Search papers, labs, and topics across Lattice.
7
0
11
16
Lax bug reproduction tests can lead to plausible but incorrect patches, but a new iterative framework boosts repair success by refining both tests and fixes.
Multilingual moral reasoning can be dramatically improved by grounding decisions in culturally specific contexts and theoretical frameworks, leading to significant performance gains.
Environmental illusions can degrade lane detection accuracy by over 7%, posing serious safety risks for autonomous vehicles.
KD can significantly enhance model performance in low-data settings, but its effectiveness hinges on the quality of the teacher model.
LLM-generated stories exhibit surprising character diversity, yet they often lack the depth and complexity found in human-written narratives.
Misfired alignment in LLMs can lead to a 18.9% failure rate in reasoning about stereotypes, revealing a critical flaw in current safety-oriented training methods.
Ditch the army of task-specific models: AdNanny shows a single, reasoning-centric LLM can handle diverse offline advertising tasks with improved accuracy and reduced manual effort.
