Related papers: Subliminal Learning: Language models transmit beha…

Supervised training of abstractive language generation models results in learning conditional probabilities over language sequences based on the supervised training signal. When the training signal contains a variety of writing styles, such…

When language models (LMs) are trained to forget (or "unlearn'') a skill, how precisely does their behavior change? We study the behavior of transformer LMs in which tasks have been forgotten via fine-tuning on randomized labels. Such LMs…

Large language models (LLMs) often struggle to learn from corrective feedback within a conversational context. They are rarely proactive in soliciting this feedback, even when faced with ambiguity, which can make their dialogues feel…

A typical assumption in state-of-the-art self-localization models is that an annotated training dataset is available in the target workspace. However, this does not always hold when a robot travels in a general open-world. This study…

Collaborative machine learning and related techniques such as federated learning allow multiple participants, each with his own training dataset, to build a joint model by training locally and periodically exchanging model updates. We…

Transfer learning is widely used to adapt large pretrained models to new tasks with only a small amount of new data. However, a challenge persists -- the features from the original task often do not fully cover what is needed for unseen…

Knowledge distillation (KD) is an effective method for model compression and transferring knowledge between models. However, its effect on model's robustness against spurious correlations that degrade performance on out-of-distribution data…

Learning dynamics, which describes how the learning of specific training examples influences the model's predictions on other examples, gives us a powerful tool for understanding the behavior of deep learning systems. We study the learning…

Recent research has shown that language models have a tendency to memorize rare or unique sequences in the training corpora which can thus leak sensitive attributes of user data. We employ a teacher-student framework and propose a novel…

The iterated learning model simulates the transmission of language from generation to generation in order to explore how the constraints imposed by language transmission facilitate the emergence of language structure. Despite each modelled…

Grammatical features across human languages show intriguing correlations often attributed to learning biases in humans. However, empirical evidence has been limited to experiments with highly simplified artificial languages, and whether…

Attaining prototypical features to represent class distributions is well established in representation learning. However, learning prototypes online from streaming data proves a challenging endeavor as they rapidly become outdated, caused…

Why do models often attend to salient words, and how does this evolve throughout training? We approximate model training as a two stage process: early on in training when the attention weights are uniform, the model learns to translate…

Most of today's distributed machine learning systems assume {\em reliable networks}: whenever two machines exchange information (e.g., gradients or models), the network should guarantee the delivery of the message. At the same time, recent…

Recently, the concept of teaching has been introduced into machine learning, in which a teacher model is used to guide the training of a student model (which will be used in real tasks) through data selection, loss function design, etc.…

Model distillation -- using outputs from a large teacher model to teach a small student model -- is a practical means of creating efficient models for a particular task. We ask: Can we identify a students' teacher based on its outputs? Such…

Large Language Models (LLMs) can sometimes degrade into repetitive loops, persistently generating identical word sequences. Because repetition is rare in natural human language, its frequent occurrence across diverse tasks and contexts in…

Multilingual models have been widely used for cross-lingual transfer to low-resource languages. However, the performance on these languages is hindered by their underrepresentation in the pretraining data. To alleviate this problem, we…

The widespread adoption of synthetic data raises new questions about how models generating the data can influence other large language models (LLMs) via distilled data. To start, our work exhaustively characterizes the impact of passive…

Recent work on large language models relies on the intuition that most natural language processing tasks can be described via natural language instructions. Language models trained on these instructions show strong zero-shot performance on…