Related papers: IDEAL: Influence-Driven Selective Annotations Empo…

As large language models are increasingly trained and fine-tuned, practitioners need methods to identify which training data drive specific behaviors, particularly unintended ones. Training Data Attribution (TDA) methods address this by…

In-context learning (ICL) allows transformer-based language models that are pre-trained on general text to quickly learn a specific task with a few "task demonstrations" without updating their parameters, significantly boosting their…

With a handful of demonstration examples, large-scale language models show strong capability to perform various tasks by in-context learning from these examples, without any fine-tuning. We demonstrate that in-context learning performance…

One emergent ability of large language models (LLMs) is that query-specific examples can be included in the prompt at inference time. In this work, we use active learning for adaptive prompt design and call it Active In-context Prompt…

The remarkable success of contrastive-learning-based multimodal models has been greatly driven by training on ever-larger datasets with expensive compute consumption. Sample selection as an alternative efficient paradigm plays an important…

Recognizing customer intent accurately with language models based on customer-agent conversational data is essential in today's digital customer service marketplace, but it is often hindered by the lack of sufficient labeled data. In this…

In-context learning (ICL) derives its power from enabling Large Language Models to adapt to new tasks via prompt-based reasoning alone, entirely bypassing the need for parameter updates. Existing theories primarily study ICL in single-task…

Albeit the implicit feedback based recommendation problem - when only the user history is available but there are no ratings - is the most typical setting in real-world applications, it is much less researched than the explicit feedback…

Offline model-based optimization aims to find a design that maximizes a property of interest using only an offline dataset, with applications in robot, protein, and molecule design, among others. A prevalent approach is gradient ascent,…

There is an especially strong need in modern large-scale data analysis to prioritize samples for manual inspection. For example, the inspection could target important mislabeled samples or key vulnerabilities exploitable by an adversarial…

Sketch recognition allows natural and efficient interaction in pen-based interfaces. A key obstacle to building accurate sketch recognizers has been the difficulty of creating large amounts of annotated training data. Several authors have…

In-Context Learning (ICL) has gained prominence due to its ability to perform tasks without requiring extensive training data and its robustness to noisy labels. A typical ICL workflow involves selecting localized examples relevant to a…

Generalizing Multimodal Large Language Models (MLLMs) to novel video domains is essential for real-world deployment but remains challenging due to the scarcity of labeled data. While In-Context Learning (ICL) offers a training-free…

Labeling data for classification requires significant human effort. To reduce labeling cost, instead of labeling every instance, a group of instances (bag) is labeled by a single bag label. Computer algorithms are then used to infer the…

Supervised finetuning (SFT) on instruction datasets has played a crucial role in achieving the remarkable zero-shot generalization capabilities observed in modern large language models (LLMs). However, the annotation efforts required to…

As an effective approach to quantify how training samples influence test sample, data attribution is crucial for understanding data and model and further enhance the transparency of machine learning models. We find that prevailing data…

Recently, prompt learning has become a new paradigm to utilize pre-trained language models (PLMs) and achieves promising results in downstream tasks with a negligible increase of parameters. The current usage of discrete and continuous…

Large-scale models trained on extensive datasets, have emerged as the preferred approach due to their high generalizability across various tasks. In-context learning (ICL), a popular strategy in natural language processing, uses such models…

By allowing models to predict without task-specific training, in-context learning (ICL) with pretrained LLMs has enormous potential in NLP. However, a number of problems persist in ICL. In particular, its performance is sensitive to the…

Distillation with unlabeled examples is a popular and powerful method for training deep neural networks in settings where the amount of labeled data is limited: A large ''teacher'' neural network is trained on the labeled data available,…