Shipei Du

Ms. Shipei Du


Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 November 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
LYLei Yang
Lei Yang
SDShipei Du
Shipei Du
YCYungui Chen
Yungui Chen
YCYanwen Chen
Yanwen Chen
LJLingjie Ji
Lingjie Ji
Large language models produce fluent but factually unreliable statements, and the mainstream routes to factuality—retrieval augmentation and alignment fine-tuning—presuppose that authoritative external knowledge is obtainable. When that assumption fails, a distinct family applies: adversarial interaction, in which a model cross-examines another model’s claims, several agents debate an answer, or a skeptical prompt interrogates its own reasoning. This review surveys representative adversarial factuality mechanisms published from 2022 to 2026 and organizes them into a two-level taxonomy, partitioned by evidential basis and adversarial structure. Two findings stand out. First, the surveyed mechanisms populate the design space unevenly, no structure is uniformly superior, and a single failure mode recurs across structures: false consensus—premature convergence on a shared but incorrect answer. Second, the field’s diagnosis of false consensus is mature while its countermeasures remain almost entirely unverified, and evaluation is biased against internal-consistency methods because established benchmarks presuppose external ground truth. The review closes with concrete directions: standard evaluation protocols, a verification convention for countermeasures, conformity-aware mechanism design, cost reporting, and a game-theoretic formalization of adversarial examination.

2 July 2026
Verified
Book Chapter
Closed access
PDF file
LLLiming Lin
Liming Lin
SDShipei Du
Shipei Du
LYLei Yang
Lei Yang
YZYihui Zhong
Yihui Zhong
YJYongxin Jian
Yongxin Jian
FCFangting Chen
Fangting Chen