An evaluation framework and balanced DPO training method show that LLMs are highly gullible to sustained misinformation and that balanced preference training can improve both robustness and receptiveness.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD
An evaluation framework and balanced DPO training method show that LLMs are highly gullible to sustained misinformation and that balanced preference training can improve both robustness and receptiveness.