相关论文: Why is prompting hard? Understanding prompts on bi…

Large Language Models (LLMs) have shown prominent performance in various downstream tasks and prompt engineering plays a pivotal role in optimizing LLMs' performance. This paper, not only as an overview of current prompt engineering…

Neural predictive models have achieved remarkable performance improvements in various natural language processing tasks. However, most neural predictive models suffer from the lack of explainability of predictions, limiting their practical…

Prompt-Tuning is an efficient method for adapting pre-trained language models to new tasks with minimal computational overhead by modifying prompt embeddings. In this work, we investigate how crucial the phenomenon of embedding collapse,…

Much of the success of modern language models depends on finding a suitable prompt to instruct the model. Until now, it has been largely unknown how variations in the linguistic expression of prompts affect these models. This study…

System prompts have emerged as a critical control surface for specifying the behavior of LLMs in chat and agent settings. Developers depend on system prompts to specify important context, output format, personalities, guardrails, content…

Crosslingual conditional generation (e.g., machine translation) has long enjoyed the benefits of scaling. Nonetheless, there are still issues that scale alone may not overcome. A source query in one language, for instance, may yield several…

Prompt-based probing has been widely used in evaluating the abilities of pretrained language models (PLMs). Unfortunately, recent studies have discovered such an evaluation may be inaccurate, inconsistent and unreliable. Furthermore, the…

Continual learning aims to refine model parameters for new tasks while retaining knowledge from previous tasks. Recently, prompt-based learning has emerged to leverage pre-trained models to be prompted to learn subsequent tasks without the…

Graph In-Context Learning, with the ability to adapt pre-trained graph models to novel and diverse downstream graphs without updating any parameters, has gained much attention in the community. The key to graph in-context learning is to…

Prompt tuning has achieved great success in transferring the knowledge from large pretrained vision-language models into downstream tasks, and has dominated the performance on visual grounding (VG). However, almost all existing prompt…

Recent advances in probabilistic modelling have led to a large number of simulation-based inference algorithms which do not require numerical evaluation of likelihoods. However, a public benchmark with appropriate performance metrics for…

The alignment of large language models (LLMs) with human values is critical as these models become increasingly integrated into various societal and decision-making processes. Traditional methods, such as reinforcement learning from human…

As powerful pre-trained vision-language models (VLMs) like CLIP gain prominence, numerous studies have attempted to combine VLMs for downstream tasks. Among these, prompt learning has been validated as an effective method for adapting to…

Forecasting a time series from multivariate predictors constitutes a challenging problem, especially using model-free approaches. Most techniques, such as nearest-neighbor prediction, quickly suffer from the curse of dimensionality and…

With the advancement of large language models (LLMs), their performance on multiple-choice question (MCQ) tasks has improved significantly. However, existing approaches face key limitations: answer choices are typically presented to LLMs…

Probing Pre-trained Language Models (PLMs) using prompts has indirectly implied that language models (LMs) can be treated as knowledge bases. To this end, this phenomena has been effective especially when these LMs are fine-tuned towards…

Human reasoning involves different strategies, each suited to specific problems. Prior work shows that large language model (LLMs) tend to favor a single reasoning strategy, potentially limiting their effectiveness in diverse reasoning…

Gene expression prediction, which predicts mRNA expression levels from DNA sequences, presents significant challenges. Previous works often focus on extending input sequence length to locate distal enhancers, which may influence target…

Consider the setting of constrained optimization, with some parameters unknown at solving time and requiring prediction from relevant features. Predict+Optimize is a recent framework for end-to-end training supervised learning models for…

It is well known that direct training of deep neural networks will generally lead to poor results. A major progress in recent years is the invention of various pretraining methods to initialize network parameters and it was shown that such…