IRIS
ROTTGER, PAUL
 Distribuzione geografica
Salva come PNG Salva come JPEG
Continente #
AS - Asia 127
EU - Europa 117
NA - Nord America 80
SA - Sud America 17
Totale 341
Salva come PNG Salva come JPEG
Nazione #
US - Stati Uniti d'America 78
HK - Hong Kong 57
SG - Singapore 33
IE - Irlanda 28
IT - Italia 26
DE - Germania 22
RU - Federazione Russa 16
BR - Brasile 15
CN - Cina 13
FI - Finlandia 8
ID - Indonesia 6
FR - Francia 5
IL - Israele 5
PH - Filippine 5
GB - Regno Unito 3
NL - Olanda 3
AZ - Azerbaigian 2
CZ - Repubblica Ceca 2
PK - Pakistan 2
TR - Turchia 2
AR - Argentina 1
AT - Austria 1
DK - Danimarca 1
DO - Repubblica Dominicana 1
GR - Grecia 1
KG - Kirghizistan 1
PA - Panama 1
PE - Perù 1
PT - Portogallo 1
SA - Arabia Saudita 1
Totale 341
Salva come PNG Salva come JPEG
Città #
Hong Kong 57
The Dalles 42
Dublin 28
Milan 25
Singapore 10
Düsseldorf 8
Frankfurt am Main 6
Cabanatuan City 5
Helsinki 5
Jakarta 5
Tel Aviv 5
Los Angeles 4
Moscow 4
Beijing 3
Munich 3
Ashburn 2
Baku 2
Campinas 2
Lappeenranta 2
Lauterbourg 2
New York 2
Portsmouth 2
São Paulo 2
Araguari 1
Athens 1
Belo Horizonte 1
Berlin 1
Bishkek 1
Boardman 1
Bonndorf 1
Brno 1
Buenos Aires 1
Cabo Frio 1
Copenhagen 1
Curitiba 1
Guangzhou 1
Islamabad 1
Istanbul 1
Lima region 1
Lisbon 1
London 1
Maceió 1
Maricá 1
Multan 1
Ponta Porã 1
Prague 1
Ribeirão das Neves 1
Rio de Janeiro 1
Riyadh 1
Tucuruí 1
Viamão 1
Vienna 1
Totale 255
Salva come PNG Salva come JPEG
Nome #
Data-efficient strategies for expanding hate speech detection into under-resourced languages 62
Two contrasting data annotation paradigms for subjective NLP tasks 50
Multilingual HateCheck: functional tests for multilingual hate speech detection models 35
The ecological fallacy in annotation: modeling human label variation goes beyond sociodemographics 28
“My answer is C”: first-token probabilities do not match text answers in instruction-tuned language models 20
The benefits, risks and bounds of personalizing the alignment of large language models to individuals 18
XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models 15
Evaluating the Elementary Multilingual Capabilities of Large Language Models with MultiQ 14
The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models 13
The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values 13
Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models 13
The Empty Signifier Problem: Towards Clearer Paradigms for Operationalising "Alignment" in Large Language Models 12
From Languages to Geographies: Towards Evaluating Cultural Bias in Hate Speech Datasets 12
Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions 12
Near to Mid-term Risks and Opportunities of Open-Source Generative AI 12
Look at the Text: Instruction-Tuned Language Models are More Robust Multiple Choice Selectors than You Think 12
Improving Adversarial Data Collection by Supporting Annotators: Lessons from GAHD, a German Hate Speech Dataset 12
Improving Covert Toxicity Detection by Retrieving and Generating References 10
Beyond Flesch-Kincaid: Prompt-based Metrics Improve Difficulty Classification of Educational Texts 10
Totale 373
Salva come PNG Salva come JPEG
Categoria #
all - tutte 1.766
article - articoli 0
book - libri 0
conference - conferenze 0
curatela - curatele 0
other - altro 0
patent - brevetti 0
selected - selezionate 0
volume - volumi 0
Totale 1.766
Salva come PNG Salva come JPEG


Totale Lug Ago Sett Ott Nov Dic Gen Feb Mar Apr Mag Giu
2022/202341 0 0 0 0 0 1 5 5 28 2 0 0
2023/202457 6 1 2 2 7 3 6 13 2 0 9 6
2024/2025275 1 4 4 0 4 11 43 37 84 84 3 0
Totale 373