Direct Preference Optimization (DPO)

Reinforcement learning is emerging as an avenue for building large language models with advanced reasoning capabilities.

Microsoft updated its smallest model family with a single, surprisingly high-performance model.

Jailbreak prompts can prod a large language model (LLM) to overstep built-in boundaries, leading it to do things like respond to queries it was trained to refuse to answer. Researchers devised a way to further boost the probability that LLMs will respond in ways that respect such limits.

Large language models sometimes generate false statements. New work makes them more likely to produce factual output.

Reinforcement learning from human feedback (RLHF) is widely used to fine-tune pretrained models to deliver outputs that align with human preferences. New work aligns pretrained models without the cumbersome step of reinforcement learning.