Xiqiao Xiong

dblp:424/5598 · DBLP profile ↗
← Back
1ranked-venue papers
1as first author
1since 2021 · last 2026
—ORCID · none

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 1 · 1 first-author · 1 since 2021

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Network and information security
1 paper
Security and privacy of machine learning · 100%
Artificial intelligence
1 paper
Question answering and dialogue systems · 100%

Topics — the 3 heaviest of 3, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Natural language and speech › Question answering and dialogue systems
multi-turn dialogue
1.012026
TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards · ACL (1) 2026
Security and privacy of machine learning
adversarial attack
1.012026
TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards · ACL (1) 2026
Security and privacy of machine learning › adversarial attack
jailbreak attack
1.012026
TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards · ACL (1) 2026

Methods — techniques the papers use, named apart from their topics

trajectory-level optimization · 2.0reinforcement learning · 2.0process reward · 2.0
YearPublicationVenuePosition
2026 TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards
abstract
Xiqiao Xiong, Ouxiang Li, Zhuo Liu, Moxin Li, Wentao Shi, Fengbin Zhu, Qifan Wang, Fuli Feng. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.
Xiqiao Xiong, Ouxiang Li, Moxin Li, Wentao Shi 0002, Fengbin Zhu, Qifan Wang 0001, Fuli Feng
ACL (1)1