Xingyu Song
Xingyu Song has 2 papers in our library, in 2025–2026, most of them on Question answering, Evaluation & benchmarks, Reasoning; often with Irene Li, Fan Gao, Mona Diab.
OpenAlex · h-index 12 · 48 works · 444 citations OpenAlex, 2026-10-14
📄 2 works in our library · 🔗 Cited 6 times in our library · ⭐ Paper Stars ranking: #11451
Affiliations
Fields, topics and concepts
📚 Shelves 7The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 2 worksComputer Science · 2 worksArtificial Intelligence · 2 worksLanguage and Linguistics · 2 worksComputer Vision and Pattern Recognition · 1 workPsychology · 1 workSocial Psychology · 1 work
🧭 Topics 3Research subjects and languages the work is about.Question answering · 1 workReasoning · 1 workEvaluation & benchmarks · 1 work
Works by year
2020s
Papers
- ReAgent: Reversible Multi-Agent Reasoning for Knowledge-Enhanced Multi-Hop QA (2025 · 8 citations)
Multi-hop QA requires chaining evidence from several sources. Standard LLM pipelines, including CoT prompting, retrieval-augmented generation and many multi-agent systems, move only forward. An error in an early hop carries through to the end, and contradictions found later have no structured way to force a revision.… - JiraiBench: A Bilingual Benchmark for Evaluating Large Language Models' Detection of Human risky health behavior Content in Jirai Community (2026)
Online content about risky health behaviors (RHB) is hard to moderate automatically. Prior work mostly targets one behavior at a time, relies heavily on English data, and pays little attention to community context and coded vocabulary. The authors address this through the Jirai ("landmine") subculture, a Japan-born…
Co-authors here
Venues
- Conference of the European Chapter of the Association for Computational Linguistics (EACL): EACL 2026
- Conference on Empirical Methods in Natural Language Processing (EMNLP): EMNLP 2025
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/xingyu-song/