🧑‍🔬 Ercong Nie

🏛️ Affiliations

🎓Ludwig-Maximilians-Universität MünchenMunich · Germany2022–2026 · 55 papersEmployment 2022–2026 · PhD Candidate, Centre for Information and Language Processingcurrent🎓Munich Center for Machine LearningMunich · Germany2023–2026 · 37 paperscurrent🎓Shanghai Jiao Tong UniversityShanghai · China2026 · 7 papersEmployment since 2026 · Assistant Professor, School of Foreign Languagescurrent🏥LMU KlinikumMunich · Germany2026 · 1 papercurrent🎓Technische Universität DarmstadtDarmstadt · Germany2026 · 1 papercurrent🎓Karlsruhe Institute of TechnologyKarlsruhe · Germany2024 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

🧭 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. Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning (2026 · 49 citations)
   LLMs lose information that falls outside their context window. Systems that add an external memory bank usually depend on fixed heuristics or prompted LLMs to choose what to store and retrieve, and nothing in that choice is trained against answer correctness. Memory-R1 addresses this with reinforcement learning…
2. Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language Models (2025 · 31 citations)
   Multilingual language models often answer a factual question correctly in one language but wrongly when the same question is posed in another.
3. BMIKE-53: Investigating Cross-Lingual Knowledge Editing with In-Context Learning (2025 · 12 citations)
   Knowledge editing (KE) updates facts stored in large language models without retraining. Most gradient-free work is monolingual, and it is unclear whether an edit made in English carries over to questions asked in other languages. The authors build BMIKE-53, a benchmark for cross-lingual in-context knowledge editing…
4. Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models (2026 · 9 citations)
   Most earlier reviews of mechanistic interpretability (MI) in LLMs describe what researchers have discovered inside models.
5. PlaM: Training-Free Plateau-Guided Model Merging for Better Visual Grounding in MLLMs (2026 · 1 citation)
   Multimodal instruction fine-tuning tends to weaken the text reasoning that MLLMs inherit from their base language models.
6. Look Within or Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning (2026)
   Parameter-efficient fine-tuning (PEFT) methods such as LoRA often match full fine-tuning (FFT) on standard benchmarks. It is less clear whether they hold up on harder tasks like reasoning and instruction-following, or under adversarial inputs. The authors address this with a theoretical analysis backed by experiments.
7. SAD: A Large-Scale Strategic Argumentative Dialogue Dataset (2026)
   Most argument-generation corpora treat argumentation as a one-shot task: produce an argument for a topic or rebut a single claim.

All works

8 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. Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement LearningAnnual Meeting of the Association for Computational Linguistics (ACL)Sikuan Yan, Xiufeng Yang, Zuchao Huang, et al.2026 · 49 citations
2. Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Mingyang Wang, Heike Adel, Lukas Lange, et al.2025 · 31 citations
3. BMIKE-53: Investigating Cross-Lingual Knowledge Editing with In-Context LearningAnnual Meeting of the Association for Computational Linguistics (ACL)Ercong Nie, Bo Shao, Mingyang Wang, et al.2025 · 12 citations
4. Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language ModelsFindings of the Association for Computational LinguisticsHengyuan Zhang, Zhihao Zhang, Ercong Nie, et al.2026 · 9 citations
5. Cross-Lingual Constituency Parsing for Middle High German: A Delexicalized Approach ↗Proceedings of the Ancient Language Processing Workshop · no summary yetErcong Nie, Helmut Schmid, Hinrich Schütze2023 · 3 citations
6. PlaM: Training-Free Plateau-Guided Model Merging for Better Visual Grounding in MLLMsFindings of the Association for Computational LinguisticsZijing Wang, YongKang Liu, Mingyang Wang, et al.2026 · 1 citation
7. Look Within or Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-TuningAnnual Meeting of the Association for Computational Linguistics (ACL)YongKang Liu, Xingle Xu, Ercong Nie, et al.2026
8. SAD: A Large-Scale Strategic Argumentative Dialogue DatasetAnnual Meeting of the Association for Computational Linguistics (ACL)YongKang Liu, Jiayang Yu, Mingyang Wang, et al.2026

🤝 Co-authors here

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

• Hinrich Schuetze ×6
• Mingyang Wang ×5
• Daling Wang ×3
• Shi Feng ×3
• YongKang Liu ×3
• Zifeng Ding ×2
• Zijing Wang ×2
• Chenming Shang
• Heike Adel
• Helmut Schmid
• Hengyuan Zhang
• Jannik Strötgen

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) ×5: ACL 2026 ×3, ACL 2025 ×2
• Findings of the Association for Computational Linguistics ×2: Findings of the Association for Computational Linguistics 2026 ×2
• Proceedings of the Ancient Language Processing Workshop

🔗 Cited by

Papers of our library cite their works 93 times (of the 149,439 papers whose bibliographies we read); 28 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/ercong-nie/