Related papers: TAG-INSTRUCT: Controlled Instruction Complexity En…

In-context learning enables language models (LM) to adapt to downstream data or tasks by incorporating few samples as demonstrations within the prompts. It offers strong performance without the expense of fine-tuning. However, the…

Manually annotating instruction data for large language models is difficult, costly, and hard to scale. Meanwhile, current automatic annotation methods typically rely on distilling synthetic data from proprietary LLMs, which not only limits…

Instruction tuning is crucial for enabling Large Language Models (LLMs) to solve real-world tasks. Prior work has shown the effectiveness of instruction-tuning data synthesized solely from LLMs, raising a fundamental question: Do we still…

Generating long, coherent text remains a challenge for large language models (LLMs), as they lack hierarchical planning and structured organization in discourse generation. We introduce Structural Alignment, a novel method that aligns LLMs…

While the abundance of rich and vast datasets across numerous fields has facilitated the advancement of natural language processing, sectors in need of specialized data types continue to struggle with the challenge of finding quality data.…

Do current large language models (LLMs) better solve graph reasoning and generation tasks with parameter updates? In this paper, we propose InstructGraph, a framework that empowers LLMs with the abilities of graph reasoning and generation…

Optimizing instructions for large language models (LLMs) is critical for harnessing their full potential in complex and diverse tasks. However, relying solely on white-box approaches demands extensive computational resources and offers…

Large Language Models are transforming software engineering, yet prompt management in practice remains ad hoc, hindering reliability, reuse, and integration into industrial workflows. We present Prompt-with-Me, a practical solution for…

Text-attributed graphs (TAGs) have emerged as a powerful representation for modeling complex relationships across diverse domains. With the rise of large language models (LLMs), there is growing interest in leveraging their capabilities for…

Tabular instruction tuning has emerged as a promising research direction for improving LLMs understanding of tabular data. However, the majority of existing works only consider question-answering and reasoning tasks over tabular data,…

Recently, the emergence of large language models (LLMs) has motivated integrating language descriptions into graphs, forming text-attributed graphs (TAGs) that enhance model encoding capabilities from a data-centric perspective. A review of…

Large Language Models (LLMs) have been integrated into recommendation systems to enhance user behavior comprehension. The Retrieval Augmented Generation (RAG) technique is further incorporated into these systems to retrieve more relevant…

Meta-training, which fine-tunes the language model (LM) on various downstream tasks by maximizing the likelihood of the target label given the task instruction and input instance, has improved the zero-shot task generalization performance.…

There has been substantial progress in applying machine learning techniques to classification problems in collider and jet physics. But as these techniques grow in sophistication, they are becoming more sensitive to subtle features of jets…

Large language models (LLMs) have demonstrated remarkable capabilities in natural language understanding and task generalization. However, their application to structured data analysis remains fragile due to inconsistencies in schema…

Task semantics can be expressed by a set of input-output examples or a piece of textual instruction. Conventional machine learning approaches for natural language processing (NLP) mainly rely on the availability of large-scale sets of…

The challenges faced by text classification with large tag systems in natural language processing tasks include multiple tag systems, uneven data distribution, and high noise. To address these problems, the ESimCSE unsupervised comparative…

Task oriented language understanding in dialog systems is often modeled using intents (task of a query) and slots (parameters for that task). Intent detection and slot tagging are, in turn, modeled using sentence classification and word…

Class-incremental learning (CIL) enables models to learn new classes progressively while preserving knowledge of previously learned ones. Recent advances in this field have shifted towards parameter-efficient fine-tuning techniques, with…

Sparse representation models a signal as a linear combination of a small number of dictionary atoms. As a generative model, it requires the dictionary to be highly redundant in order to ensure both a stable high sparsity level and a low…