🧑‍🔬 Songlin Hu

🏛️ Affiliations

🏛️Chinese Academy of SciencesBeijing · China2002–2026 · 219 paperscurrent🔬Institute of Information EngineeringBeijing · China2015–2026 · 182 paperscurrent🎓University of Chinese Academy of SciencesBeijing · China2009–2026 · 133 paperscurrent🔬Institute of Computing TechnologyBeijing · China2002–2015 · 28 papersEmployment 2002–2015🎓Hubei Normal UniversityHuangshi · China2006–2016 · 7 papers🎓Nanjing University of Posts and TelecommunicationsNanjing · China2018–2024 · 5 papers🔬State Key Laboratory of Software EngineeringHubei2012–2013 · 3 papers🎓Wuhan UniversityWuhan · China2012–2013 · 3 papers🎓Tianjin UniversityTianjin · China2022–2025 · 2 papers🎓Chongqing UniversityChongqing · China2023–2024 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 10 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.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. Mem2ActBench: A Benchmark for Evaluating Long-Term Memory Utilization in Task-Oriented Autonomous Agents (2026 · 1 citation)
   Most memory benchmarks for LLM agents check whether a system can recall a stored fact when asked directly.
2. FABLE: Fine-grained Fact Anchoring for Unstructured Model Editing (2026)
   Current unstructured model editing methods, such as UnKE and AnyEdit, can make an LLM reproduce an edited passage in full.
3. FAIRGAMER: Evaluating Social Biases in LLM-Based Video Game NPCs (2026)
   LLMs increasingly drive non-player characters (NPCs) in video games, and they can carry social stereotypes into gameplay.
4. More Thinking, Less Talking: Internalizing Deliberative Safety into LLM Parameters (2026)
   Explicit Safety-oriented Chain-of-Thought (SCoT) helps LLMs resist jailbreaks. However, the visible reasoning trace creates its own risks: it can leak harmful details before the model reaches a refusal, and it shows attackers how the model's safety logic works. The authors ask whether the protection of deliberative…
5. Resolving the Security-Auditability Dilemma with Auditable Latent Chain-of-Thought Alignment (2026)
   Reasoning-based safety alignment has LLMs write out their safety deliberation as a Chain-of-Thought (CoT), which makes supervision and auditing possible.

All works

16 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. Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering ↗Proceedings of the AAAI Conference on Artificial Intelligence · no summary yetShangwen Lv et al.2020 · 247 citations
2. Multi-hop Selector Network for Multi-turn Response Selection in Retrieval-based Chatbots ↗Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · no summary yetChunyuan Yuan et al.2019 · 162 citations
3. Towards Propagation Uncertainty: Edge-enhanced Bayesian Graph Convolutional Networks for Rumor Detection ↗Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · no summary yetLingwei Wei et al.2021 · 147 citations
4. Supervised Prototypical Contrastive Learning for Emotion Recognition in Conversation ↗Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · no summary yetXiaohui Song et al.2022 · 136 citations
5. Supervised Adversarial Contrastive Learning for Emotion Recognition in Conversations ↗Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetDou Hu et al.2023 · 110 citations
6. Label-Specific Dual Graph Neural Network for Multi-Label Text Classification ↗Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · no summary yetQianwen Ma et al.2021 · 92 citations
7. Early Detection of Fake News by Utilizing the Credibility of News, Publishers, and Users based on Weakly Supervised Learning ↗Proceedings of the 28th International Conference on Computational Linguistics · no summary yetChunyuan Yuan et al.2020 · 90 citations
8. Symmetric Metric Learning with Adaptive Margin for Recommendation ↗Proceedings of the AAAI Conference on Artificial Intelligence · no summary yetMingming Li et al.2020 · 65 citations
9. SAM-Net: Integrating Event-Level and Chain-Level Attentions to Predict What Happens Next ↗Proceedings of the AAAI Conference on Artificial Intelligence · no summary yetShangwen Lv et al.2019 · 65 citations
10. "Mask and Infill" : Applying Masked Language Model to Sentiment Transfer ↗arXiv:1908.08039 · no summary yetXing Wu et al.2019 · 49 citations
11. Mem2ActBench: A Benchmark for Evaluating Long-Term Memory Utilization in Task-Oriented Autonomous AgentsAnnual Meeting of the Association for Computational Linguistics (ACL)Yiting Shen, Kun Li, Wei Zhou, et al.2026 · 1 citation
12. Propagation Structure-Semantic Transfer Learning for Robust Fake News Detection ↗arXiv:2604.23974 · no summary yetMengyang Chen et al.2026 · 1 citation
13. FABLE: Fine-grained Fact Anchoring for Unstructured Model EditingFindings of the Association for Computational LinguisticsPeng Wang, Biyu Zhou, Xuehai Tang, et al.2026
14. FAIRGAMER: Evaluating Social Biases in LLM-Based Video Game NPCsAnnual Meeting of the Association for Computational Linguistics (ACL)Bingkang Shi, Jen-tse Huang, Luo Long, et al.2026
15. More Thinking, Less Talking: Internalizing Deliberative Safety into LLM ParametersAnnual Meeting of the Association for Computational Linguistics (ACL)Guan Wang, Xuehai Tang, Biyu Zhou, et al.2026
16. Resolving the Security-Auditability Dilemma with Auditable Latent Chain-of-Thought AlignmentAnnual Meeting of the Association for Computational Linguistics (ACL)Guan Wang, Biyu Zhou, Xuehai Tang, et al.2026

🤝 Co-authors here

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

• Biyu Zhou ×3
• Jizhong Han ×3
• Xuehai Tang ×3
• Guan Wang ×2
• Hongzhu Yi
• Jen-tse Huang
• Peng Wang
• Wei Zhou

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) ×5: ACL 2026 ×4
• Proceedings of the AAAI Conference on Artificial Intelligence ×3
• Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) ×2
• Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2026
• Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
• Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
• Proceedings of the 28th International Conference on Computational Linguistics

🔗 Cited by

Papers of our library cite their works 275 times (of the 149,439 papers whose bibliographies we read); 16 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

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