相关论文: Efficacy of Machine-Generated Instructions

As text generated by large language models proliferates, it becomes vital to understand how humans engage with such text, and whether or not they are able to detect when the text they are reading did not originate with a human writer. Prior…

As large language models (LLMs) continue to advance, instruction tuning has become critical for improving their ability to generate accurate and contextually appropriate responses. Although numerous instruction-tuning datasets have been…

Instruction-tuning is a widely adopted finetuning method that enables large language models (LLMs) to generate output that more closely resembles human responses. However, no studies have shown that instruction-tuning actually teaches LLMs…

Data augmentation is widely used in vision to introduce variation and mitigate overfitting, by enabling models to learn invariant properties. However, augmentation only indirectly captures these properties and does not explicitly constrain…

Auto-regressive large language models such as GPT-3 require enormous computational resources to use. Traditionally, structured pruning methods are employed to reduce resource usage. However, their application to and efficacy for generative…

The evaluation of machine learning models using human-labeled validation data can be expensive and time-consuming. AI-labeled synthetic data can be used to decrease the number of human annotations required for this purpose in a process…

Pre-trained vision-language models learn massive data to model unified representations of images and natural languages, which can be widely applied to downstream machine learning tasks. In addition to zero-shot inference, in order to better…

Large language models are increasingly capable of generating fluent-appearing text with relatively little task-specific supervision. But can these models accurately explain classification decisions? We consider the task of generating…

Large Language Models (LLMs) exhibit remarkable text classification capabilities, excelling in zero- and few-shot learning (ZSL and FSL) scenarios. However, since they are trained on different datasets, performance varies widely across…

This study aims to provide a comparative analysis of performance of certain models popular in machine learning and the BERT model on the Stanford Question Answering Dataset (SQuAD). The analysis shows that the BERT model, which was once…

The creation of instruction data and evaluation benchmarks for serving Large language models often involves enormous human annotation. This issue becomes particularly pronounced when rapidly developing such resources for a non-English…

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…

Large-scale, transformer-based language models such as GPT-2 are pretrained on diverse corpora scraped from the internet. Consequently, they are prone to generating non-normative text (i.e. in violation of social norms). We introduce a…

We fine-tune GPT-3 to answer long-form questions using a text-based web-browsing environment, which allows the model to search and navigate the web. By setting up the task so that it can be performed by humans, we are able to train models…

In Machine Translation (MT) evaluation, metric performance is assessed based on agreement with human judgments. In recent years, automatic metrics have demonstrated increasingly high levels of agreement with humans. To gain a clearer…

Technology-assisted review (TAR) refers to iterative active learning workflows for document review in high recall retrieval (HRR) tasks. TAR research and most commercial TAR software have applied linear models such as logistic regression to…

This study examines the feasibility and potential advantages of using large language models, in particular GPT-4o, to perform partial credit grading of large numbers of student written responses to introductory level physics problems.…

Instruction tuning is instrumental in enabling Large Language Models~(LLMs) to follow user instructions to complete various open-domain tasks. The success of instruction tuning depends on the availability of high-quality instruction data.…

Instruction tuning enables language models to more effectively generalize and better follow user intent. However, obtaining instruction data is costly and challenging. Prior work employs methods such as expensive human annotation,…

Despite the increase in popularity of language models for code generation, it is still unknown how training on bimodal coding forums affects a model's code generation performance and reliability. We, therefore, collect a dataset of over…