Di Wu
Di Wu has 4 papers in our library, in 2024–2026, most of them on Language models & pretraining, Reasoning, Information retrieval & search; often with Kai-Wei Chang, Christof Monz, Dong Yu.
OpenAlex · ORCID · h-index 25 · 235 works · 2,926 citations OpenAlex, 2026-10-14
📄 4 works in our library · 🔗 Cited 108 times in our library · 1 more in our library without a page yet · ⭐ Paper Stars ranking: #6697
Affiliations
Fields, topics and concepts
📚 Shelves 12The field of science this work belongs to (OpenAlex fields).Computer Science · 3 worksArts and Humanities · 2 worksArtificial Intelligence · 2 worksLanguage and Linguistics · 2 worksInformation Systems · 1 workComputer Vision and Pattern Recognition · 1 workDecision Sciences · 1 workGeneral Decision Sciences · 1 workPolitical Science and International Relations · 1 workPsychology · 1 workSocial Psychology · 1 workSocial Sciences · 1 work
🧭 Topics 4Research subjects and languages the work is about.Reasoning · 1 workLanguage models & pretraining · 1 workInformation retrieval & search · 1 workVision & language · 1 work
Works by year
2020s
Papers
- LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory (2024 · 95 citations)
Chat assistants increasingly store past conversations to personalize their answers, but it is unclear how well they remember across many sessions. - Please Translate Again: Two Simple Experiments on Whether Human-Like Reasoning Helps Translation (2025 · 12 citations)
The paper asks whether LLM translation actually benefits from human-style reasoning. In that approach, the model first analyses the source text (idioms, meanings and similar aspects), then drafts a translation, then refines it. The authors re-implement the four-step Step-by-step prompt of Briakou et al. (2024), a… - Label Effects: Shared Heuristic Reliance in Trust Assessment by Humans and LLM-as-a-Judge (2026 · 1 citation)
The paper asks whether LLMs used as automatic evaluators (LLM-as-a-Judge) are swayed by disclosed authorship, and whether this resembles how people judge health information. - VisRet: Visualization Improves Knowledge-Intensive Text-to-Image Retrieval (2026 · 1 citation)
Text-to-image retrieval often fails when a query demands specific visual configurations, such as an animal's posture or the camera angle.
All works
- LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive MemoryarXiv:2410.10813Di Wu, Hongwei Wang, Wenhao Yu, et al.2024 · 95 citations
- Please Translate Again: Two Simple Experiments on Whether Human-Like Reasoning Helps TranslationConference on Empirical Methods in Natural Language Processing (EMNLP)Di Wu, Seth Aycock, Christof Monz2025 · 12 citations
- Original or Translated? On the Use of Parallel Data for Translation Quality Estimation ↗arXiv:2212.10257 · no summary yetBaopu Qiu et al.2022 · 5 citations
- Label Effects: Shared Heuristic Reliance in Trust Assessment by Humans and LLM-as-a-JudgeAnnual Meeting of the Association for Computational Linguistics (ACL)Xin Sun, Di Wu, Sijing Qin, et al.2026 · 1 citation
- VisRet: Visualization Improves Knowledge-Intensive Text-to-Image RetrievalAnnual Meeting of the Association for Computational Linguistics (ACL)Di Wu, Yixin Wan, Kai-Wei Chang2026 · 1 citation
Co-authors here
- Kai-Wei Chang ×2
- Christof Monz
- Dong Yu
- Hongwei Wang
- Saku Sugawara
- Seth Aycock
- Wenhao Yu
- Xin Sun
- Yixin Wan
- Yuwei Zhang
Venues
- Annual Meeting of the Association for Computational Linguistics (ACL) ×2: ACL 2026 ×2
- Conference on Empirical Methods in Natural Language Processing (EMNLP): EMNLP 2025
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/di-wu/