Related papers: Towards Understanding Continual Factual Knowledge …

We introduce a lifelong imitation learning framework that enables continual policy refinement across sequential tasks under realistic memory and data constraints. Our approach departs from conventional experience replay by operating…

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…

Computer vision models suffer from a phenomenon known as catastrophic forgetting when learning novel concepts from continuously shifting training data. Typical solutions for this continual learning problem require extensive rehearsal of…

Knowledge distillation is a common paradigm for transferring capabilities from larger models to smaller ones. While traditional distillation methods leverage a probabilistic divergence over the output of the teacher and student models,…

This paper studies satisfaction of temporal properties on unknown stochastic processes that have continuous state spaces. We show how reinforcement learning (RL) can be applied for computing policies that are finite-memory and deterministic…

Pretraining language models directly on web-scale corpora is the de facto paradigm. We study an alternative where the model is initially exposed to abstract structured data to ease the subsequent acquisition of rich semantic knowledge, much…

Pre-trained Language Models (PLMs) encode various facts about the world at their pre-training phase as they are trained to predict the next or missing word in a sentence. There has a been an interest in quantifying and improving the amount…

Large language models (LLMs) exhibit remarkable capabilities in question answering and reasoning thanks to their extensive parametric memory. However, their knowledge is inherently limited by the scope of their pre-training data, while…

Large language models (LLMs) struggle with cross-lingual knowledge transfer: they hallucinate when asked in one language about facts expressed in a different language during training. This work introduces a controlled setting to study the…

Prompt tuning is a new few-shot transfer learning technique that only tunes the learnable prompt for pre-trained vision and language models such as CLIP. However, existing prompt tuning methods tend to learn spurious or entangled…

In-context learning \ -- performing tasks based on examples given in the prompt \ -- is an important capability that has emerged in large language models and has received significant attention in both theory and practice. Existing…

Large language models (LLMs) are increasingly used in applications requiring factual accuracy, yet their outputs often contain hallucinated responses. While fact-checking can mitigate these errors, existing methods typically retrieve…

Large Language Models (LLMs) exhibit significant disparities in performance across languages, primarily benefiting high-resource languages while marginalizing underrepresented ones. Continual Pretraining (CPT) has emerged as a promising…

This paper considers continual learning of large-scale pretrained neural machine translation model without accessing the previous training data or introducing model separation. We argue that the widely used regularization-based methods,…

Adapting general large language models (LLMs) to specialized domains presents great challenges due to varied data distributions. This adaptation typically requires continual pre-training on massive domain-specific corpora to facilitate…

Current parameter-efficient fine-tuning (PEFT) methods build adapters widely agnostic of the context of downstream task to learn, or the context of important knowledge to maintain. As a result, there is often a performance gap compared to…

Continual Test-Time Adaptation (CTTA) aims to adapt a source pre-trained model to continually changing target domains during inference. As a fundamental principle, an ideal CTTA method should rapidly adapt to new domains (exploration) while…

Large Language Models (LLMs) have become a mainstay for many everyday applications. However, as data evolve their knowledge quickly becomes outdated. Continual learning aims to update LLMs with new information without erasing previously…

Humans can retain old knowledge while learning new information, but Large Language Models (LLMs) often suffer from catastrophic forgetting when post-pretrained or supervised fine-tuned (SFT) on domain-specific data. Moreover, for Multimodal…

Conventional continual pretraining (CPT) for large language model (LLM) domain adaptation often suffers from catastrophic forgetting and limited domain capacity. Existing strategies adopt layer expansion, introducing additional trainable…