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 23 reinforcement learning 9 language models 6 benchmarking 4 natural language processing 4 AI agents 3 vision-language models 3 world models 3

30 JUL 2026 · Paper

Would You Walk to the Car Wash? Revealing the Salience Bias of Large Language Models in Commonsense Reasoning

This paper shows that large language models struggle with commonsense reasoning due to a bias towards explicit conditions, which can be misled by irrelevant information, and that this issue can be improved by adjusting the task framing or using lightweight prompting. Practitioners caring about the reliability of language models in real-world applications might want to consider this when using them for tasks that require critical thinking.

large language models commonsense reasoning salience bias task framing inference-time prompting

30 JUL 2026 · Paper

Can Large Language Models Execute Parent Orders?

This paper explores using large language models to improve execution costs in algorithmic trading by breaking down a large order into smaller ones, and finds that these models can outperform human traders and other approaches in certain situations.

large language models algorithmic trading parent-order execution financial decision-making