Haitian Sun
Haitian Sun has 2 papers in our library, in 2023–2026, most of them on Language models & pretraining, Vision & language; often with Alan Ritter, Bhuwan Dhingra, Hexiang Hu.
OpenAlex · ORCID · h-index 13 · 57 works · 1,260 citations OpenAlex, 2026-10-14
📄 2 works in our library · 🔗 Cited 448 times in our library · 9 more in our library without a page yet · ⭐ Paper Stars ranking: #7723
Affiliations
Fields, topics and concepts
📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 2 worksComputer Science · 2 worksArtificial Intelligence · 2 worksLanguage and Linguistics · 2 worksComputer Vision and Pattern Recognition · 1 workInformation Systems · 1 work
🧭 Topics 2Research subjects and languages the work is about.Language models & pretraining · 2 worksVision & language · 1 work
Works by year
2020s
Papers
- Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions? (2023 · 111 citations)
The paper asks whether current pre-trained vision-language models can handle questions about an image that need specific factual knowledge not visible in the picture, such as when a pictured church was built. - Over-Searching in Search-Augmented Large Language Models (2026)
Search-augmented LLMs can call a search tool even when doing so offers no benefit, such as when the answer is already within the model's knowledge or when no answer exists for the question.
All works
- Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text ↗Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · no summary yetHaitian Sun et al.2018 · 623 citations
- PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text ↗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 yetHaitian Sun, Tania Bedrax-Weiss, William Cohen2019 · 479 citations
- Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?Conference on Empirical Methods in Natural Language Processing (EMNLP)Yang Chen, Hexiang Hu, Yi Luan, et al.2023 · 111 citations
- LEGO: Latent Execution-Guided Reasoning for Multi-Hop Question Answering on Knowledge Graphs ↗International Conference on Machine Learning · no summary yetHongyu Ren et al.2021 · 49 citations
- ConditionalQA: A Complex Reading Comprehension Dataset with Conditional Answers ↗Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetHaitian Sun, William Cohen, Ruslan Salakhutdinov2022 · 34 citations
- Reasoning Over Virtual Knowledge Bases With Open Predicate Relations ↗arXiv (Cornell University) · no summary yetHaitian Sun et al.2021 · 27 citations
- End-to-End Multihop Retrieval for Compositional Question Answering over Long Documents ↗arXiv (Cornell University) · no summary yetHaitian Sun, William W. Cohen, Ruslan Salakhutdinov2021 · 20 citations
- Answering Ambiguous Questions with a Database of Questions, Answers, and Revisions ↗arXiv (Cornell University) · no summary yetHaitian Sun, William W. Cohen, Ruslan Salakhutdinov2023 · 6 citations
- Reasoning over Logically Interacted Conditions for Question Answering ↗arXiv (Cornell University) · no summary yetHaitian Sun, William W. Cohen, Ruslan Salakhutdinov2022 · 6 citations
- Automatic Question-Answer Generation for Long-Tail Knowledge ↗arXiv (Cornell University) · no summary yetRohan S. Kumar et al.2024 · 4 citations
- Over-Searching in Search-Augmented Large Language ModelsConference of the European Chapter of the Association for Computational Linguistics (EACL)Roy Xie, Deepak Gopinath, David Qiu, et al.2026
Co-authors here
Venues
- Conference on Empirical Methods in Natural Language Processing (EMNLP) ×2: EMNLP 2023
- Conference of the European Chapter of the Association for Computational Linguistics (EACL): EACL 2026
- International Conference on Machine Learning
- 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 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/haitian-sun/