[2303.13360] Towards the Scalable Evaluation of Cooperativeness in Language Models

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. arXiv Operational Status Get status notifications via email or slack

[2303.13360] Towards the Scalable Evaluation of Cooperativeness in Language Models Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Computation and Language arXiv:2303.13360 (cs) [Submitted on 16 Mar 2023] Title: Towards the Scalable Evaluation of Cooperativeness in Language Models Authors: Alan Chan , Maxime Riché , Jesse Clifton View a PDF of the paper titled Towards the Scalable Evaluation of Cooperativeness in Language Models, by Alan Chan and 2 other authors View PDF Abstract:

related reading

• Discovering Language Model Behaviors with Model-Written Evaluations — LessWronglesswrong.com
• 2308.03958arxiv.org
• Automated Alignment Researchers: Using large language models to scale scalable oversight \ Anthropicanthropic.com
• Seed Bank, Co-op, Stoop Swapwritefutureslab.com
• [2606.04071] Covert Influence Between Language Modelsarxiv.org
• Scaling Activation Oracles to Trillion-Parameter Modelstransluce.org
• Unsupervised Elicitation of Language Modelsarxiv.org
• Group | Sherry Tongshuang Wucs.cmu.edu
• [2212.09251] Discovering Language Model Behaviors with Model-Written Evaluationsarxiv.org
• PhD_thesis_Shirley_Wu_final.pdfcs.stanford.edu
• The bitter lesson of LLM evalsparsed.com
• Measuring progress on scalable oversightanthropic.com