Search papers, labs, and topics across Lattice.
Meituan
2
0
5
Forget noisy, biased LLM evaluators: CDRRM distills preference insights into compact rubrics, letting a frozen judge model leapfrog fully fine-tuned baselines with just 3k training samples.
Predict how well your LLM will transfer to a new domain *before* fine-tuning, by using sparse autoencoders to spot tell-tale signs of domain shift in the model's representations.
