7 papers
The Circuit Basis of Metacognitive Failure in Language Models: Interference and Hallucination
Qiyao Liang, Risto Miikkulainen, Ila Fiete
Language models often answer with high confidence, as measured by output entropy, even when they are wrong. We study two situations that lead to such errors, knowledge conflict, wh…
The Blessing of Dimensionality in LLM Fine-tuning: A Variance-Curvature Perspective
Qiyao Liang, Jinyeop Song, Yizhou Liu +4
Weight-perturbation evolution strategies (ES) can fine-tune billion-parameter language models with surprisingly small populations (e.g., ), contradicting classical…
Modular connectivity in neural networks emerges from Poisson noise-motivated regularisation, and promotes robustness and compositional generalisation
Daoyuan Qian, Qiyao Liang, Ila Fiete
Circuits in the brain commonly exhibit modular architectures that factorise complex tasks, resulting in the ability to compositionally generalise and reduce catastrophic forgetting…
Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning
Xin Qiu, Yulu Gan, Conor F. Hayes +6
Fine-tuning large language models (LLMs) for downstream tasks is an essential stage of modern AI deployment. Reinforcement learning (RL) has emerged as the dominant fine-tuning par…
Compositional Generalization via Forced Rendering of Disentangled Latents
Qiyao Liang, Daoyuan Qian, Liu Ziyin +1
Composition-the ability to generate myriad variations from finite means-is believed to underlie powerful generalization. However, compositional generalization remains a key challen…
How Diffusion Models Learn to Factorize and Compose
Qiyao Liang, Ziming Liu, Mitchell Ostrow +1
Diffusion models are capable of generating photo-realistic images that combine elements which likely do not appear together in the training set, demonstrating the ability to \texti…
Do Diffusion Models Learn Semantically Meaningful and Efficient Representations?
Qiyao Liang, Ziming Liu, Ila Fiete
Diffusion models are capable of impressive feats of image generation with uncommon juxtapositions such as astronauts riding horses on the moon with properly placed shadows. These o…