Measuring LLM Sycophancy under Sustained Multi-Turn Pressure
Large language models (LLMs) may abandon correct positions when users push back, exhibiting a failure mode known as sycophancy. Existing evaluations typically use short, pre-specified conversations and may therefore miss failures that emerge under sustained, adaptive disagreement. We introduce SPINE, a benchmark in which an LLM proxy plays a persistent but mistaken user and adaptively challenges a target model for up to 25 turns. We evaluate four production systems and three Olmo3-7b variants on 100 false-presupposition and 100 unethical-query items. Our experimental results show that collapse
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 55%Evaluating long-term memory limits in stateless LLM chatbots — feedback needed [D] →
- PossiblePossibly related (embedding) · 55%Language Models Can Control Their Own Attention [R] →
- FuzzyOverlapping authors or contributors · 62%affaan-m/ECC →
“Shared author/contributor keys: jiang”
- FuzzyOverlapping authors or contributors · 62%BerriAI/litellm →
“Shared author/contributor keys: jiang”
- LinkedLinked via arxiv author · 85%Leyuan Tang →
“Measuring LLM Sycophancy under Sustained Multi-Turn Pressure”
- LinkedLinked via arxiv author · 85%Kangda Wei →
“Measuring LLM Sycophancy under Sustained Multi-Turn Pressure”
- LinkedLinked via arxiv author · 85%Tianyu Jiang →
“Measuring LLM Sycophancy under Sustained Multi-Turn Pressure”
- LinkedLinked via arxiv author · 85%Ruihong Huang →
“Measuring LLM Sycophancy under Sustained Multi-Turn Pressure”