Zobrazeno 1 - 10
of 203
pro vyhledávání: '"Cohn, Trevor"'
Autor:
Wang, Jun, Briakou, Eleftheria, Dadkhahi, Hamid, Agarwal, Rishabh, Cherry, Colin, Cohn, Trevor
A critical component in knowledge distillation is the means of coupling the teacher and student. The predominant sequence knowledge distillation method involves supervised learning of the student against teacher-decoded outputs, and is exemplified by
Externí odkaz:
http://arxiv.org/abs/2407.10456
Modern NLP models are often trained on public datasets drawn from diverse sources, rendering them vulnerable to data poisoning attacks. These attacks can manipulate the model's behavior in ways engineered by the attacker. One such tactic involves the
Externí odkaz:
http://arxiv.org/abs/2405.11575
Autor:
He, Xuanli, Wang, Jun, Xu, Qiongkai, Minervini, Pasquale, Stenetorp, Pontus, Rubinstein, Benjamin I. P., Cohn, Trevor
The implications of backdoor attacks on English-centric large language models (LLMs) have been widely examined - such attacks can be achieved by embedding malicious behaviors during training and activated under specific conditions that trigger malici
Externí odkaz:
http://arxiv.org/abs/2404.19597
In this work, we measure the impact of affixal negation on modern English large language models (LLMs). In affixal negation, the negated meaning is expressed through a negative morpheme, which is potentially challenging for LLMs as their tokenizers a
Externí odkaz:
http://arxiv.org/abs/2404.02421
While multilingual machine translation (MNMT) systems hold substantial promise, they also have security vulnerabilities. Our research highlights that MNMT systems can be susceptible to a particularly devious style of backdoor attack, whereby an attac
Externí odkaz:
http://arxiv.org/abs/2404.02393
Cross-lingual open domain question answering (CLQA) is a complex problem, comprising cross-lingual retrieval from a multilingual knowledge base, followed by answer generation in the query language. Both steps are usually tackled by separate models, r
Externí odkaz:
http://arxiv.org/abs/2402.16508
A good translation should be faithful to the source and should respect the norms of the target language. We address a theoretical puzzle about the relationship between these objectives. On one hand, intuition and some prior work suggest that accuracy
Externí odkaz:
http://arxiv.org/abs/2402.12690
Human translators linger on some words and phrases more than others, and predicting this variation is a step towards explaining the underlying cognitive processes. Using data from the CRITT Translation Process Research Database, we evaluate the exten
Externí odkaz:
http://arxiv.org/abs/2312.11852
We present Multi-EuP, a new multilingual benchmark dataset, comprising 22K multi-lingual documents collected from the European Parliament, spanning 24 languages. This dataset is designed to investigate fairness in a multilingual information retrieval
Externí odkaz:
http://arxiv.org/abs/2311.01870
Federated Learning allows collaborative training without data sharing in settings where participants do not trust the central server and one another. Privacy can be further improved by ensuring that communication between the participants and the serv
Externí odkaz:
http://arxiv.org/abs/2310.05960