Elamur Research⌕
☰
home / authors / Fei Sun

Fei Sun

Fei Sun has 6 papers in our library, in 2024–2026, most of them on Language models & pretraining, Reasoning; often with Xueqi Cheng, Hexiang Tan, Huawei Shen.

6 papers in our library · 2024–2026

OpenAlex · ORCID · Wikidata · h-index 32 · 123 works · 10,587 citations OpenAlex, 2026-10-14

📄 6 works in our library · 🔗 Cited 297 times in our library · 5 more in our library without a page yet · ⭐ Paper Stars ranking: #7321

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

🏛️Chinese Academy of SciencesBeijing · China2015–2026 · 20 paperscurrent🔬Institute of Computing TechnologyBeijing · China2015–2026 · 18 paperscurrent🎓Nanjing University of Science and TechnologyNanjing · China2018–2026 · 7 paperscurrent🎓University of Chinese Academy of SciencesBeijing · China2026 · 2 paperscurrent🏢State Development & Investment CorporationBeijing · China2026 · 1 papercurrent🏢Alibaba GroupHangzhou · China2018–2022 · 42 papers🎓Hefei UniversityHefei · China2020–2025 · 5 papers🏢Alibaba DAMO AcademyHangzhou · China2020–2022 · 5 papers🏢MetaMenlo Park · United States2019 · 5 papers🏢Anhui Jiyuan SoftwareHefei2023–2025 · 4 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 14 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 6The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 6 worksComputer Science · 6 worksArtificial Intelligence · 6 worksLanguage and Linguistics · 6 worksComputer Vision and Pattern Recognition · 2 worksInformation Systems · 1 work

🧭 Topics 2Research subjects and languages the work is about.Language models & pretraining · 4 worksReasoning · 1 work

 Works by year

2020s

20262 papers20253 papers20241 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts? (2024 · 37 citations)
    Hybrid question-answering systems give an LLM two kinds of context: passages it wrote itself and passages retrieved from an external corpus such as Wikipedia.
  2. Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs (2025 · 12 citations)
    LLM error detectors often treat agreement across sampled answers as a sign of correctness. This paper identifies a blind spot in that assumption: self-consistent errors , where a model gives the same wrong answer, up to semantic equivalence, in its greedy output and in all stochastic samples. The authors define these…
  3. The Mirage of Model Editing: Revisiting Evaluation in the Wild (2025 · 9 citations)
    Published model-editing results often look nearly perfect. This paper asks whether those results hold once the evaluation reflects how an edited LLM would actually be used. The authors build QAEdit, a benchmark drawn from Natural Questions, TriviaQA and SimpleQA. GPT-4 adds the subjects and paraphrased prompts that…
  4. The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis (2026 · 6 citations)
    Reasoning LLMs often keep generating "thinking" tokens after they already have enough information to answer, which wastes compute and is known as overthinking.
  5. InductionBench: LLMs Fail in the Simplest Complexity Class (2025 · 5 citations)
    Most reasoning benchmarks for LLMs test deduction: the rules are given (axioms, programming syntax) and must be applied.
  6. BaseCal: Unsupervised Confidence Calibration via Base Model Signals (2026 · 1 citation)
    Post-trained LLMs (PoLLMs), such as instruction-tuned or RLHF-aligned models, tend to be overconfident: they assign high probability even to wrong answers, which limits the usefulness of confidence for detecting hallucinations.

All works

11 works of theirs in our library, the most cited first; 6 with a page here, the others link their original until we summarise them.

  1. FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search ↗arXiv:1812.03443 · no summary yetBichen Wu et al.2018 · 1,405 citations
  2. Deep Session Interest Network for Click-Through Rate Prediction ↗International Joint Conference on Artificial Intelligence · no summary yetYufei Feng et al.2019 · 298 citations
  3. ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation ↗arXiv:1812.08934 · no summary yetXiaoliang Dai et al.2018 · 297 citations
  4. Improving Multi-turn Dialogue Modelling with Utterance ReWriter ↗Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · no summary yetHui Su et al.2019 · 157 citations
  5. Component-Enhanced Chinese Character Embeddings ↗Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · no summary yetYanran Li et al.2015 · 110 citations
  6. Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts?Annual Meeting of the Association for Computational Linguistics (ACL)Hexiang Tan, Fei Sun, Wanli Yang, et al.2024 · 37 citations
  7. Too Consistent to Detect: A Study of Self-Consistent Errors in LLMsConference on Empirical Methods in Natural Language Processing (EMNLP)Hexiang Tan, Fei Sun, Sha Liu, et al.2025 · 12 citations
  8. The Mirage of Model Editing: Revisiting Evaluation in the WildAnnual Meeting of the Association for Computational Linguistics (ACL)Wanli Yang, Fei Sun, Jiajun Tan, et al.2025 · 9 citations
  9. The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics AnalysisAnnual Meeting of the Association for Computational Linguistics (ACL)Zihao Wei, Liang Pang, Jiahao Liu, et al.2026 · 6 citations
  10. InductionBench: LLMs Fail in the Simplest Complexity ClassAnnual Meeting of the Association for Computational Linguistics (ACL)Wenyue Hua, Tyler Wong, Fei Sun, et al.2025 · 5 citations
  11. BaseCal: Unsupervised Confidence Calibration via Base Model SignalsAnnual Meeting of the Association for Computational Linguistics (ACL)Hexiang Tan, Wanli Yang, Junwei Zhang, et al.2026 · 1 citation

 Co-authors here

12 of 21 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 297 times (of the 149,439 papers whose bibliographies we read); 24 citing papers with a page here →.

Updated

↑ back to top

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