Zobrazeno 1 - 10
of 40
pro vyhledávání: '"Su, Jinyan"'
Dense retrievers are widely used in information retrieval and have also been successfully extended to other knowledge intensive areas such as language models, e.g., Retrieval-Augmented Generation (RAG) systems. Unfortunately, they have recently been
Externí odkaz:
http://arxiv.org/abs/2406.05087
Autor:
Su, Jinyan, Dean, Sarah
In digital markets comprised of many competing services, each user chooses between multiple service providers according to their preferences, and the chosen service makes use of the user data to incrementally improve its model. The service providers'
Externí odkaz:
http://arxiv.org/abs/2406.01481
Autor:
Wang, Yuxia, Mansurov, Jonibek, Ivanov, Petar, Su, Jinyan, Shelmanov, Artem, Tsvigun, Akim, Afzal, Osama Mohammed, Mahmoud, Tarek, Puccetti, Giovanni, Arnold, Thomas, Whitehouse, Chenxi, Aji, Alham Fikri, Habash, Nizar, Gurevych, Iryna, Nakov, Preslav
Publikováno v:
Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)
We present the results and the main findings of SemEval-2024 Task 8: Multigenerator, Multidomain, and Multilingual Machine-Generated Text Detection. The task featured three subtasks. Subtask A is a binary classification task determining whether a tex
Externí odkaz:
http://arxiv.org/abs/2404.14183
Autor:
Wang, Yuxia, Mansurov, Jonibek, Ivanov, Petar, Su, Jinyan, Shelmanov, Artem, Tsvigun, Akim, Afzal, Osama Mohanned, Mahmoud, Tarek, Puccetti, Giovanni, Arnold, Thomas, Aji, Alham Fikri, Habash, Nizar, Gurevych, Iryna, Nakov, Preslav
Publikováno v:
ACL 2024 main
The advent of Large Language Models (LLMs) has brought an unprecedented surge in machine-generated text (MGT) across diverse channels. This raises legitimate concerns about its potential misuse and societal implications. The need to identify and diff
Externí odkaz:
http://arxiv.org/abs/2402.11175
Prompted weak supervision (PromptedWS) applies pre-trained large language models (LLMs) as the basis for labeling functions (LFs) in a weak supervision framework to obtain large labeled datasets. We further extend the use of LLMs in the loop to addre
Externí odkaz:
http://arxiv.org/abs/2402.01867
In the age of large language models (LLMs) and the widespread adoption of AI-driven content creation, the landscape of information dissemination has witnessed a paradigm shift. With the proliferation of both human-written and machine-generated real a
Externí odkaz:
http://arxiv.org/abs/2311.04917
The spread of fake news has emerged as a critical challenge, undermining trust and posing threats to society. In the era of Large Language Models (LLMs), the capability to generate believable fake content has intensified these concerns. In this study
Externí odkaz:
http://arxiv.org/abs/2309.08674
Autor:
Wang, Yuxia, Mansurov, Jonibek, Ivanov, Petar, Su, Jinyan, Shelmanov, Artem, Tsvigun, Akim, Whitehouse, Chenxi, Afzal, Osama Mohammed, Mahmoud, Tarek, Sasaki, Toru, Arnold, Thomas, Aji, Alham Fikri, Habash, Nizar, Gurevych, Iryna, Nakov, Preslav
Large language models (LLMs) have demonstrated remarkable capability to generate fluent responses to a wide variety of user queries. However, this has also raised concerns about the potential misuse of such texts in journalism, education, and academi
Externí odkaz:
http://arxiv.org/abs/2305.14902
With the rapid progress of large language models (LLMs) and the huge amount of text they generated, it becomes more and more impractical to manually distinguish whether a text is machine-generated. Given the growing use of LLMs in social media and ed
Externí odkaz:
http://arxiv.org/abs/2306.05540
In this paper, we revisit the problem of Differentially Private Stochastic Convex Optimization (DP-SCO) in Euclidean and general $\ell_p^d$ spaces. Specifically, we focus on three settings that are still far from well understood: (1) DP-SCO over a co
Externí odkaz:
http://arxiv.org/abs/2303.18047