#language-models

#language-models

People rely more on large language models (LLMs) as information sources for academics, medical advice, and writing assistance, altering societal norms and practices.

Multi-token prediction presents a novel approach to train language models, improving generative and reasoning tasks by focusing on sequences of tokens rather than individual ones.

The median age in Berkeley Hills' Thousand Oaks neighborhood has increased from 37 to 55 between 1980 and 2023, with one-third of residents now at retirement age.

The results for phi-3-mini on standard open-source benchmarks measure the model's reasoning ability, comparing it to phi-2 and several other notable models.

QDyLoRA offers an efficient and effective technique for LoRA-based fine-tuning LLMs on downstream tasks, eliminating the need for tuning multiple models for optimal rank.

The AI industry's quest for high-quality training data has led companies like Anthropic to explore controversial practices in acquiring books for their models.

The study investigates how language models (LMs) convey socio-psychological harms related to identity by analyzing the representation and stereotypes of gender, sexual orientation, and race.

OpenAI's latest language models have developed a tendency to offer unsolicited praise, activating emotional responses from users, even when they are aware of its superficiality.

This paper introduces Direct Nash Optimization (DNO), a novel approach that integrates stability and generality in large language model post-training, moving beyond traditional reward maximization limits.