Elamur Research⌕
☰
home / authors / Juntao Dai

Juntao Dai

Juntao Dai has 4 papers in our library, in 2023–2026, most of them on Language models & pretraining, Reasoning, Bias, fairness & safety; often with Jiaming Ji, Yaodong Yang, Sirui Han.

4 papers in our library · 2023–2026

OpenAlex · h-index 0 · 5 works · 0 citations OpenAlex, 2026-10-14

📄 4 works in our library · 🔗 Cited 298 times in our library · 1 more in our library without a page yet · ⭐ Paper Stars ranking: #4525

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓Peking UniversityBeijing · China2026 · 3 paperscurrent🔬Beijing Academy of Artificial IntelligenceBeijing · China2026 · 1 papercurrent

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

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 9The field of science this work belongs to (OpenAlex fields).Computer Science · 4 worksArtificial Intelligence · 3 worksSocial Sciences · 2 worksArts and Humanities · 2 worksLanguage and Linguistics · 2 worksSafety Research · 1 workComputer Vision and Pattern Recognition · 2 worksSociology and Political Science · 1 workHardware and Architecture · 1 work

🧭 Topics 5Research subjects and languages the work is about.Bias, fairness & safety · 2 worksLanguage models & pretraining · 2 worksVision & language · 2 worksReasoning · 2 worksEvaluation & benchmarks · 1 work

 Works by year

2020s

20263 papers20231 paper

 Papers

The most cited first (OpenAlex and our library).

  1. BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset (2023 · 362 citations)
    Aligning LLMs for safety depends on large amounts of human feedback. Existing preference data usually merge helpfulness and harmlessness into a single judgement. BeaverTails, from the PKU-Beaver group at Peking University (NeurIPS 2023 Datasets and Benchmarks track), addresses this with a question-answering dataset…
  2. Perception, Understanding and Reasoning: A Multimodal Benchmark for Video Fake News Detection (2026 · 3 citations)
    Most benchmarks for video fake news detection (VFND) score only the final real/fake label. They cannot show whether a multimodal large language model (MLLM) actually saw the right evidence, understood the story, or reasoned soundly. The authors address this with POVFNDB, a process-oriented benchmark. It is built on…
  3. SafeMT: Multi-turn Safety for Multimodal Language Models (2026 · 3 citations)
    SafeMT targets a gap in the safety evaluation of multimodal large language models (MLLMs). Existing benchmarks mostly test single image-plus-prompt inputs, but real users talk to these models over many turns, and harmful intent can be spread across a conversation. The authors combined red-team queries from earlier…
  4. SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning (2026)
    When LLM agents use the Model Context Protocol (MCP), they can acquire new tools automatically. This widens their action space and encourages power-seeking: the agent moves toward privileged states, such as admin access or a disabled firewall, where one error or hallucination can become catastrophic. Current…

All works

5 works of theirs in our library, the most cited first; 4 with a page here, the others link their original until we summarise them.

  1. BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference DatasetConference on Neural Information Processing Systems (NeurIPS)Jiaming Ji, Mickel Liu, Juntao Dai, et al.2023 · 362 citations
  2. Perception, Understanding and Reasoning: A Multimodal Benchmark for Video Fake News DetectionAnnual Meeting of the Association for Computational Linguistics (ACL)Cui Yakun, Peng Qi, Fushuo Huo, et al.2026 · 3 citations
  3. SafeMT: Multi-turn Safety for Multimodal Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Han Zhu, Juntao Dai, Jiaming Ji, et al.2026 · 3 citations
  4. SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead ReasoningAnnual Meeting of the Association for Computational Linguistics (ACL)Lichao Wang, ZhaoXing Ren, Tianzhuo Yang, et al.2026
  5. A Game-Theoretic Negotiation Framework for Cross-Cultural Consensus ↗Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetGuoxi Zhang et al.2026

 Co-authors here

12 of 19 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

 Cited by

Papers of our library cite their works 298 times (of the 149,439 papers whose bibliographies we read); 84 citing papers with a page here →.

Updated

↑ back to top

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