相关论文: When Does Context Help? A Systematic Study of Targ…

Instructional alignment, the match between intended cognition and enacted activity, is central to effective instruction but hard to operationalize at scale. We examine alignment in cybersecurity simulations using multimodal traces from 23…

Deep models are used for molecular property prediction, yet they are often difficult to interpret and may rely on spurious context rather than causal structure, which reduces reliability under distribution shift and harms predictive…

We investigate the use of in-context learning and prompt engineering to estimate the contributions of training data in the outputs of instruction-tuned large language models (LLMs). We propose two novel approaches: (1) a similarity-based…

Humans effortlessly identify objects by leveraging a rich understanding of the surrounding scene, including spatial relationships, material properties, and the co-occurrence of other objects. In contrast, most computational object…

Owing to the capability of in-context learning, large language models (LLMs) have shown impressive performance across diverse mathematical reasoning benchmarks. However, we find that few-shot demonstrations can sometimes bring negative…

Selecting which instances to label is a key challenge in low-label tabular learning. For recent Tabular Foundation Models such as TabPFN, context selection directly determines predictive performance. Supervised oracle experiments show that…

Large language model fine-tuning has been identified as an efficient approach to applying the pre-trained Large language models to other domains. To guarantee data privacy for different data owners, models are often fine-tuned in federated…

The In-Context Learning (ICL) is to understand a new task via a few demonstrations (aka. prompt) and predict new inputs without tuning the models. While it has been widely studied in NLP, it is still a relatively new area of research in…

Automating the recognition of outcomes reported in clinical trials using machine learning has a huge potential of speeding up access to evidence necessary in healthcare decision-making. Prior research has however acknowledged inadequate…

Semantic segmentation is still a challenging task for parsing diverse contexts in different scenes, thus the fixed classifier might not be able to well address varying feature distributions during testing. Different from the mainstream…

Learning and predicting the performance of given software configurations are of high importance to many software engineering activities. While configurable software systems will almost certainly face diverse running environments (e.g.,…

Most reinforcement learning (RL) methods only focus on learning a single task from scratch and are not able to use prior knowledge to learn other tasks more effectively. Context-based meta RL techniques are recently proposed as a possible…

Motivated by the recent success of time-series foundation models for zero-shot forecasting, we present a methodology for $\textit{in-context fine-tuning}$ of a time-series foundation model. In particular, we design a pretrained foundation…

Biological vision systems make adaptive use of context to recognize objects in new settings with novel contexts as well as occluded or blurry objects in familiar settings. In this paper, we investigate how vision models adaptively use…

Efficient utilisation of both intra- and extra-textual context remains one of the critical gaps between machine and human translation. Existing research has primarily focused on providing individual, well-defined types of context in…

We investigate ensemble methods for prediction in an online setting. Unlike all the literature in ensembling, for the first time, we introduce a new approach using a meta learner that effectively combines the base model predictions via…

This thesis investigates two key phenomena in large language models (LLMs): in-context learning (ICL) and model collapse. We study ICL in a linear transformer with tied weights trained on linear regression tasks, and show that minimising…

Recent advancements in long-context large language models have attracted significant attention, yet their practical applications often suffer from suboptimal context utilization. This study investigates structuring training data to enhance…

Recent interest has surged in employing Large Language Models (LLMs) for machine translation (MT) via in-context learning (ICL) (Vilar et al., 2023). Most prior studies primarily focus on optimizing translation quality, with limited…

Neural sequence-to-sequence systems deliver state-of-the-art performance for automatic speech recognition. When using appropriate modeling units, e.g., byte-pair encoding, these systems are in principle open vocabulary systems. In practice,…