Zhijing Jin
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
NLP×2ML×1Crypto×1
Frequent co-authors
Research Timeline
2026
One Word at a Time: Incremental Completion Decomposition Breaks LLM Safety
The paper introduces Incremental Completion Decomposition (ICD), a novel jailbreak strategy that successfully bypasses LLM safety mechanisms by eliciting malicious content through a sequence of single-word continuations.
STRIDE: Training Data Attribution via Sparse Recovery from Subset Perturbations
This paper proposes a new framework called STRIDE for training data attribution in Large Language Models.
Highlighted terms show continued research focus across papers
Papers
cs.LGcs.CLRecentJun 3, 2026
STRIDE: Training Data Attribution via Sparse Recovery from Subset Perturbations
Rishit Dagli, Abir Harrasse, Luke Zhang, Florent Draye +3 more
This paper proposes a new framework called STRIDE for training data attribution in Large Language Models.
View →
cs.CLcs.CRRecentApr 1, 2026