Xiangyu Wen
Xiangyu Wen has 2 papers in our library, in 2026, most of them on Summarization, Dialogue systems, Evaluation & benchmarks; often with Da Chen, Zhijian Xu.
OpenAlex · h-index 1 · 9 works · 7 citations OpenAlex, 2026-10-14
Affiliations
🎓Chinese University of Hong KongHong Kong ·
China2024–2026 · 5 papers🎓Lanzhou University of TechnologyLanzhou ·
China2023–2026 · 5 papers
Fields, topics and concepts
📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 2 worksArts and Humanities · 2 worksComputer Science · 2 worksLanguage and Linguistics · 2 works
🧭 Topics 4Research subjects and languages the work is about.Dialogue systems · 1 workEvaluation & benchmarks · 1 workReasoning · 1 workSummarization · 1 work
Works by year
2020s
Papers
- Solve-Detect-Verify: Inference-Time Scaling with Flexible Generative Verifier (2026 · 1 citation)
Step-by-step reasoning in LLMs creates a cost problem. Solvers keep generating text after they already have an answer, and checking their work is expensive. Process-based verifiers such as GenPRM re-read the context at every step. Cheap "NoThinking"-style checks are fast but flag many false positives. - Beyond Overlap Metrics: Rewarding Reasoning and Preferences for Faithful Multi-Role Dialogue Summarization (2026)
The paper addresses the problem that summarizers of multi-speaker conversations are usually tuned toward overlap metrics such as ROUGE and BERTScore.
Co-authors here
Venues
- Annual Meeting of the Association for Computational Linguistics (ACL): ACL 2026
- Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2026
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/xiangyu-wen/