🧑‍🔬 Wenbo Su

🏛️ Affiliations

🏢Alibaba GroupHangzhou · China2017–2026 · 47 papersEmployment since 2017current🏢Alibaba GroupSan Mateo · United States2025–2026 · 11 paperscurrent🎓ShanghaiTech UniversityShanghai · China2025–2026 · 2 paperscurrent

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues (2024 · 174 citations)
   Existing LLM benchmarks mostly test single-turn instructions. Multi-turn ones such as MT-Bench cover only two turns and broad skill categories, so they miss much of what happens in real chatbot conversations. MT-Bench-101 fills this gap with a fine-grained multi-turn benchmark. The authors studied real user–chatbot…
2. Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning? (2025 · 30 citations)
   Reasoning models in the o1 style produce very long chains of thought (CoT). Until this paper, there was no systematic way to check how good those chains are, or whether other models can find the mistakes in them. The authors built DeltaBench to address both gaps. It contains 1,236 problems from Math, Programming, PCB…
3. Chinese SafetyQA: A Safety Short-form Factuality Benchmark for Large Language Models (2024 · 4 citations)
   Models deployed in China must handle questions about local law, policy and ethics correctly. Existing safety benchmarks mostly use red-teaming or case-based prompts that mix several risks at once, which makes it hard to tell which areas of safety knowledge a model lacks. The authors introduce Chinese SafetyQA, a…
4. USB: A COMPREHENSIVE AND UNIFIED SAFETY EVALUATION BENCHMARK FOR MULTIMODAL LARGE LANGUAGE MODELS (2026 · 1 citation)
   Existing safety benchmarks for multimodal large language models (MLLMs) cover few risk types and contain few samples.
5. PretrainRL: Alleviating Factuality Hallucination of Large Language Models at the Beginning (2026)
   The paper addresses factual hallucinations in LLMs, meaning confident statements that can be checked and shown false.
6. Read As Human: Compressing Context via Parallelizable Close Reading and Skimming (2026)
   Long prompts, such as those produced by retrieval-augmented generation, make LLM inference slow because attention cost grows quadratically.
7. SELECting over Tokens: Curating Pre-training Data at Scale via Token Classification (2026)
   Web-scraped pre-training corpora contain a lot of boilerplate and noise. Standard cleaning pipelines use document-level heuristics that can only keep or drop whole pages. Generative token-level refiners such as ProX-C are finer-grained but slow at scale and may hallucinate edits. The authors propose SelecT, which…

All works

10 works of theirs in our library, the most cited first; 7 with a page here, the others link their original until we summarise them.

1. MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn DialoguesAnnual Meeting of the Association for Computational Linguistics (ACL)Ge Bai, Jie Liu, Xingyuan Bu, et al.2024 · 174 citations
2. SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines ↗arXiv:2502.14739 · no summary yetM-A-P Team et al.2025 · 89 citations
3. Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning?Annual Meeting of the Association for Computational Linguistics (ACL)Yancheng He, Shilong Li, Jiaheng Liu, et al.2025 · 30 citations
4. Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning ↗arXiv:2508.08221 · no summary yetZihe Liu et al.2025 · 15 citations
5. Deconstructing Long Chain-of-Thought: A Structured Reasoning Optimization Framework for Long CoT Distillation ↗arXiv:2503.16385 · no summary yetYijia Luo et al.2025 · 14 citations
6. Chinese SafetyQA: A Safety Short-form Factuality Benchmark for Large Language ModelsarXiv:2412.15265Yingshui Tan, Boren Zheng, Baihui Zheng, et al.2024 · 4 citations
7. USB: A COMPREHENSIVE AND UNIFIED SAFETY EVALUATION BENCHMARK FOR MULTIMODAL LARGE LANGUAGE MODELSAnnual Meeting of the Association for Computational Linguistics (ACL)Baolin Zheng, Guanlin Chen, Qingyang Teng, et al.2026 · 1 citation
8. PretrainRL: Alleviating Factuality Hallucination of Large Language Models at the BeginningFindings of the Association for Computational LinguisticsLangming Liu, Kangtao Lv, Haibin Chen, et al.2026
9. Read As Human: Compressing Context via Parallelizable Close Reading and SkimmingAnnual Meeting of the Association for Computational Linguistics (ACL)Jiwei Tang, Shilei Liu, Zhicheng Zhang, et al.2026
10. SELECting over Tokens: Curating Pre-training Data at Scale via Token ClassificationAnnual Meeting of the Association for Computational Linguistics (ACL)Xin Tong, Weidong Zhang, Jiaang Li, et al.2026

🤝 Co-authors here

12 of 33 co-authors with a page, the most papers together first.

• Bo Zheng ×6
• Jiaheng Liu ×4
• Haibin Chen ×3
• Langming Liu ×3
• Shilei Liu ×3
• Yancheng He ×3
• Yujin Yuan ×3
• Huiyun Jing ×2
• Jincheng Wei ×2
• Kangtao Lv ×2
• Weidong Zhang ×2
• Weixun Wang ×2

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Annual Meeting of the Association for Computational Linguistics (ACL) ×6: ACL 2026 ×3, ACL 2025, ACL 2024
• Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2026
• Conference on Neural Information Processing Systems (NeurIPS)

🔗 Cited by

Papers of our library cite their works 312 times (of the 149,439 papers whose bibliographies we read); 99 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/wenbo-su/