--- title: "Songyang Gao — author profile and papers — Elamur Research" description: "Songyang Gao, Daqing Oilfield General Hospital: 5 papers on Elamur Research (2023–2025), h-index 8 — affiliations, topics, co-authors and…" canonical: "https://research.elamur.ai/free/en/authors/songyang-gao/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/songyang-gao/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Songyang Gao # Songyang Gao Songyang Gao has 5 papers in our library, in 2023–2025, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/); often with [Shihan Dou](https://md.research.elamur.ai/free/en/authors/shihan-dou/), [Limao Xiong](https://md.research.elamur.ai/free/en/authors/limao-xiong/), [Wei Shen](https://md.research.elamur.ai/free/en/authors/wei-shen/). 5 papers in our library · 2023–2025 [OpenAlex](https://openalex.org/A5050969774) · [ORCID](https://orcid.org/0000-0001-9878-1420) · [**h-index 8**](https://openalex.org/authors/A5050969774) · [45 works](https://openalex.org/works?filter=author.id:A5050969774) · [200 citations](https://openalex.org/works?filter=author.id:A5050969774&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 5 works in our library](https://md.research.elamur.ai/free/en/authors/songyang-gao/#papers) · [🔗 Cited 295 times in our library](https://md.research.elamur.ai/free/en/authors/songyang-gao/cited-by/) · [2 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #5102](https://md.research.elamur.ai/free/en/paper-stars/page/52/#star-5102) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Songyang+Gao) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Songyang+Gao) · [dblp](https://dblp.org/search?q=Songyang+Gao) · [ACL Anthology](https://aclanthology.org/search/?q=Songyang+Gao) ## Affiliations [🔬**Shanghai Artificial Intelligence Laboratory** Shanghai · China 2024–2026 · 6 papers*current*](https://md.research.elamur.ai/free/en/labs/shanghai-artificial-intelligence-laboratory/) · [🏥**Daqing Oilfield General Hospital** Daqing · China 2026 · 1 paper*current*](https://ror.org/01ey7we33) · [🔬**Research Institute of Petroleum Exploration and Development** Beijing · China 2026 · 1 paper*current*](https://ror.org/02awe6g05) · [🎓**The Hong Kong University of Science and Technology (Guangzhou)** Guangzhou · China 2026 · 1 paper*current*](https://md.research.elamur.ai/free/en/universities/the-hong-kong-university-of-science-and-technology-guangzhou/) · [🎓**Fudan University** Shanghai · China 2022–2025 · 20 papers](https://md.research.elamur.ai/free/en/universities/fudan-university/) · [🎓**Dalian University of Technology** Dalian · China 2022–2023 · 2 papers](https://md.research.elamur.ai/free/en/universities/dalian-university-of-technology/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 9 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 9 The field of science this work belongs to (OpenAlex fields).[Computer Science · 5 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Artificial Intelligence · 5 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Arts and Humanities · 4 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Language and Linguistics · 4 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · [Engineering · 1 work](https://md.research.elamur.ai/free/en/shelves/engineering/) · [Computer Vision and Pattern Recognition · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · [Control and Systems Engineering · 1 work](https://md.research.elamur.ai/free/en/shelves/engineering/control-and-systems-engineering/) · [Applied Mathematics · 1 work](https://md.research.elamur.ai/free/en/shelves/mathematics/applied-mathematics/) · [Mathematics · 1 work](https://md.research.elamur.ai/free/en/shelves/mathematics/) 🧭 Topics 2 Research subjects and languages the work is about.[Language models & pretraining · 4 works](https://md.research.elamur.ai/free/en/topics/language-models/) · [Reasoning · 1 work](https://md.research.elamur.ai/free/en/topics/reasoning/) ## Works by year ### 2020s [**2025** 3 papers](https://md.research.elamur.ai/free/en/authors/songyang-gao/year/2025/) · [**2024** 1 paper](https://md.research.elamur.ai/free/en/authors/songyang-gao/year/2024/) · [**2023** 1 paper](https://md.research.elamur.ai/free/en/authors/songyang-gao/year/2023/) ## Papers The most cited first (OpenAlex and our library). 1. **[Secrets of RLHF in Large Language Models Part I: PPO](https://md.research.elamur.ai/free/en/papers/zheng-2023-secrets-rlhf-large-language-models/)** *(2023 · 135 citations)* RLHF is the main way to make LLMs helpful, honest and harmless. Its PPO stage, though, is unstable, sensitive to hyperparameters and costly to debug, and few open implementations existed. This report from the Fudan NLP Group and ByteDance breaks the RLHF pipeline into its stages: SFT, reward model training, and PPO… 2. **[LoRAMoE: Alleviating World Knowledge Forgetting in Large Language Models via MoE-Style Plugin](https://md.research.elamur.ai/free/en/papers/dou-2024-loramoe-alleviating-world-knowledge-forgetting/)** *(2024 · 93 citations)* The paper examines a trade-off in supervised fine-tuning (SFT) of LLMs. Adding much more instruction data keeps improving downstream tasks, but it also erodes the factual knowledge the model gained