Related papers: Experiments with Neural Networks for Small and Lar…
Data duplication during pretraining can degrade generalization and lead to memorization, motivating aggressive deduplication pipelines. However, at web scale, it is unclear what constitutes a ``duplicate'': beyond surface-form matches,…
Due to the large number of submissions that more and more conferences experience, finding an automatized way to well distribute the submitted papers among reviewers has become necessary. We model the peer-reviewing matching problem as a…
Spell-checking is the process of detecting and sometimes providing suggestions for incorrectly spelled words in a text. Basically, the larger the dictionary of a spell-checker is, the higher is the error detection rate; otherwise,…
This study was motivated by the problem of identifying fake documents on the Internet. To explore possible solutions to this problem we introduce a model of a network community in which members submit documents with verifiable content.…
Language models typically tokenize raw text into sequences of subword identifiers from a predefined vocabulary, a process inherently sensitive to typographical errors, length variations, and largely oblivious to the internal structure of…
We present the problem of finding comparable researchers for any given researcher. This problem has many motivations. Firstly, know thyself. The answers of where we stand among research community and who we are most alike may not be easily…
In the realm of text manipulation and linguistic transformation, the question of authorship has been a subject of fascination and philosophical inquiry. Much like the Ship of Theseus paradox, which ponders whether a ship remains the same…
The DarkWeb represents a hotbed for illicit activity, where users communicate on different market forums in order to exchange goods and services. Law enforcement agencies benefit from forensic tools that perform authorship analysis, in…
The number of scientific publications is constantly rising, increasing the strain on the review process. The number of submissions is actually higher, as each manuscript is often reviewed several times before publication. To face the deluge…
Dual encoders perform retrieval by encoding documents and queries into dense lowdimensional vectors, scoring each document by its inner product with the query. We investigate the capacity of this architecture relative to sparse bag-of-words…
Existing neural network verifiers compute a proof that each input is handled correctly under a given perturbation by propagating a symbolic abstraction of reachable values at each layer. This process is repeated from scratch independently…
As LLMs rapidly advance and enter real-world use, their privacy implications are increasingly important. We study an authorship de-anonymization threat: using LLMs to link anonymous documents to their authors, potentially compromising…
We present a document-level neural machine translation model which takes both source and target document context into account using memory networks. We model the problem as a structured prediction problem with interdependencies among the…
Verifying the identity of a person using handwritten signatures is challenging in the presence of skilled forgeries, where a forger has access to a person's signature and deliberately attempt to imitate it. In offline (static) signature…
Predicting the emergence of future research collaborations between authors in academic social networks (SNs) is a very effective example that demonstrates the link prediction problem. This problem refers to predicting the potential…
The article presents a system for testing the independence of solutions to algorithmic problems sent by students as part of the student programming competition. First, the context was discussed, as well as the need to organize programming…
We present a novel divide-and-conquer method for the neural summarization of long documents. Our method exploits the discourse structure of the document and uses sentence similarity to split the problem into an ensemble of smaller…
This paper introduces several techniques that improve the scalability of the deductive verification of data-level programs working on arrays and matrices. First of all, we introduce a technique to rewrite expressions with (nested)…
Neural networks are one of the most investigated and widely used techniques in Machine Learning. In spite of their success, they still find limited application in safety- and security-related contexts, wherein assurance about networks'…
Data mining, machine learning, and natural language processing are powerful techniques that can be used together to extract information from large texts. Depending on the task or problem at hand, there are many different approaches that can…