Supervised fine-tuning (SFT) is a critical step in aligning large language models (LLMs) with human instructions and values, yet many aspects of SFT remain poorly understood.We trained a wide range of base models on a variety of datasets including code generation, mathematical reasoning, and general-domain tasks, resulting in 1,000+ SFT models under controlled conditions.We then identified the dataset properties that matter most and examined the layer-wise modifications introduced by SFT.Our findings reveal that some training-task synergies persist across all models while others vary substantially, emphasizing the importance of model-specific strategies.Moreover, we demonstrate that perplexity consistently predicts SFT effectiveness, often surpassing superficial similarity between the training data and the benchmark, and that mid-layer weight changes correlate most strongly with performance gains.We release these 1,000+ SFT models and benchmark results to accelerate further research.All resources are available at https://github.

Yuko Nakagi, Takuya Matsuyama, Naoko Koide-Majima, Hiroto Q. Yamaguchi, Rieko Kubo, Shinji Nishimoto, Yu Takagi. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

Reconstructing visual experiences from human brain activity offers a unique way to understand how the brain represents the world, and to interpret the connection between computer vision models and our visual system. While deep generative models have recently been employed for this task, reconstructing realistic images with high semantic fidelity is still a challenging problem. Here, we propose a new method based on a diffusion model (DM) to reconstruct images from human brain activity obtained via functional magnetic resonance imaging (fMRI). More specifically, we rely on a latent diffusion model (LDM) termed Stable Diffusion. This model reduces the computational cost of DMs, while preserving their high generative performance. We also characterize the inner mechanisms of the LDM by studying how its different components (such as the latent vector of image Z, conditioning inputs C, and different elements of the denoising U-Net) relate to distinct brain functions. We show that our proposed method can reconstruct high-resolution images with high fidelity in straight-forward fashion, without the need for any additional training and fine-tuning of complex deep-learning models. We also provide a quantitative interpretation of different LDM components from a neuroscientific perspective. Overall, our study proposes a promising method for reconstructing images from human brain activity, and provides a new framework for understanding DMs. Please check out our webpage at https://sites.google.com/view/stablediffusion-withbrain/.

Recent advances in neuroscience data acquisition allow for the simultaneous recording of large populations of neurons across multiple brain areas while subjects perform complex cognitive tasks. Interpreting these data requires us to index how task-relevant information is shared across brain regions, but this is often confounded by the mixing of different task parameters at the single neuron level. Here, inspired by a method developed for a single brain area, we introduce a new technique for demixing variables across multiple brain areas, called demixed shared component analysis (dSCA). dSCA decomposes population activity into a few components, such that the shared components capture the maximum amount of shared information across brain regions while also depending on relevant task parameters. This yields interpretable components that express which variables are shared between different brain regions and when this information is shared across time. To illustrate our method, we reanalyze two datasets recorded during decision-making tasks in rodents and macaques. We find that dSCA provides new insights into the shared computation between different brain areas in these datasets, relating to several different aspects of decision formation.