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

Dandan Guo

2 indexed papers

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

Publications per year

2
26

Top categories

Crypto×2AI×1NLP×1Society×1Info Retrieval×1

Frequent co-authors

Bang An1×
Yibo Yang1×
Ebtisam Alshehri1×
Carlos Hinojosa1×
Bernard Ghanem1×
Yimeng Chen1×

Research Timeline

2026
How Much Can We Trust LLM Search Agents? Measuring Endorsement Vulnerability to Web Content Manipulation

The paper introduces SearchGEO, a framework for measuring endorsement corruption in large language model-based web-search agents.

Defending Against Harmful Supervision Hidden in Benign Samples

The paper proposes Dual-Reference SFT to mitigate harmful fine-tuning of language models by embedding harmful QA pairs in benign training samples.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIEmpiricalRecentJun 29, 2026

Defending Against Harmful Supervision Hidden in Benign Samples