5 papers
A Universal Vibe? Finding and Controlling Language-Agnostic Informal Register with SAEs
Uri Z. Kialy, Avi Shtarkberg, Ayal Klein
While multilingual language models successfully transfer factual and syntactic knowledge across languages, it remains unclear whether they process culture-specific pragmatic regist…
Effective QA-driven Annotation of Predicate-Argument Relations Across Languages
Jonathan Davidov, Aviv Slobodkin, Shmuel Tomi Klein +3
Explicit representations of predicate-argument relations form the basis of interpretable semantic analysis, supporting reasoning, generation, and evaluation. However, attaining suc…
QA-Noun: Representing Nominal Semantics via Natural Language Question-Answer Pairs
Maria Tseytlin, Paul Roit, Omri Abend +2
Decomposing sentences into fine-grained meaning units is increasingly used to model semantic alignment. While QA-based semantic approaches have shown effectiveness for representing…
QAPyramid: Fine-grained Evaluation of Content Selection for Text Summarization
Shiyue Zhang, David Wan, Arie Cattan +3
How to properly conduct human evaluations for text summarization is a longstanding challenge. The Pyramid human evaluation protocol, which assesses content selection by breaking th…
Large language models for mental health
Andreas Triantafyllopoulos, Yannik Terhorst, Iosif Tsangko +10
Digital technologies have long been explored as a complement to standard procedure in mental health research and practice, ranging from the management of electronic health records…