[2306.03081] Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programs

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

[2306.03081] Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programs Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Artificial Intelligence arXiv:2306.03081 (cs) [Submitted on 5 Jun 2023 ( v1 ), last revised 26 Nov 2023 (this version, v2)] Title: Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programs Authors: Alexander K. Lew , Tan Zhi-Xuan , Gabriel Grand , Vikash K. Mansinghka View a PDF of the paper titled Sequential

related reading

• Productizing Large Language Modelsblog.replit.com
• [2605.03907] Steer Like the LLM: Activation Steering that Mimics Promptingarxiv.org
• GitHub - brexhq/prompt-engineering: Tips and tricks for working with Large Language Models like OpenAI's GPT-4.github.com
• [2201.11903] Chain of Thought Prompting Elicits Reasoning in Large Language Modelsarxiv.org
• Large Language Diffusion Modelsarxiv.org
• Stream of Search (SoS): Learning to Search in Languagearxiv.org
• Large Language Model: world models or surface statistics?thegradient.pub
• Training Large Language Models to Reason in a Continuous Latent Spacearxiv.org
• [2203.02155] Training language models to follow instructions with human feedbackarxiv.org
• Steering Might Stop Working Soon — LessWronglesswrong.com
• Reasoning as Trajectoriesslhleosun.github.io
• Large Language Models Must Be Taught to Know What They Don't Knowarxiv.org