Elamur Research⌕
☰
home / authors / Zifeng Cheng

Zifeng Cheng

Zifeng Cheng has 2 papers in our library, in 2025, most of them on Language models & pretraining; often with Qing Gu, Yafeng Yin, Yuchen Fu.

2 papers in our library · 2025

OpenAlex · ORCID · h-index 9 · 47 works · 289 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 25 times in our library · 2 more in our library without a page yet · ⭐ Paper Stars ranking: #9247

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓Nanjing UniversityNanjing · China2019–2026 · 30 paperscurrent🎓Guangxi Medical UniversityNanning · China2024–2026 · 7 paperscurrent

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 more institutions on single bylines are not listed.

 Fields, topics and concepts

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

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 2 worksComputer Science · 2 worksArtificial Intelligence · 2 worksComputer Vision and Pattern Recognition · 2 worksLanguage and Linguistics · 2 works

🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 2 works

 Works by year

2020s

20252 papers

 Papers

The most cited first (OpenAlex and our library).

  1. Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs (2025 · 10 citations)
    Decoder-only LLMs rely on causal attention. When sentence embeddings are extracted from them without fine-tuning, tokens near the start of the input cannot see later tokens. Prompt-based methods such as PromptEOL read the embedding from the final prompt token, but that token still inherits the skewed representations…
  2. Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering (2025 · 8 citations)
    Large language models can produce sentence embeddings without any training data or fine-tuning: a prompt wraps the sentence, and the hidden state of the final token serves as the vector.

All works

4 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

  1. A Unified Target-Oriented Sequence-to-Sequence Model for Emotion-Cause Pair Extraction ↗IEEE/ACM Transactions on Audio Speech and Language Processing · no summary yetZifeng Cheng et al.2021 · 70 citations
  2. Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMsAnnual Meeting of the Association for Computational Linguistics (ACL)Yuchen Fu, Zifeng Cheng, Zhiwei Jiang, et al.2025 · 10 citations
  3. Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time SteeringAnnual Meeting of the Association for Computational Linguistics (ACL)Zifeng Cheng, Zhonghui Wang, Yuchen Fu, et al.2025 · 8 citations
  4. AEA: Adaptive Expert Allocation Improves Sentence Embeddings from Mixture-of-Experts LLM ↗Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetShufan Yang et al.2026

 Co-authors here

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

Venues

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

 Cited by

Papers of our library cite their works 25 times (of the 149,439 papers whose bibliographies we read); 5 citing papers with a page here →.

Updated

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