2308.03958

arxiv.org · 7,162 words · saved by 2 readers

N/A

February 16, 2024 S IMPLE SYNTHETIC DATA REDUCES SYCOPHANCY IN LARGE LANGUAGE MODELS Jerry Wei Da Huang Yifeng Lu Denny Zhou Quoc V. Le Google DeepMind A BSTRACT arXiv:2308.03958v2 [cs.CL] 15 Feb 2024 Sycophancy is an undesirable behavior where…

saved by

Linda
Sidhant Chaliha

related reading

[2305.18290] Direct Preference Optimization: Your Language Model is Secretly a Reward Modelarxiv.org
Modifying LLM Beliefs with Synthetic Document Finetuningalignment.anthropic.com
[2303.17548] Whose Opinions Do Language Models Reflect?arxiv.org
[2203.02155] Training language models to follow instructions with human feedbackarxiv.org
[2505.13995] ELEPHANT: Measuring and understanding social sycophancy in LLMsarxiv.org
[2605.27288] It's Not Always Sycophancy: Measuring LLM Conformity as a Function of Epistemic Uncertaintyarxiv.org
[2409.19759] Balancing Cost and Effectiveness of Synthetic Data Generation Strategies for LLMsarxiv.org
[2511.08579] Training Language Models to Explain Their Own Computationsarxiv.org
[2302.08582] Pretraining Language Models with Human Preferencesarxiv.org
[2510.27062] Consistency Training Helps Stop Sycophancy and Jailbreaksarxiv.org
[2606.04071] Covert Influence Between Language Modelsarxiv.org
2212.03827arxiv.org