Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Ruifeng Xu

Ruifeng Xu

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

NLP×2AI×1Crypto×1

Frequent co-authors

Jing Li2×
Jingjie Lin1×
Bingbing Wang1×
Zihan Wang1×
Zhengda Jin1×
Weiming Qiao1×

Research Timeline

2026
BAIT: Boundary-Guided Disclosure Escalation via Self-Conditioned Reasoning

The paper introduces BAIT, a three-step jailbreak framework that systematically forces large language models to disclose harmful information by leveraging their internal reasoning and consistency tendencies.

Connecting the Dots: Benchmarking Reflective Memory in Long-Horizon Dialogue

The paper introduces RefMem-Bench, a new benchmark for measuring reflective memory in long-horizon dialogue, and proposes REMIND, a framework that significantly improves models' ability to synthesize fragmented cues into high-level interpretations.

Highlighted terms show continued research focus across papers

Papers

cs.CLcs.AIRecentMay 31, 2026

Connecting the Dots: Benchmarking Reflective Memory in Long-Horizon Dialogue

Jingjie Lin, Bingbing Wang, Zihan Wang, Zhengda Jin +3 more

The paper introduces RefMem-Bench, a new benchmark for measuring reflective memory in long-horizon dialogue, and proposes REMIND, a framework that significantly improves models' ability to synthesize…

View →
cs.CRcs.CLRecentMay 26, 2026

BAIT: Boundary-Guided Disclosure Escalation via Self-Conditioned Reasoning

Xuan Luo, Yue Wang, Geng Tu, Jing Li +1 more

The paper introduces BAIT, a three-step jailbreak framework that systematically forces large language models to disclose harmful information by leveraging their internal reasoning and consistency tend…

View →