🧑‍🔬 Shuzheng Si

🏛️ Affiliations

🎓University of Illinois Urbana-ChampaignUrbana · United States2025–2026 · 2 paperscurrent🎓Peking UniversityBeijing · China2022–2025 · 7 papers🎓Tsinghua UniversityBeijing · China2025 · 5 papers

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. One-Shot Learning as Instruction Data Prospector for Large Language Models (2024 · 61 citations)
   Instruction tuning datasets keep growing, but larger collections often carry noisy examples, and choosing good subsets usually depends on costly trial-and-error.
2. MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning (2023 · 58 citations)
   Most vision-language models (VLMs) built on large language models handle prompts with a single image well.
3. ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code (2023 · 33 citations)
   ML-Bench tests whether LLMs and autonomous agents can use real machine-learning GitHub repositories as libraries.
4. Aligning Large Language Models to Follow Instructions and Hallucinate Less via Effective Data Filtering (2025 · 11 citations)
   Instruction tuning can teach LLMs to hallucinate when the training examples contain knowledge the model never acquired in pre-training.
5. UltraIF: Advancing Instruction Following from the Wild (2025 · 7 citations)
   Open-source models still follow complex, multi-constraint instructions worse than industry models, partly because leading labs do not release their instruction data.
6. GATEAU: Selecting Influential Samples for Long Context Alignment (2025 · 5 citations)
   Teaching LLMs to follow instructions over very long inputs is hard because human annotation of long instruction-following data is costly.
7. A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent Tasks (2026 · 4 citations)
   LLM-based agents on long, multi-step tasks often flail. Without an overall plan, they fall into aimless trial-and-error and produce hallucinated actions. Prior fixes either teach planning implicitly via SFT or RL on the executor, which needs lots of data or converges slowly, or supply explicit guidance that depends…
8. FaithLens: Detecting and Explaining Faithfulness Hallucination (2026 · 1 citation)
   LLMs often produce claims that contradict, distort, or go beyond the context they were given. This faithfulness hallucination is a problem for RAG and summarization. Current detectors are either expensive prompted LLMs or compact classifiers that return only a binary label, give no reasoning, and generalize unevenly…

All works

9 works of theirs in our library, the most cited first; 8 with a page here, the others link their original until we summarise them.

1. One-Shot Learning as Instruction Data Prospector for Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Yunshui Li, Binyuan Hui, Xiaobo Xia, et al.2024 · 61 citations
2. MMICL: Empowering Vision-language Model with Multi-Modal In-Context LearningarXiv:2309.07915Haozhe Zhao, Zefan Cai, Shuzheng Si, et al.2023 · 58 citations
3. ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level CodearXiv:2311.09835Xiangru Tang, Yuliang Liu, Zefan Cai, et al.2023 · 33 citations
4. Aligning Large Language Models to Follow Instructions and Hallucinate Less via Effective Data FilteringAnnual Meeting of the Association for Computational Linguistics (ACL)Shuzheng Si, Haozhe Zhao, Gang Chen, et al.2025 · 11 citations
5. UltraIF: Advancing Instruction Following from the WildConference on Empirical Methods in Natural Language Processing (EMNLP)Kaikai An, Li Sheng, Ganqu Cui, et al.2025 · 7 citations
6. GATEAU: Selecting Influential Samples for Long Context AlignmentConference on Empirical Methods in Natural Language Processing (EMNLP)Shuzheng Si, Haozhe Zhao, Gang Chen, et al.2025 · 5 citations
7. A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent TasksAnnual Meeting of the Association for Computational Linguistics (ACL)Shuzheng Si, Haozhe Zhao, Kangyang Luo, et al.2026 · 4 citations
8. FaithLens: Detecting and Explaining Faithfulness HallucinationFindings of the Association for Computational LinguisticsShuzheng Si, Qingyi Wang, Haozhe Zhao, et al.2026 · 1 citation
9. MENTOR: Efficient Autoregressive Image Generation with Balanced Multimodal Control ↗Findings of the Association for Computational Linguistics: ACL 2026 · no summary yetHaozhe Zhao et al.2026

🤝 Co-authors here

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

• Baobao Chang ×6
• Haozhe Zhao ×5
• Kaikai An ×5
• Fanchao Qi ×4
• Gang Chen ×4
• Kangyang Luo ×4
• Maosong Sun ×4
• Minjia Zhang ×2
• Yunshui Li ×2
• Yuzhuo Bai ×2
• Zefan Cai ×2
• Binyuan Hui

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) ×3: ACL 2026, ACL 2025, ACL 2024
• Conference on Empirical Methods in Natural Language Processing (EMNLP) ×2: EMNLP 2025 ×2
• Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2026
• Findings of the Association for Computational Linguistics: ACL 2026

🔗 Cited by

Papers of our library cite their works 148 times (of the 149,439 papers whose bibliographies we read); 39 citing papers with a page here →.

Updated 31 October 2026

↑ back to top

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