Unlocking memorization in large language models with dynamic soft prompting
Pretrained large language models (LLMs) have revolutionized natural language processing
(NLP) tasks such as summarization, question answering, and translation. However, LLMs …
(NLP) tasks such as summarization, question answering, and translation. However, LLMs …
Active learning for identifying disaster-related tweets: A comparison with keyword filtering and generic fine-tuning
Abstract Information from social media can provide essential information for emergency
response during natural disasters in near real-time. However, it is a difficult task to identify …
response during natural disasters in near real-time. However, it is a difficult task to identify …
Zero-shot text classification with knowledge resources under label-fully-unseen setting
Classification techniques are at the heart of many real-world applications, eg sentiment
analysis, recommender systems and automatic text annotation, to process and analyse large …
analysis, recommender systems and automatic text annotation, to process and analyse large …
The Use of Generative Search Engines for Knowledge Work and Complex Tasks
Until recently, search engines were the predominant method for people to access online
information. The recent emergence of large language models (LLMs) has given machines …
information. The recent emergence of large language models (LLMs) has given machines …
Lexicans at Chemotimelines 2024: Chemotimeline Chronicles-Leveraging Large Language Models (LLMs) for Temporal Relations Extraction in Oncological …
V Sharma, A Fernández, A Ioanovici… - Proceedings of the …, 2024 - aclanthology.org
Automatic generation of chemotherapy treatment timelines from electronic health records
(EHRs) notes not only streamlines clinical workflows but also promotes better coordination …
(EHRs) notes not only streamlines clinical workflows but also promotes better coordination …
Sparse Attention Vectors: Generative Multimodal Model Features Are Discriminative Vision-Language Classifiers
Generative Large Multimodal Models (LMMs) like LLaVA and Qwen-VL excel at a wide
variety of vision-language (VL) tasks such as image captioning or visual question …
variety of vision-language (VL) tasks such as image captioning or visual question …
Clustering-Based Joint Topic-Sentiment Modeling of Social Media Data: A Neural Networks Approach
With the vast amount of social media posts available online, topic modeling and sentiment
analysis have become central methods to better understand and analyze online behavior …
analysis have become central methods to better understand and analyze online behavior …
Evaluating Source Code Quality with Large Language Models: a comparative study
IRS Simões, E Venson - Proceedings of the XXIII Brazilian Symposium …, 2024 - dl.acm.org
Code quality is an attribute composed of various metrics, such as complexity, readability,
testability, interoperability, reusability, and the use of good or bad practices, among others …
testability, interoperability, reusability, and the use of good or bad practices, among others …
Evaluation of an llm in identifying logical fallacies: A call for rigor when adopting llms in hci research
G Lim, ST Perrault - Companion Publication of the 2024 Conference on …, 2024 - dl.acm.org
There is increasing interest in the adoption of large language models (LLMs) in HCI
research. However, LLMs may often be regarded as a panacea because of their powerful …
research. However, LLMs may often be regarded as a panacea because of their powerful …
Mapping Source Code to Software Architecture by Leveraging Large Language Models
N Johansson, M Caporuscio, T Olsson - European Conference on …, 2024 - Springer
Abstract Architecture refactoring is a big challenge and requires thorough analysis and labor-
intensive, error-prone activities to restructure functionalities from a legacy architecture to a …
intensive, error-prone activities to restructure functionalities from a legacy architecture to a …