21 citations · 63 across the 17 of their papers we have counts for
6 papers · 1 filter
Towards More Robust Retrieval-Augmented Generation: Evaluating RAG Under Adversarial Poisoning Attacks
Jinyan Su, Jin Peng Zhou, Zhengxin Zhang +2
Retrieval-Augmented Generation (RAG) systems have emerged as a promising solution to mitigate LLM hallucinations and enhance their performance in knowledge-intensive domains. Howev…
Learning from Streaming Data when Users Choose
Jinyan Su, Sarah Dean
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 th…
Corpus Poisoning via Approximate Greedy Gradient Descent
Jinyan Su, Preslav Nakov, Claire Cardie
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-Augme…
SemEval-2024 Task 8: Multidomain, Multimodel and Multilingual Machine-Generated Text Detection
Yuxia Wang, Jonibek Mansurov, Petar Ivanov +12
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 subtask…
Leveraging Large Language Models for Structure Learning in Prompted Weak Supervision
Jinyan Su, Peilin Yu, Jieyu Zhang +1
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 la…
M4GT-Bench: Evaluation Benchmark for Black-Box Machine-Generated Text Detection
Yuxia Wang, Jonibek Mansurov, Petar Ivanov +11
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 pot…