5 papers
Tau-Eval: A Unified Evaluation Framework for Useful and Private Text Anonymization
Gabriel Loiseau, Damien Sileo, Damien Riquet +2
Text anonymization is the process of removing or obfuscating information from textual data to protect the privacy of individuals. This process inherently involves a complex trade-o…
TAROT: Task-Oriented Authorship Obfuscation Using Policy Optimization Methods
Gabriel Loiseau, Damien Sileo, Damien Riquet +2
Authorship obfuscation aims to disguise the identity of an author within a text by altering the writing style, vocabulary, syntax, and other linguistic features associated with the…
Logic Haystacks: Probing LLMs Long-Context Logical Reasoning (Without Easily Identifiable Unrelated Padding)
Damien Sileo
Large language models demonstrate promising long context processing capabilities, with recent models touting context windows close to one million tokens. However, the evaluations s…
Attention Overflow: Language Model Input Blur during Long-Context Missing Items Recommendation
Damien Sileo
Large language models (LLMs) can suggest missing elements from items listed in a prompt, which can be used for list completion or recommendations based on users' history. However,…
Scaling Synthetic Logical Reasoning Datasets with Context-Sensitive Declarative Grammars
Damien Sileo
Logical reasoning remains a challenge for natural language processing, but it can be improved by training language models to mimic theorem provers on procedurally generated problem…