Search:
Match:
1 results
Research#LLM🔬 ResearchAnalyzed: Jan 10, 2026 09:41

AdvJudge-Zero: Adversarial Tokens Manipulate LLM Judgments

Published:Dec 19, 2025 09:22
1 min read
ArXiv

Analysis

This research explores a vulnerability in LLMs, demonstrating the ability to manipulate their binary decisions using adversarial control tokens. The implications are significant for the reliability of LLMs in applications requiring trustworthy judgments.
Reference

The study is sourced from ArXiv.