Lin Li
Lin Li has 5 papers in our library, in 2021–2026, most of them on Language models & pretraining, Coreference resolution, Dialogue systems; often with Bin Wang, Bo-Hsiang Tseng, Bo Shen.
OpenAlex · h-index 0 · 8 works · 0 citations OpenAlex, 2026-10-14
📄 5 works in our library · 🔗 Cited 52 times in our library · ⭐ Paper Stars ranking: #7016
Affiliations
Fields, topics and concepts
📚 Shelves 9The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 5 worksComputer Science · 5 worksArtificial Intelligence · 5 worksLanguage and Linguistics · 5 worksInformation Systems · 2 worksComputer Science Applications · 1 workComputer Vision and Pattern Recognition · 1 workPsychology · 1 workSocial Psychology · 1 work
🧭 Topics 5Research subjects and languages the work is about.Language models & pretraining · 3 worksCode & programming languages · 1 workCoreference resolution · 1 workDialogue systems · 1 workSemantic parsing & meaning representation · 1 work
Works by year
2020s
Papers
- PanGu-Coder: Program Synthesis with Function-Level Language Modeling (2022 · 49 citations)
The paper addresses text-to-code generation: producing a Python function body that passes unit tests, given an English problem description and a function signature. - CREAD: Combined Resolution of Ellipses and Anaphora in Dialogues (2021 · 24 citations)
Users of dialogue assistants often refer back to earlier entities with pronouns or short descriptions (anaphora), or leave information out entirely (ellipsis). - Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognition (2025 · 13 citations)
Reasoning-focused LLMs such as DeepSeek-R1 are expensive to deploy because they are very large and generate long chains of thought, sometimes tens of thousands of tokens per problem. - ICT-NLP at SemEval-2026 Task 1: Humor Generation via RAG-based Augmentation and Multi-LLM Internal-External Voting (2026 · 1 citation)
This system paper describes the ICT-NLP entry submitted to SemEval-2026 Task 1 (Humor Generation), competing in Subtask A's Chinese track. - Concept rather than Document: Context Compression via AMR-based Conceptual Entropy (2026)
RAG systems often pass LLMs long retrieved documents full of material unrelated to the question, which can hurt reasoning and slow inference.
Co-authors here
- Bin Wang
- Bo-Hsiang Tseng
- Bo Shen
- Dong Li
- Fei Mi
- Fenia Christopoulou
- Guandong Xu
- Guchun Zhang
- Hanting Chen
- Hao Yu
- Haoyu Wang
- Hong Yu
Venues
- Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2026
- Conference of the North American Chapter of the Association for Computational Linguistics (NAACL): NAACL 2021
- International Workshop on Semantic Evaluation (SemEval): SemEval 2026
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/lin-li/