9 papers
Budgeted Subset Refinement for Execution-Aware LLM Research Ideation
Micah Zhang
Large language models (LLMs) can generate research ideas that appear novel to expert reviewers, but recent work also shows that such ideas often lack diversity, are difficult for L…
Memory Inception: Latent-Space KV Cache Manipulation for Steering LLMs
Andy Zeyi Liu, Michael Zhang, Ilana Greenberg +3
Steering large language models (LLMs) is usually done by either instruction prompting or activation steering. Prompting often gives strong control, but caches guidance tokens at ev…
HALO: Hybrid Adaptive Latent Reasoning for Language Models
Micah Zhang
We study how to improve a frozen pretrained language model with a small amount of adaptive extra computation. A simple approach is to add additional refinement steps on top of the…
OpenAI GPT-5 System Card
Aaditya Singh, Adam Fry, Adam Perelman +483
This is the system card published alongside the OpenAI GPT-5 launch, August 2025. GPT-5 is a unified system with a smart and fast model that answers most questions, a deeper reason…
PAVE: Premise-Aware Validation and Editing for Retrieval-Augmented LLMs
Tianyi Huang, Caden Yang, Emily Yin +2
Retrieval-augmented language models can retrieve relevant evidence yet still commit to answers before explicitly checking whether the retrieved context supports the conclusion. We…
BEADs: Bias Evaluation Across Domains
Shaina Raza, Mizanur Rahman, Michael R. Zhang
Recent advances in large language models (LLMs) have substantially improved natural language processing (NLP) applications. However, these models often inherit and amplify biases p…