Elamur Research⌕
☰
home / authors / Zihao Li

Zihao Li

Zihao Li has 8 papers in our library, in 2024–2026, most of them on Language models & pretraining, Machine translation, Low-resource languages; often with Jörg Tiedemann, Mengnan Du, Xu Wang.

8 papers in our library · 2024–2026

OpenAlex · h-index 0 · 6 works · 0 citations OpenAlex, 2026-10-14

📄 8 works in our library · 🔗 Cited 90 times in our library · 1 more in our library without a page yet · ⭐ Paper Stars ranking: #6341

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

🎓University of Illinois Urbana-ChampaignUrbana · United States2026 · 2 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.

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 8 worksArtificial Intelligence · 8 worksArts and Humanities · 7 worksLanguage and Linguistics · 7 worksComputer Vision and Pattern Recognition · 2 worksInformation Systems · 2 works

🧭 Topics 5Research subjects and languages the work is about.Low-resource languages · 2 worksLanguage models & pretraining · 3 worksMachine translation · 2 worksReasoning · 2 worksInformation retrieval & search · 1 work

 Works by year

2020s

20264 papers20253 papers20241 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages (2024 · 95 citations)
    LLMs are trained on corpora dominated by English. For example, about 92.65% of GPT-3 tokens and 89.7% of LlaMa2 pre-training data are English. As a result, low-resource languages get weaker support, yet there are few quantitative ways to measure this gap. The authors propose Language Ranker, an intrinsic metric that…
  2. Scaling Low-Resource MT via Synthetic Data Generation with LLMs (2025 · 15 citations)
    Most of the world's languages lack enough human-translated parallel text to train strong machine translation systems.
  3. Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models (2025 · 11 citations)
    Long chain-of-thought reasoning, as in DeepSeek-R1, improves LLM performance on hard problems. Obtaining it usually requires distillation or post-training on expensive long-CoT data. The authors instead strengthen reasoning at inference time by steering residual activations, using only ordinary (vanilla) CoT.
  4. Model Unlearning via Sparse Autoencoder Subspace Guided Projections (2025 · 8 citations)
    The paper addresses selective knowledge removal from LLMs, where hazardous or private information must be erased without hurting general ability.
  5. Test-Time Scaling of Reasoning Models for Machine Translation (2026 · 5 citations)
    The paper asks whether giving reasoning models more inference-time compute (test-time scaling, TTS) improves machine translation, as it does for math and coding.
  6. RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarking (2026 · 3 citations)
    Many real questions can only be answered by combining facts spread over several tables, yet RAG systems mostly target plain text, and realistic benchmarks for multi-table retrieval are scarce.
  7. Beyond Query Memorization: Large Language Model Routing with Query Decomposition and Historical Matching (2026)
    The paper addresses LLM routing: picking, for each incoming query, a model from a pool that is good enough while keeping inference cost low.
  8. Learning to Translate by Translating: Stabilizing the Dual Loop via Semantic-Aware Self-Evolution (2026)
    Supervised LLM translation systems such as Tower and X-ALMA rely on large, expensive human-made parallel corpora.

All works

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

  1. Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource LanguagesProceedings of the AAAI Conference on Artificial IntelligenceZihao Li, Yucheng Shi, Zirui Liu, et al.2024 · 95 citations
  2. Scaling Low-Resource MT via Synthetic Data Generation with LLMsConference on Empirical Methods in Natural Language Processing (EMNLP)Ona de Gibert, Joseph Attieh, Teemu Vahtola, et al.2025 · 15 citations
  3. Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language ModelsConference on Empirical Methods in Natural Language Processing (EMNLP)Zihao Li, Xu Wang, Yuzhe Yang, et al.2025 · 11 citations
  4. Model Unlearning via Sparse Autoencoder Subspace Guided ProjectionsConference on Empirical Methods in Natural Language Processing (EMNLP)Xu Wang, Zihao Li, Benyou Wang, et al.2025 · 8 citations
  5. Test-Time Scaling of Reasoning Models for Machine TranslationConference of the European Chapter of the Association for Computational Linguistics (EACL)Zihao Li, Shaoxiong Ji, Jörg Tiedemann2026 · 5 citations
  6. RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and BenchmarkingFindings of the Association for Computational LinguisticsJiaru Zou, Dongqi Fu, Sirui Chen, et al.2026 · 3 citations
  7. Beyond Query Memorization: Large Language Model Routing with Query Decomposition and Historical MatchingAnnual Meeting of the Association for Computational Linguistics (ACL)Bo Lv, Jingbo Sun, Jianwei Lv, et al.2026
  8. Learning to Translate by Translating: Stabilizing the Dual Loop via Semantic-Aware Self-EvolutionFindings of the Association for Computational LinguisticsKui Liu, Mingming Yin, Zuoli Tang, et al.2026
  9. CAST: Achieving Stable LLM-based Text Analysis for Data Analytics ↗Findings of the Association for Computational Linguistics: ACL 2026 · no summary yetJinxiang Xie et al.2026

 Co-authors here

12 of 30 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 90 times (of the 149,439 papers whose bibliographies we read); 21 citing papers with a page here →.

Updated

↑ back to top

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