相关论文: A Unifying Scheme for Extractive Content Selection…

While large language models (LLMs) are increasingly capable of handling longer contexts, recent work has demonstrated that they exhibit the "lost in the middle" phenomenon (Liu et al., 2024) of unevenly attending to different parts of the…

Pre-trained Language Models (PLMs), such as ChatGPT, have significantly advanced the field of natural language processing. This progress has inspired a series of innovative studies that explore the adaptation of PLMs to time series…

Detecting out of policy speech (OOPS) content is important but difficult. While machine learning is a powerful tool to tackle this challenging task, it is hard to break the performance ceiling due to factors like quantity and quality…

Multi-label classification (MLC) is an ML task of predictive modeling in which a data instance can simultaneously belong to multiple classes. MLC is increasingly gaining interest in different application domains such as text mining,…

The recent development and success of Large Language Models (LLMs) necessitate an evaluation of their performance across diverse NLP tasks in different languages. Although several frameworks have been developed and made publicly available,…

In this paper, we propose CLMSM, a domain-specific, continual pre-training framework, that learns from a large set of procedural recipes. CLMSM uses a Multi-Task Learning Framework to optimize two objectives - a) Contrastive Learning using…

With the increasing capabilities of large language models (LLMs), these high-performance models have achieved state-of-the-art results on a wide range of natural language processing (NLP) tasks. However, the models' performance on…

Recent advancements in Large Language Models (LLMs) have transformed many fields including scientific discovery, content generation, biomedical text mining, and educational technology. However, the substantial requirements for training…

This position paper proposes a systematic approach towards developing a framework to help select the most effective embedding models for natural language processing (NLP) tasks, addressing the challenge posed by the proliferation of both…

Text structuralization is one of the important fields of natural language processing (NLP) consists of information extraction (IE) and structure formalization. However, current studies of text structuralization suffer from a shortage of…

In-context learning (ICL) enables large language models (LLMs) to perform new tasks by prompting them with a sequence of training examples. However, it is known that ICL is very sensitive to the choice of training examples: randomly…

Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of tasks by understanding input information and predicting corresponding outputs. However, the internal mechanisms by which LLMs comprehend input and…

Effective information gathering and knowledge codification are pivotal for developing recommendation systems that promote circular economy practices. One promising approach involves the creation of a centralized knowledge repository…

NLP benchmarks have largely focused on short texts, such as sentences and paragraphs, even though long texts comprise a considerable amount of natural language in the wild. We introduce SCROLLS, a suite of tasks that require reasoning over…

Recent research in retrieval-augmented generation (RAG) has concentrated on retrieving useful information from candidate documents. However, numerous methodologies frequently neglect the calibration capabilities of large language models…

Recommender systems serve as foundational infrastructure in modern information ecosystems, helping users navigate digital content and discover items aligned with their preferences. At their core, recommender systems address a fundamental…

Large Language Models (LLMs) have shown strong in-context learning (ICL) abilities with a few demonstrations. However, one critical challenge is how to select demonstrations to elicit the full potential of LLMs. In this paper, we propose…

Many real-world user queries (e.g. "How do to make egg fried rice?") could benefit from systems capable of generating responses with both textual steps with accompanying images, similar to a cookbook. Models designed to generate interleaved…

We propose a generic and interpretable learning framework for building robust text classification model that achieves accuracy comparable to full models under test-time budget constraints. Our approach learns a selector to identify words…

Detecting problematic content, such as hate speech, is a multifaceted and ever-changing task, influenced by social dynamics, user populations, diversity of sources, and evolving language. There has been significant efforts, both in academia…