Related papers: WikiIns: A High-Quality Dataset for Controlled Tex…
Prefix-tuning is a powerful lightweight technique for adapting a large pre-trained language model to a downstream application. However, it uses the same dataset-level tuned prompt for all examples in the dataset. We extend this idea and…
Instructional texts for specific target groups should ideally take into account the prior knowledge and needs of the readers in order to guide them efficiently to their desired goals. However, targeting specific groups also carries the risk…
Knowledge editing aims to correct outdated or inaccurate knowledge in neural networks. In this paper, we explore knowledge editing using easily accessible documents instead of manually labeled factual triples employed in earlier research.…
Modern machine learning relies on datasets to develop and validate research ideas. Given the growth of publicly available data, finding the right dataset to use is increasingly difficult. Any research question imposes explicit and implicit…
Wikipedia is written in the wikitext markup language. When serving content, the MediaWiki software that powers Wikipedia parses wikitext to HTML, thereby inserting additional content by expanding macros (templates and mod-ules). Hence,…
A crucial issue of current text generation models is that they often uncontrollably generate factually inconsistent text with respective of their inputs. Limited by the lack of annotated data, existing works in evaluating factual…
Controlled video generation has seen drastic improvements in recent years. However, editing actions and dynamic events, or inserting contents that should affect the behaviors of other objects in real-world videos, remains a major challenge.…
Automatic medical text simplification can assist providers with patient-friendly communication and make medical texts more accessible, thereby improving health literacy. But curating a quality corpus for this task requires the supervision…
Visual data from the Web power image classifiers, which often underpin many web services, such as recommendation and content moderation. However, the raw Web data often contain spurious correlations and social biases, and neural networks…
Instruction-based image editing through natural language has emerged as a powerful paradigm for intuitive visual manipulation. While recent models achieve impressive results on single edits, they suffer from severe quality degradation under…
Recent advancements in generative models have enabled high-fidelity text-to-image generation. However, open-source image-editing models still lag behind their proprietary counterparts, primarily due to limited high-quality data and…
Instruction-based image editing holds immense potential for a variety of applications, as it enables users to perform any editing operation using a natural language instruction. However, current models in this domain often struggle with…
News article revision histories provide clues to narrative and factual evolution in news articles. To facilitate analysis of this evolution, we present the first publicly available dataset of news revision histories, NewsEdits. Our dataset…
Large Language Models (LLMs) usually suffer from knowledge cutoff or fallacy issues, which means they are unaware of unseen events or generate text with incorrect facts owing to outdated/noisy data. To this end, many knowledge editing…
As the modern tool of choice for question answering, large language models (LLMs) are expected to deliver answers with up-to-date knowledge. To achieve such ideal question-answering systems, locating and then editing outdated knowledge in…
A significant amount of research is focused on developing and evaluating large language models for a variety of code synthesis tasks. These include synthesizing code from natural language, synthesizing tests from code, and synthesizing…
The knowledge of scripts, common chains of events in stereotypical scenarios, is a valuable asset for task-oriented natural language understanding systems. We propose the Goal-Oriented Script Construction task, where a model produces a…
Knowledge Editing is a technique that updates large language models (LLMs) with new information to maintain their world knowledge. This approach avoids the need to rebuild the model from scratch, thereby addressing the high costs associated…
The effective communication of procedural knowledge remains a significant challenge in natural language processing (NLP), as purely textual instructions often fail to convey complex physical actions and spatial relationships. We address…
It is standard procedure these days to solve Information Extraction task by fine-tuning large pre-trained language models. This is not the case for generation task, which relies on a variety of techniques for controlled language generation.…