Related papers: Engineering Monosemanticity in Toy Models

Recent NLP studies reveal that substantial linguistic information can be attributed to single neurons, i.e., individual dimensions of the representation vectors. We hypothesize that modeling strong interactions among neurons helps to better…

The ability of machine learning models to store input information in hidden layer vector embeddings, analogous to the concept of `memory', is widely employed but not well characterized. We find that language model embeddings typically…

Recent research (arXiv:2310.11453, arXiv:2402.17764) has proposed binary and ternary transformer networks as a way to significantly reduce memory and improve inference speed in Large Language Models (LLMs) while maintaining accuracy. In…

Polysemanticity is pervasive in language models and remains a major challenge for interpretation and model behavioral control. Leveraging sparse autoencoders (SAEs), we map the polysemantic topology of two small models (Pythia-70M and…

The effectiveness of a language model is influenced by its token representations, which must encode contextual information and handle the same word form having a plurality of meanings (polysemy). Currently, none of the common language…

In this paper, we explore the learning of neural network embeddings for natural images and speech waveforms describing the content of those images. These embeddings are learned directly from the waveforms without the use of linguistic…

Neural network language models (NNLMs) have achieved ever-improving accuracy due to more sophisticated architectures and increasing amounts of training data. However, the inductive bias of these models (formed by the distributional…

Monolingual data have been demonstrated to be helpful in improving translation quality of both statistical machine translation (SMT) systems and neural machine translation (NMT) systems, especially in resource-poor or domain adaptation…

Sparse autoencoders (SAEs) decompose polysemantic neural representations, where neurons respond to multiple unrelated concepts, into monosemantic features that capture single, interpretable concepts. However, standard training objectives…

Unsupervised learning of cross-lingual word embedding offers elegant matching of words across languages, but has fundamental limitations in translating sentences. In this paper, we propose simple yet effective methods to improve…

Monotonicity reasoning is one of the important reasoning skills for any intelligent natural language inference (NLI) model in that it requires the ability to capture the interaction between lexical and syntactic structures. Since no test…

Neural language models have become powerful tools for learning complex representations of entities in natural language processing tasks. However, their interpretability remains a significant challenge, particularly in domains like…

The thesis explores the role machine learning methods play in creating intuitive computational models of neural processing. Combined with interpretability techniques, machine learning could replace human modeler and shift the focus of human…

The last decade has seen huge progress in the development of advanced machine learning models; however, those models are powerless unless human users can interpret them. Here we show how the mind's construction of concepts and meaning can…

Multilingual neural machine translation with a single model has drawn much attention due to its capability to deal with multiple languages. However, the current multilingual translation paradigm often makes the model tend to preserve the…

Large language models (LLMs) often exhibit gender bias, posing challenges for their safe deployment. Existing methods to mitigate bias lack a comprehensive understanding of its mechanisms or compromise the model's core capabilities. To…

State-of-the-art pre-trained language models have been shown to memorise facts and perform well with limited amounts of training data. To gain a better understanding of how these models learn, we study their generalisation and memorisation…

Deep learning models for semantics are generally evaluated using naturalistic corpora. Adversarial methods, in which models are evaluated on new examples with known semantic properties, have begun to reveal that good performance at these…

Polysemantic neurons -- neurons that activate for a set of unrelated features -- have been seen as a significant obstacle towards interpretability of task-optimized deep networks, with implications for AI safety. The classic origin story of…

Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing. Currently, most disentanglement methods are unsupervised…