Room to Reconsider: Reply Length Decides Whether Pushback Makes Language Models Sycophantic or Self-Correcting
cs.CL, cs.AI
Submitted: 2026-11-08
Updated: 2026-11-08
Terminology
Sources
- Dual-Stance Evaluation of Sycophancy: The Structure of Agreement and the Limits of Intervention
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Sycophantic Anchors: Localizing and Quantifying User Agreement in Reasoning Models
- Large Language Models Cannot Self-Correct Reasoning Yet
- Language Models (Mostly) Know What They Know
- Are You Sure? Challenging LLMs Leads to Performance Drops in The FlipFlop Experiment
- Steering Llama 2 via Contrastive Activation Addition
- Towards Understanding Sycophancy in Language Models
- 2 OLMo 2 Furious
- Sycophancy Is Not One Thing: Causal Separation of Sycophantic Behaviors in LLMs
- When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Models
- Simple synthetic data reduces sycophancy in large language models
- Qwen3 Technical Report
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data