Related papers: Exploring Fine-tuned Generative Models for Keyphra…

Zero-shot cross-lingual knowledge transfer enables a multilingual pretrained language model, finetuned on a task in one language, make predictions for this task in other languages. While being broadly studied for natural language…

Pre-trained Generative models such as BART, T5, etc. have gained prominence as a preferred method for text generation in various natural language processing tasks, including abstractive long-form question answering (QA) and summarization.…

In this paper, we fine-tuned three pre-trained BERT models on the task of "definition extraction" from mathematical English written in LaTeX. This is presented as a binary classification problem, where either a sentence contains a…

Retrieval-Augmented Generation (RAG) systems face significant performance gaps when applied to technical domains requiring precise information extraction from complex documents. Current evaluation methodologies relying on document-level…

This paper studies multi-task training of retrieval-augmented generation models for knowledge-intensive tasks. We propose to clean the training set by utilizing a distinct property of knowledge-intensive generation: The connection of…

Large Language Models trained on web-scale text acquire language generation abilities that can solve a wide range of tasks, particularly when task knowledge is refined into the generative prior using in-context examples. However, spurious…

The recent success of large language models for text generation poses a severe threat to academic integrity, as plagiarists can generate realistic paraphrases indistinguishable from original work. However, the role of large autoregressive…

Machine Translation models are trained to translate a variety of documents from one language into another. However, models specifically trained for a particular characteristics of the documents tend to perform better. Fine-tuning is a…

Generating keyphrases that summarize the main points of a document is a fundamental task in natural language processing. Although existing generative models are capable of predicting multiple keyphrases for an input document as well as…

Retrieval-Augmented Generation (RAG) systems have recently shown remarkable advancements by integrating retrieval mechanisms into language models, enhancing their ability to produce more accurate and contextually relevant responses.…

We propose a comprehensive study of one-stage elicitation techniques for querying a large pre-trained generative transformer (GPT-3.5-turbo) in the rhetorical role prediction task of legal cases. This task is known as requiring textual…

Practitioners deploying small open-weight large language models (LLMs) for medical question answering face a recurring design choice: invest in a domain-fine-tuned model, or keep a general-purpose model and inject domain knowledge at…

We study question answering in the domain of radio regulations, a legally sensitive and high-stakes area. We propose a telecom-specific Retrieval-Augmented Generation (RAG) pipeline and introduce, to our knowledge, the first multiple-choice…

While machine-generated texts (MGTs) offer great convenience, they also pose risks such as disinformation and phishing, highlighting the need for reliable detection. Metric-based methods, which extract statistically distinguishable features…

Retrieval-Augmented Generation (RAG) enhances LLM factuality, but multi-domain applications face challenges like lack of diverse benchmarks and poor out-of-domain generalization. The first contribution of this work is to introduce a diverse…

Recently, generative methods have been widely used in keyphrase prediction, thanks to their capability to produce both present keyphrases that appear in the source text and absent keyphrases that do not match any source text. However, the…

Keyphrase generation aims at generating important phrases (keyphrases) that best describe a given document. In scholarly domains, current approaches have largely used only the title and abstract of the articles to generate keyphrases. In…

Developing an efficient retriever to retrieve knowledge from a large-scale knowledge base (KB) is critical for task-oriented dialogue systems to effectively handle localized and specialized tasks. However, widely used generative models such…

Topics models, such as LDA, are widely used in Natural Language Processing. Making their output interpretable is an important area of research with applications to areas such as the enhancement of exploratory search interfaces and the…

Paraphrase generation, a.k.a. paraphrasing, is a common and important task in natural language processing. Emotional paraphrasing, which changes the emotion embodied in a piece of text while preserving its meaning, has many potential…