Related papers: Fine-tuned network relies on generic representatio…

Generative large language models (LLMs) are a promising alternative to pre-trained language models for entity matching due to their high zero-shot performance and ability to generalize to unseen entities. Existing research on using LLMs for…

Pre-training has exhibited notable benefits to downstream tasks by boosting accuracy and speeding up convergence, but the exact reasons for these benefits still remain unclear. To this end, we propose to quantitatively and explicitly…

Deep pretrained language models have achieved great success in the way of pretraining first and then fine-tuning. But such a sequential transfer learning paradigm often confronts the catastrophic forgetting problem and leads to sub-optimal…

Prompt tuning has become a new paradigm for model tuning and it has demonstrated success in natural language pretraining and even vision pretraining. In this work, we explore the transfer of prompt tuning to multimodal pretraining, with a…

Pretrained language models (PLMs) have produced substantial improvements in discourse-aware neural machine translation (NMT), for example, improved coherence in spoken language translation. However, the underlying reasons for their strong…

Natural language explanations promise to offer intuitively understandable explanations of a neural network's decision process in complex vision-language tasks, as pursued in recent VL-NLE models. While current models offer impressive…

The exploration of various vision-language tasks, such as visual captioning, visual question answering, and visual commonsense reasoning, is an important area in artificial intelligence and continuously attracts the research community's…

Weak-to-strong (W2S) generalization, in which a strong model is fine-tuned on outputs of a weaker, task-specialized model, has been proposed as an approach to aligning superhuman AI systems. Existing theoretical analyses either fix the…

We present a new paradigm for fine-tuning large-scale visionlanguage pre-trained models on downstream task, dubbed Prompt Regularization (ProReg). Different from traditional fine-tuning which easily overfits to the downstream task data,…

Small language models fine-tuned for graph property estimation have demonstrated strong in-distribution performance, yet their generalization capabilities beyond training conditions remain poorly understood. In this work, we systematically…

We define general linguistic intelligence as the ability to reuse previously acquired knowledge about a language's lexicon, syntax, semantics, and pragmatic conventions to adapt to new tasks quickly. Using this definition, we analyze…

Language models (LMs) trained on vast quantities of unlabelled data have greatly advanced the field of natural language processing (NLP). In this study, we re-visit the widely accepted notion in NLP that continued pre-training LMs on…

Representation learning has been widely studied in the context of meta-learning, enabling rapid learning of new tasks through shared representations. Recent works such as MAML have explored using fine-tuning-based metrics, which measure the…

A common way to use large pre-trained language models for downstream tasks is to fine tune them using additional layers. This may not work well if downstream domain is a specialized domain whereas the large language model has been…

Reinforcement Learning (RL) has been successful in various domains like robotics, game playing, and simulation. While RL agents have shown impressive capabilities in their specific tasks, they insufficiently adapt to new tasks. In…

Transfer learning has fundamentally changed the landscape of natural language processing (NLP) research. Many existing state-of-the-art models are first pre-trained on a large text corpus and then fine-tuned on downstream tasks. However,…

Current large language models can perform reasonably well on complex tasks that require step-by-step reasoning with few-shot learning. Are these models applying reasoning skills they have learnt during pre-training and reason outside of…

Fine-tuning is the dominant paradigm for adapting pretrained large language models (LLMs) to downstream NLP tasks. In practice, fine-tuning datasets may contain various forms of noise arising from annotation errors, preprocessing artifacts,…

Pre-trained vision language models still fall short of human visual cognition. In an effort to improve visual cognition and align models with human behavior, we introduce visual stimuli and human judgments on visual cognition tasks,…

Parameter-Efficient Fine-Tuning (PEFT) is a popular class of techniques that strive to adapt large models in a scalable and resource-efficient manner. Yet, the mechanisms underlying their training performance and generalization remain…