Related papers: As Language Models Scale, Low-order Linear Depth D…
What happens when a language model thinks without words? Standard reasoning LLMs verbalize intermediate steps as chain-of-thought; latent reasoning transformers (LRTs) instead perform deliberation entirely in continuous hidden space. We…
The rapid growth in natural language processing (NLP) research has led to numerous new models, outpacing our understanding of how they compare to established ones. One major reason for this difficulty is saturating benchmarks, which may not…
Recent research has demonstrated that transformers, particularly linear attention models, implicitly execute gradient-descent-like algorithms on data provided in-context during their forward inference step. However, their capability in…
Neural models trained for next utterance generation in dialogue task learn to mimic the n-gram sequences in the training set with training objectives like negative log-likelihood (NLL) or cross-entropy. Such commonly used training…
Surrogate models play a crucial role in retrospectively interpreting complex and powerful black box machine learning models via model distillation. This paper focuses on using model-based trees as surrogate models which partition the…
We analyze the operation of transformer language adapters, which are small modules trained on top of a frozen language model to adapt its predictions to new target languages. We show that adapted predictions mostly evolve in the source…
Large Language Models (LLMs) have been shown to organize the representations of input sequences into straighter neural trajectories in their deep layers, which has been hypothesized to facilitate next-token prediction via linear…
We conduct a preliminary inquiry into the ability of generative transformer models to deductively reason from premises provided. We observe notable differences in the performance of models coming from different training setups and find that…
We demonstrate a situation in which Large Language Models, trained to be helpful, harmless, and honest, can display misaligned behavior and strategically deceive their users about this behavior without being instructed to do so. Concretely,…
Large language models have achieved remarkable success in general language understanding tasks. However, as a family of generative methods with the objective of next token prediction, the semantic evolution with the depth of these models…
Transformer architectures are the backbone of the modern AI revolution. However, they are based on simply stacking the same blocks in dozens of layers and processing information sequentially from one block to another. In this paper, we…
Large language models (LLMs) show remarkable capabilities across a variety of tasks. Despite the models only seeing text in training, several recent studies suggest that LLM representations implicitly capture aspects of the underlying…
Large pre-trained language models are often trained on large volumes of internet data, some of which may contain toxic or abusive language. Consequently, language models encode toxic information, which makes the real-world usage of these…
Psychological research consistently finds that human ratings of words across diverse semantic scales can be reduced to a low-dimensional form with relatively little information loss. We find that the semantic associations encoded in the…
Large language models (LLMs) achieve state-of-the-art results across many natural language tasks, but their internal mechanisms remain difficult to interpret. In this work, we extract, process, and visualize latent state geometries in…
Transformer-based Large Language Models (LLMs) have become a fixture in modern machine learning. Correspondingly, significant resources are allocated towards research that aims to further advance this technology, typically resulting in…
Larger language models become simultaneously better and worse at handling contextual information -- better at ignoring false claims, worse at ignoring irrelevant tokens. We formalize this apparent paradox through the first scaling laws for…
Large language models (LLMs) have demonstrated remarkable capabilities in handling complex dialogue tasks without requiring use case-specific fine-tuning. However, analyzing live dialogues in real-time necessitates low-latency processing…
Large-scale neural language models exhibit remarkable performance in in-context learning: the ability to learn and reason about the input context on the fly. This work studies in-context counterfactual reasoning in language models, that is,…
Modern AI agents such as large language models are trained on diverse tasks -- translation, code generation, mathematical reasoning, and text prediction -- simultaneously. A key question is how to quantify the influence of each individual…