相关论文: Cyclic Ablation: Testing Concept Localization agai…

Negation is a common linguistic feature that is crucial in many language understanding tasks, yet it remains a hard problem due to diversity in its expression in different types of text. Recent work has shown that state-of-the-art NLP…

Neural conditional language generation models achieve the state-of-the-art in Neural Machine Translation (NMT) but are highly dependent on the quality of parallel training dataset. When trained on low-quality datasets, these models are…

As Large Language Models (LLMs) become increasingly prevalent, their generated outputs are proliferating across the web, risking a future where machine-generated content dilutes human-authored text. Since online data is the primary resource…

We study the possibility of imitating the functionality of an image-to-image translation model by observing input-output pairs. We focus on cases where training the model from scratch is impossible, either because training data are…

We find that existing language modeling datasets contain many near-duplicate examples and long repetitive substrings. As a result, over 1% of the unprompted output of language models trained on these datasets is copied verbatim from the…

Continual learning is an emerging topic in the field of deep learning, where a model is expected to learn continuously for new upcoming tasks without forgetting previous experiences. This field has witnessed numerous advancements, but few…

While the problem of hallucinations in neural machine translation has long been recognized, so far the progress on its alleviation is very little. Indeed, recently it turned out that without artificially encouraging models to hallucinate,…

As Large Language Models (LLMs) transition into autonomous agentic roles, the risk of deception-defined behaviorally as the systematic provision of false information to satisfy external incentives-poses a significant challenge to AI safety.…

Large language models can be continually pre-trained or fine-tuned to improve performance in specific domains, languages, or skills, but this specialization often degrades other capabilities and may cause catastrophic forgetting. We…

Safety-aligned language models systematically refuse harmful requests. While activation steering can modulate refusal, ablating the raw "refusal vector" calculated from contrastive harmful and harmless prompts often causes collateral damage…

Reasoning is a core capability of large language models, yet how multi-step reasoning is learned and executed remains unclear. We study this question in a controlled cellular-automata (1dCA) framework that excludes memorisation by using…

Generative AI systems increasingly expose powerful reasoning and image refinement capabilities through user-facing chatbot interfaces. In this work, we show that the na\"ive exposure of such capabilities fundamentally undermines modern…

Imitation Learning offers a promising approach to learn directly from data without requiring explicit models, simulations, or detailed task definitions. During inference, actions are sampled from the learned distribution and executed on the…

Large Language Models (LLMs) have recently developed new advanced functionalities. Their effectiveness relies on statistical learning and generalization capabilities. However, they face limitations in internalizing the data they process and…

We study the tendency of AI systems to deceive by constructing a realistic simulation setting of a company AI assistant. The simulated company employees provide tasks for the assistant to complete, these tasks spanning writing assistance,…

Active localization is the problem of generating robot actions that allow it to maximally disambiguate its pose within a reference map. Traditional approaches to this use an information-theoretic criterion for action selection and…

Building reliable deception detectors for AI systems -- methods that could predict when an AI system is being strategically deceptive without necessarily requiring behavioural evidence -- would be valuable in mitigating risks from advanced…

Training data compositions for Large Language Models (LLMs) can significantly affect their downstream performance. However, a thorough data ablation study exploring large sets of candidate data mixtures is typically prohibitively expensive…

It takes several years for the developing brain of a baby to fully master word repetition-the task of hearing a word and repeating it aloud. Repeating a new word, such as from a new language, can be a challenging task also for adults.…

Generative models can create entirely new images, but they can also partially modify real images in ways that are undetectable to the human eye. In this paper, we address the challenge of automatically detecting such local manipulations.…