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
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
method 2
citation-polarity summary
verdicts
UNVERDICTED 6roles
method 2polarities
use method 2representative citing papers
Merlin generates CodeQL queries from natural language questions via RAG-based iteration and a self-test technique using assistive queries, achieving 3.8x higher task accuracy and 31% less completion time in user studies while finding additional software issues.
SPARK improves LLM-based test code fault localization by retrieving similar past faults and selectively annotating suspicious lines in new failing tests.
A RAG-enhanced LLM pipeline with segmentation improves C-to-Rust transpilation correctness and eliminates raw pointer dereferences and unsafe type casts in several Coreutils programs.
Mujica-MyGo decomposes multi-turn RAG interactions via multi-agent workflows and applies minimalist policy gradient optimization to improve performance on QA benchmarks while avoiding long-context problems.
KUBO, a dual-module platform for verified government updates and community discussions, outperforms Facebook in task speed, information recall, and user satisfaction for hyperlocal communication in the Philippines.
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.
-
Generating Complex Code Analyzers from Natural Language Questions
Merlin generates CodeQL queries from natural language questions via RAG-based iteration and a self-test technique using assistive queries, achieving 3.8x higher task accuracy and 31% less completion time in user studies while finding additional software issues.
-
Similar Pattern Annotation via Retrieval Knowledge for LLM-Based Test Code Fault Localization
SPARK improves LLM-based test code fault localization by retrieving similar past faults and selectively annotating suspicious lines in new failing tests.
-
LLM4C2Rust: Large Language Models for Automated Memory-Safe Code Transpilation
A RAG-enhanced LLM pipeline with segmentation improves C-to-Rust transpilation correctness and eliminates raw pointer dereferences and unsafe type casts in several Coreutils programs.
-
Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning
Mujica-MyGo decomposes multi-turn RAG interactions via multi-agent workflows and applies minimalist policy gradient optimization to improve performance on QA benchmarks while avoiding long-context problems.
-
User-Centered Design of Hyperlocal Communication Platforms: Insights from the Design and Evaluation of KUBO
KUBO, a dual-module platform for verified government updates and community discussions, outperforms Facebook in task speed, information recall, and user satisfaction for hyperlocal communication in the Philippines.