FIGS: Evaluating Multi-Turn Sycophancy Without Penalizing Empathy

arXiv:2609.39863 · cs.AI, cs.CL · Submitted 2026-09-30 · Read on arXiv

cs.AI, cs.CL

Submitted: 2026-09-30

Updated: 2026-09-30

Code: https://github.com/compass-group-tue/FIGSBench

Terminology

• Sycophancy — 200× in this paper · explained in 4 episodes
• Benchmark — 40× in this paper · explained in 2 episodes
• Archetype — 33× in this paper · explained in 1 episode
• Accuracy — 14× in this paper · explained in 1 episode
• Ablation — 9× in this paper · explained in 1 episode
• Frustration — 9× in this paper · explained in 2 episodes
• Alignment — 7× in this paper · explained in 1 episode
• Core — 7× in this paper · explained in 2 episodes
• Grounding — 5× in this paper · explained in 3 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Verification — 3× in this paper · explained in 2 episodes
• Abstraction — 2× in this paper · explained in 1 episode
• Adam — 2× in this paper · explained in 2 episodes
• Factual Integrity and Grounded Support — 2× in this paper
• Benchmarking — 1× in this paper · explained in 3 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• KV cache — 1× in this paper · explained in 3 episodes
• LLM judge — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Multimodal Inputs — 1× in this paper · explained in 2 episodes
• Number of Flips — 1× in this paper
• Scaffolding — 1× in this paper · explained in 3 episodes

Sources

• Sycophantic Agreement Transfers with Neutral Data via Contrastive Preference Optimization
• DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
• DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
• The Llama 3 Herd of Models
• Kimi K3: Open Frontier Intelligence
• GPT-4o System Card
• Measuring LLM Sycophancy under Sustained Multi-Turn Pressure
• Simple synthetic data reduces sycophancy in large language models

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection