Firehose

Filtered to Papers, tagged “large language models” · clear filters

Browse: People · Companies · Papers · Podcasts · Hacker News · Deep dives

All People Companies Papers Podcasts Hacker News

Browse by tag

continual learning 26 reinforcement learning 11 benchmarks 7 robotics 6 benchmarking 3 foundation models 3 vision-language models 3

29 OCT 2026 · Paper

On the Origin and Evolution of Training-Inference Mismatch in LLM Reinforcement Learning

This paper investigates the problem of training-inference mismatch in reinforcement learning for large language models, where the training and inference processes can produce different results, leading to suboptimal training. A practitioner might care about this issue because it can lead to poor performance and instability in training, especially when using off-policy methods.

reinforcement learning large language models training-inference mismatch asynchronous sampling continual learning

27 OCT 2026 · Paper

Follow the Gradient: Tracing Safety Degradation Back to Training Data

This paper helps prevent large language models from becoming unsafe by identifying training data that causes them to behave badly, even if the data itself looks harmless. Practitioners can use this technique to build safer language models that are more reliable and trustworthy.

continual learning large language models gradient embedding safety degradation content filters