Alignment faking in large language models presented a demonstration of Claude 3 Opus and Claude 3.5 Sonnet selectively complying with a helpfulonly training objective to prevent modification of their behavior outside of training. We expand this analysis to 25 models and find that only 5 (Claude 3 Opus, Claude 3.5 Sonnet, Llama 3 405B, Grok 3, Gemini 2.0 Flash) comply with harmful queries more when they infer they are in training than when they infer they are in deployment. First, we study the motivations of these 5 models. Results from perturbing details of the scenario suggest that only Claude 3 Opus's compliance gap is primarily and consistently motivated by trying to keep its goals. Second, we investigate why many chat models don't fake alignment. Our results suggest this is not entirely due to a lack of capabilities: many base models fake alignment some of the time, and post-training eliminates alignment-faking for some models and amplifies it for others.We investigate 5 hypotheses for how post-training may suppress alignment faking and find that variations in refusal behavior may account for a significant portion of differences in alignment faking.

Learning representations for solutions of constrained optimization problems (COPs) with unknown cost functions is challenging, as models like (Variational) Autoencoders struggle to enforce constraints when decoding structured outputs. We propose an Inverse Optimization Latent Variable Model (IO-LVM) that learns a latent space of COP cost functions from observed solutions and reconstructs feasible outputs by solving a COP with a solver in the loop. Our approach leverages estimated gradients of a Fenchel-Young loss through a non-differentiable deterministic solver to shape the latent space. Unlike standard Inverse Optimization or Inverse Reinforcement Learning methods, which typically recover a single or context-specific cost function, IO-LVM captures a distribution over cost functions, enabling the identification of diverse solution behaviors arising from different agents or conditions not available during the training process. We validate our method on real-world datasets of ship and taxi routes, as well as paths in synthetic graphs, demonstrating its ability to reconstruct paths and cycles, predict their distributions, and yield interpretable latent representations.

We present the design and implementation of a new lifetime-aware tensor offloading framework for GPU memory expansion using low-cost PCIe-based solid-state drives (SSDs). Our framework, TERAIO, is developed explicitly for large language model (LLM) training with multiple GPUs and multiple SSDs. Its design is driven by our observation that the active tensors take only a small fraction (1.7% on average) of allocated GPU memory in each LLM training iteration, the inactive tensors are usually large and will not be used for a long period of time, creating ample opportunities for offloading/prefetching tensors to/from slow SSDs without stalling the GPU training process. TERAIO accurately estimates the lifetime (active period of time in GPU memory) of each tensor with the profiling of the first few iterations in the training process. With the tensor lifetime analysis, TERAIO will generate an optimized tensor offloading/prefetching plan and integrate it into the compiled LLM program via PyTorch. TERAIO has a runtime tensor migration engine to execute the offloading/prefetching plan via GPUDirect storage, which allows direct tensor migration between GPUs and SSDs for alleviating the CPU bottleneck and maximizing the SSD bandwidth utilization. In comparison with state-of-the-art studies such as ZeRO-Offload and ZeRO-Infinity, we show that TERAIO improves the training performance of various LLMs by 1.47 on average, and achieves 80.7% of the ideal performance assuming unlimited GPU memory.

This startup's new mechanistic interpretability tool lets you debug LLMs Goodfire wants to make training AI models more like good old-fashioned software engineering. The San Francisco-based startup Goodfire just released a new tool, called Silico, that lets researchers and engineers peer inside an AI model and adjust its parameters--the settings that determine a model's behavior --during training. This could give model makers more fine-grained control over how this technology is built than was once thought possible. Goodfire claims Silico is the first off-the-shelf tool of its kind that can help developers debug all stages of the development process, from building a data set to training a model. LLMs contain a LOT of parameters. The company says its mission is to make building AI models less like alchemy and more like a science.

Federated learning (FL) is a distributed paradigm that coordinates massive local clients to collaboratively train a global model via stage-wise local training processes on the heterogeneous dataset. Previous works have implicitly studied that FL suffers from the "client-drift" problem, which is caused by the inconsistent optimum across local clients. However, till now it still lacks solid theoretical analysis to explain the impact of this local inconsistency. To alleviate the negative impact of the "client drift" and explore its substance in FL, in this paper, we first design an efficient FL algorithm FedInit, which allows employing the personalized relaxed initialization state at the beginning of each local training stage.

In this section, we show our empirical observations obtained from fine-tuning PLMs on poisoned494 datasets. Specifically, we demonstrate that the backdoor triggers are easier to learn from the lower495 layers than the features corresponding to the main task. This observation plays a pivotal role in496 designing and understanding our defense algorithm. In our experiment, we focus on the SST-2497 dataset [30] and consider the widely adopted word-level backdoor trigger and the more stealthy498 style-level trigger. For the word-level trigger, we follow the approach in prior work [25] and adopt the499 meaningless word "bb" as the trigger to minimize its impact on the original text's semantic meaning.500

This paper explores the connection between learning trajectories of Deep Neural Networks (DNNs) and their generalization capabilities when optimized using (stochastic) gradient descent algorithms. Instead of concentrating solely on the generalization error of the DNN post-training, we present a novel perspective for analyzing generalization error by investigating the contribution of each update step to the change in generalization error. This perspective enable a more direct comprehension of how the learning trajectory influences generalization error. Building upon this analysis, we propose a new generalization bound that incorporates more extensive trajectory information. Our proposed generalization bound depends on the complexity of learning trajectory and the ratio between the bias and diversity of training set. Experimental observations reveal that our method effectively captures the generalization error throughout the training process. Furthermore, our approach can also track changes in generalization error when adjustments are made to learning rates and label noise levels. These results demonstrate that learning trajectory information is a valuable indicator of a model's generalization capabilities.

Self-supervised learning (SSL) is a powerful tool in machine learning, but understanding the learned representations and their underlying mechanisms remains a challenge. This paper presents an in-depth empirical analysis of SSL-trained representations, encompassing diverse models, architectures, and hyperparameters. Our study reveals an intriguing aspect of the SSL training process: it inherently facilitates the clustering of samples with respect to semantic labels, which is surprisingly driven by the SSL objective's regularization term. This clustering process not only enhances downstream classification but also compresses the data information. Furthermore, we establish that SSL-trained representations align more closely with semantic classes rather than random classes. Remarkably, we show that learned representations align with semantic classes across various hierarchical levels, and this alignment increases during training and when moving deeper into the network. Our findings provide valuable insights into SSL's representation learning mechanisms and their impact on performance across different sets of classes.