🧑‍🔬 Lu Cheng

🏛️ Affiliations

🎓University of Illinois ChicagoChicago · United States2025–2026 · 12 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. Large Language Models for Data Annotation and Synthesis: A Survey (2024 · 262 citations)
   Labeling or generating training data by hand is slow, expensive and often requires domain experts. This survey examines how LLMs such as GPT-4, Gemini and LLaMA-2 can automate that work. It is a literature review, so it reports no new experiments. The authors frame the setting with two roles: an annotator model A…
2. Shakespearean Sparks: The Dance of Hallucination and Creativity in LLMs' Decoding Layers (2025 · 3 citations)
   Hallucination in LLMs is often said to be linked to creativity, but earlier work treated this link mostly in theory or through qualitative examples.
3. QuCo-RAG: Quantifying Uncertainty from the Pre-training Corpus for Dynamic Retrieval-Augmented Generation (2026 · 2 citations)
   Dynamic RAG systems decide during generation when to fetch external evidence. Most rely on model-internal signals such as token probabilities, entropy or attention, but LLMs are poorly calibrated and can be confidently wrong. QuCo-RAG replaces these signals with counts taken from the model's pre-training corpus.…
4. Robust Uncertainty Quantification for Self-Evolving Large Language Models via Continual Domain Pretraining (2026 · 2 citations)
   The paper tackles uncertainty quantification for LLMs that keep learning through continual domain pretraining (CDP), where a model is fine-tuned on one knowledge domain after another.
5. When and What to Ask: AskBench and Rubric-Guided RLVR for LLM Clarification (2026 · 2 citations)
   LLMs tend to answer right away, even when a prompt leaves out decisive details or contains confidently stated errors.

🤝 Co-authors here

8 co-authors with a page, the most papers together first.

• Bohan Jiang
• Dawei Li
• Huan Liu
• Jiale Zhao
• Jundong Li
• Song Wang
• Tongtong Wu
• Zhen Tan

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
• Conference on Empirical Methods in Natural Language Processing (EMNLP): EMNLP 2024

🔗 Cited by

Papers of our library cite their works 99 times (of the 149,439 papers whose bibliographies we read); 25 citing papers with a page here →.

Updated 31 October 2026

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