🧑‍🔬 Rui Li

🏛️ Affiliations

🎓Peking UniversityBeijing · China2026 · 3 paperscurrent🎓University of Science and Technology of ChinaHefei · China2026 · 3 paperscurrent🏢Winning Health Technology GroupShanghai · China2026 · 1 papercurrent

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. A Survey on In-context Learning (2023 · 978 citations)
   This survey maps the fast-growing research on in-context learning (ICL). In ICL a large language model solves a task after seeing a handful of worked examples placed in its prompt, and its weights are never updated. The authors first give a formal definition: the model scores candidate answers conditioned on a…
2. Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment (2025 · 11 citations)
   Fine-tuning a safety-aligned LLM can weaken its refusal behaviour even when the training data look harmless.
3. HAUNTATTACK: When Attack Follows Reasoning as a Shadow (2026 · 3 citations)
   Large Reasoning Models (LRMs) such as DeepSeek-R1 and o1 are strong at multi-step problem solving, but it is unclear whether this skill becomes a safety weakness when harmful intent is woven into the reasoning itself.
4. Speculative Decoding with a Speculative Vocabulary (2026 · 2 citations)
   Speculative decoding speeds up language model inference without changing outputs. In EAGLE-style drafters, which use only a single decoder layer, most drafting time goes into projecting the hidden state onto the target model's large vocabulary. Earlier remedies (FR-Spec, VocabTrim, EAGLE-3) limit the drafter to a…
5. Be Your Own Red Teamer: Safety Alignment via Self-Play and Reflective Experience Replay (2026 · 1 citation)
   LLM safety training usually depends on fixed red-teaming resources, such as static defense prompts or pre-collected jailbreak datasets.

All works

8 works of theirs in our library, the most cited first; 5 with a page here, the others link their original until we summarise them.

1. A Survey on In-context LearningarXiv:2301.00234Qingxiu Dong, Lei Li, Damai Dai, et al.2023 · 978 citations
2. Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety AlignmentConference on Empirical Methods in Natural Language Processing (EMNLP)Hao Li, Lijun Li, Zhenghao Lu, et al.2025 · 11 citations
3. HAUNTATTACK: When Attack Follows Reasoning as a ShadowFindings of the Association for Computational LinguisticsJingyuan Ma, Rui Li, Zheng Li, et al.2026 · 3 citations
4. Speculative Decoding with a Speculative VocabularyFindings of the Association for Computational LinguisticsMiles Williams, Young D. Kwon, Rui Li, et al.2026 · 2 citations
5. Be Your Own Red Teamer: Safety Alignment via Self-Play and Reflective Experience ReplayFindings of the Association for Computational LinguisticsHao Wang, Yanting Wang, Hao Li, et al.2026 · 1 citation
6. Merlin's Whisper: Enabling Efficient Reasoning in Large Language Models via Black-box Persuasive Prompting ↗Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetHeming Xia et al.2026
7. Eval-RAR: Evaluation-Driven Retrieval-Augmented Reasoning via Reinforcement Learning ↗Findings of the Association for Computational Linguistics: ACL 2026 · no summary yetHeng Yu et al.2026
8. Controllable Contamination Detection for Reliable LLM Evaluation with Statistical Guarantees ↗Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetZheng Zhang et al.2026

🤝 Co-authors here

12 of 19 co-authors with a page, the most papers together first.

• Lei Sha ×3
• Hao Li ×2
• Heming Xia ×2
• Jingyuan Ma ×2
• Baobao Chang
• Ce Zheng
• Damai Dai
• Hao Wang
• Jing Shao
• Jingjing Xu
• Lei Li
• Lijun Li

Venues

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

• Findings of the Association for Computational Linguistics ×3: Findings of the Association for Computational Linguistics 2026 ×3
• Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) ×2
• Conference on Empirical Methods in Natural Language Processing (EMNLP): EMNLP 2025
• Findings of the Association for Computational Linguistics: ACL 2026

🔗 Cited by

Papers of our library cite their works 744 times (of the 149,439 papers whose bibliographies we read); 129 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/rui-li/