Shengjie Bi
Shengjie Bi has 2 papers in our library, in 2026, most of them on Reasoning; often with Beibin Li, Hejia Zhang, Jingyu Zhang.
OpenAlex · h-index 0 · 9 works · 0 citations OpenAlex, 2026-10-14
📄 2 works in our library · 🔗 Cited 9 times in our library · ⭐ Paper Stars ranking: #10070
Affiliations
Fields, topics and concepts
📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 2 worksComputer Science · 2 worksArts and Humanities · 1 workLanguage and Linguistics · 1 workComputer Vision and Pattern Recognition · 1 work
🧭 Topics 1Research subjects and languages the work is about.Reasoning · 1 work
Works by year
2020s
Papers
- AdvancedIF: Rubric-Based Benchmarking and Reinforcement Learning for Advancing LLM Instruction Following (2026 · 9 citations)
LLMs still struggle with demanding instruction following (IF): prompts with many stacked constraints, instructions carried across long conversations, and directives in system prompts. - Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models (2026)
Reinforcement learning with verifiable rewards (RLVR) improves math and multimodal reasoning, but it tends to wear away skills a model already had, such as perception, OCR and robustness.
Co-authors here
- Beibin Li
- Hejia Zhang
- Jingyu Zhang
- Karishma Mandyam
- Madian Khabsa
- Shishir G Patil
- Sopan Khosla
- Xianjun Yang
- Yuanshun Yao
Venues
- Annual Meeting of the Association for Computational Linguistics (ACL): ACL 2026
- Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2026
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/shengjie-bi/