in pre-training. The authors build a 5-million-sample instruction set covering seven task categories and fine-tune… 3. **[ToolEyes: Fine-Grained Evaluation for Tool Learning Capabilities of Large Language Models in Real-world Scenarios](https://md.research.elamur.ai/free/en/papers/ye-2025-tooleyes-fine-grained-evaluation-tool/)** *(2025 · 35 citations)* Most benchmarks for tool use by large language models only check whether a model picks the expected API. That approach works only when correct answers can be fixed in advance, and it reveals little about the skills behind successful tool use. ToolEyes addresses both gaps. The authors define seven realistic scenarios… 4. **[CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward](https://md.research.elamur.ai/free/en/papers/liu-2025-compassverifier-unified-robust-verifier-llms/)** *(2025 · 16 citations)* Checking whether an LLM's free-form output matches a reference answer is central to benchmarking and to reward signals in RL. 5. **[Intern-S1-MO: Long-horizon Reasoning Agent for Olympiad?Level Mathematical Problem Solving](https://md.research.elamur.ai/free/en/papers/gu-2025-intern-s1-mo-long/)** *(2025 · 1 citation)* Even strong Large Reasoning Models (LRMs) struggle on IMO-level problems. The exploration these problems need outgrows a single 64K–128K context window, and earlier workarounds were mostly prompt-only pipelines on proprietary models. The authors present Intern-S1-MO, an agent framework that splits problem solving… ## All works 7 works of theirs in our library, the most cited first; 5 with a page here, the others link their original until we summarise them. 1. [**Secrets of RLHF in Large Language Models Part I: PPO arXiv:2307.04964**Rui Zheng, Shihan Dou, Songyang Gao, et al.*2023 · 135 citations*](https://md.research.elamur.ai/free/en/papers/zheng-2023-secrets-rlhf-large-language-models/) 2. **[LoRAMoE: Alleviating World Knowledge Forgetting in Large Language Models via MoE-Style Plugin](https://md.research.elamur.ai/free/en/papers/dou-2024-loramoe-alleviating-world-knowledge-forgetting/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Shihan Dou, Enyu Zhou, Yan Liu, et al.*2024 · 93 citations* 3. **[Secrets of RLHF in Large Language Models Part II: Reward Modeling ↗](https://arxiv.org/abs/2401.06080) arXiv:2401.06080 · no summary yet**Binghai Wang et al.*2024 · 72 citations* 4. **[ToolEyes: Fine-Grained Evaluation for Tool Learning Capabilities of Large Language Models in Real-world Scenarios](https://md.research.elamur.ai/free/en/papers/ye-2025-tooleyes-fine-grained-evaluation-tool/) [International Conference on Computational Linguistics (COLING)](https://md.research.elamur.ai/free/en/venues/coling/)**Junjie Ye, Guanyu Li, SongYang Gao, et al.*2025 · 35 citations* 5. **[AgentGym: Evolving Large Language Model-based Agents across Diverse Environments ↗](https://arxiv.org/abs/2406.04151) arXiv:2406.04151 · no summary yet**Zhiheng Xi et al.*2024 · 33 citations* 6. **[CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward](https://md.research.elamur.ai/free/en/papers/liu-2025-compassverifier-unified-robust-verifier-llms/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Shudong Liu, Hongwei Liu, Junnan Liu, et al.*2025 · 16 citations* 7. [**Intern-S1-MO: Long-horizon Reasoning Agent for Olympiad?Level Mathematical Problem Solving arXiv:2512.10739**Yuzhe Gu, Songyang Gao, Zijian Wu, et al.*2025 · 1 citation*](https://md.research.elamur.ai/free/en/papers/gu-2025-intern-s1-mo-long/) ## Co-authors here 12 of 34 co-authors with a page, the most papers together first. - [Shihan Dou](https://md.research.elamur.ai/free/en/authors/shihan-dou/) ×3 - [Limao Xiong](https://md.research.elamur.ai/free/en/authors/limao-xiong/) ×2 - [Wei Shen](https://md.research.elamur.ai/free/en/authors/wei-shen/) ×2 - [Wenwei Zhang](https://md.research.elamur.ai/free/en/authors/wenwei-zhang/) ×2 - [Xiaoran Fan](https://md.research.elamur.ai/free/en/authors/xiaoran-fan/) ×2 - [Yan Liu](https://md.research.elamur.ai/free/en/authors/yan-liu/) ×2 - [Yuhao Zhou](https://md.research.elamur.ai/free/en/authors/yuhao-zhou/) ×2 - [Yuzhe Gu](https://md.research.elamur.ai/free/en/authors/yuzhe-gu/) ×2 - [Binghai Wang](https://md.research.elamur.ai/free/en/authors/binghai-wang/) - [Caishuang Huang](https://md.research.elamur.ai/free/en/authors/caishuang-huang/) - [Chengqi Lyu](https://md.research.elamur.ai/free/en/authors/chengqi-lyu/) - [Derek F. Wong](https://md.research.elamur.ai/free/en/authors/derek-f-wong/) ## 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)](https://md.research.elamur.ai/free/en/venues/acl/): [ACL 2024](https://md.research.elamur.ai/free/en/venues/acl/2024/) - [International Conference on Computational Linguistics (COLING)](https://md.research.elamur.ai/free/en/venues/coling/): [COLING 2025](https://md.research.elamur.ai/free/en/venues/coling/2025/) - [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/): [EMNLP 2025](https://md.research.elamur.ai/free/en/venues/emnlp/2025/) ## Cited by Papers of our library cite their works 295 times (of the 149,439 papers whose bibliographies we read); [59 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/songyang-gao/cited-by/). Updated 31 October 2026