Search papers, labs, and topics across Lattice.
6
0
10
3
Evolving data snapshots can boost LLM performance by over 20% in both intrinsic and extrinsic evaluations, reshaping how we approach human-centered AI alignment.
Safety in education-facing LLMs is inversely related to their teaching effectiveness, challenging assumptions about model specialization.
R-CAI can generate high-quality toxic data while improving semantic coherence, revolutionizing how we approach adversarial data synthesis for AI safety.
HiGMem revolutionizes memory retrieval for LLMs by cutting down irrelevant context while boosting precision, achieving a remarkable F1 score improvement with far fewer data points.
Low-resource language models can get a major boost in translation quality and tokenization efficiency by using reinforcement learning to directly enforce structural constraints like sequence length and linguistic well-formedness during training.
Forget hand-crafted student profiles: HACHIMI generates a million theory-aligned, quota-controlled student personas, offering a standardized synthetic population for educational LLM benchmarking and social-science simulations.
