Large language models (LLMs) have shown promise in medical question answering, with
Med-PaLM being the first to exceed a 'passing'score in United States Medical Licensing …

Sparse autoencoders (SAEs) are an unsupervised method for learning a sparse
decomposition of a neural network's latent representations into seemingly interpretable …

Since the emergence of ChatGPT, research on large language models (LLMs) has actively
progressed across various fields. LLMs, pre-trained on vast text datasets, have exhibited …

Verifiers or reward models are often used to enhance the reasoning performance of large
language models (LLMs). A common approach is the Best-of-N method, where N candidate …

Large Language Models (LLMs) have demonstrated remarkable capabilities across various
fields, from natural language understanding to text generation. Compared to non-generative …

Training on high-quality synthetic data from strong language models (LMs) is a common
strategy to improve the reasoning performance of LMs. In this work, we revisit whether this …

MicroRNAs (miRNAs) are small non-coding RNAs (18–26 nucleotides) that regulate gene
expression by interacting with target mRNAs, affecting various physiological and …

Large language models (LLMs) such as GPT-4 sometimes appear to be creative, solving
novel tasks often with a few demonstrations in the prompt. These tasks require the models to …

In this report, we introduce a collection of methods to enhance reward modeling for LLMs,
focusing specifically on data-centric techniques. We propose effective data selection and …

Language models (LMs) derive their capabilities from extensive training on diverse data,
including potentially copyrighted material. These models can memorize and generate …