Researchers developed WaLLM, a general-purpose LLM chatbot, and deployed it on WhatsApp to study user behavior. The study found that users primarily used WaLLM for health and well-being advice, and that engagement features had varying adoption rates and associated user patterns.

Researchers propose a method called 'grafting' to apply pre-training interventions to AI models without requiring a full post-training run, reducing iteration time and improving model stability.

Researchers developed practical training recipes for looped language models, reducing training budgets and improving performance on various benchmarks. They also introduced a method to convert pretrained dense models into looped ones, achieving gains on multiple tasks.

New benchmark (PriceBench) helps measure LLM preferences in hotel booking, revealing inconsistent and exploitable behavior in less capable LLMs, and significant price/quality trade-offs across providers.

MoMHa is a system that optimizes large language model (LLM) harnesses by considering multiple objectives: accuracy, safety, and token cost. It uses an agentic proposer to search for optimal harness design and outperforms alternative approaches in various domains.

This paper studies the use of intuitive prompting to improve the fidelity of language models (LLMs) simulating social media reactions. The authors found that instructing LLMs to respond intuitively and immediately resulted in higher fidelity and better performance on unfamiliar content, suggesting potential applications for general-purpose simulated users.