency gain and over 5x lower latency than strong baselines across six benchmarks.
A query-agnostic black-box attack uses zero-shot surrogate LLMs and adversarial learning on learnable queries to create transferable injection tokens that alter LLM retriever rankings.
GRC unifies generation, retrieval, and compression in LLMs via meta latent tokens for single-pass execution with modular flexibility.
Dense retrieval augmented with ECLASS semantics achieves 94.3% Hit@5 on expert queries for electronic components, substantially outperforming BM25 and foundation-model baselines.
citing papers explorer
-
GS-QA: A Benchmark for Geospatial Question Answering
GS-QA is a new benchmark of 2,800 QA pairs on 28 templates using OSM and Wikipedia data to evaluate LLMs on spatial predicates, multi-source reasoning, and diverse answer types including distances and counts.
-
MCompassRAG: Topic Metadata as a Semantic Compass for Paragraph-Level Retrieval
MCompassRAG adds topic metadata to chunk representations and uses LLM distillation to train a lightweight topic-aware retriever, reporting 8.24% average information efficiency gain and over 5x lower latency than strong baselines across six benchmarks.
-
"Someone Hid It": Query-Agnostic Black-Box Attacks on LLM-Based Retrieval
A query-agnostic black-box attack uses zero-shot surrogate LLMs and adversarial learning on learnable queries to create transferable injection tokens that alter LLM retriever rankings.
-
GRC: Unifying Reasoning-Driven Generation, Retrieval and Compression
GRC unifies generation, retrieval, and compression in LLMs via meta latent tokens for single-pass execution with modular flexibility.
-
ECLASS-Augmented Semantic Product Search for Electronic Components
Dense retrieval augmented with ECLASS semantics achieves 94.3% Hit@5 on expert queries for electronic components, substantially outperforming BM25 and foundation-model baselines.