IRIS
ROTTGER, PAUL
 Distribuzione geografica
Salva come PNG Salva come JPEG
Continente #
EU - Europa 939
NA - Nord America 641
AS - Asia 535
SA - Sud America 105
AF - Africa 34
Totale 2.254
Salva come PNG Salva come JPEG
Nazione #
US - Stati Uniti d'America 607
FI - Finlandia 375
RU - Federazione Russa 320
SG - Singapore 121
CN - Cina 113
IT - Italia 85
HK - Hong Kong 83
VN - Vietnam 79
BR - Brasile 77
BD - Bangladesh 60
DE - Germania 34
FR - Francia 30
IE - Irlanda 28
ZA - Sudafrica 27
GB - Regno Unito 24
CA - Canada 18
ES - Italia 14
IN - India 13
PL - Polonia 11
JP - Giappone 10
MX - Messico 9
ID - Indonesia 8
KR - Corea 8
IL - Israele 6
PH - Filippine 6
AR - Argentina 5
CO - Colombia 5
EC - Ecuador 5
PE - Perù 5
PK - Pakistan 5
AT - Austria 4
NL - Olanda 4
SA - Arabia Saudita 4
TR - Turchia 4
CL - Cile 3
IQ - Iraq 3
AZ - Azerbaigian 2
CZ - Repubblica Ceca 2
DO - Repubblica Dominicana 2
DZ - Algeria 2
JM - Giamaica 2
NP - Nepal 2
UY - Uruguay 2
VE - Venezuela 2
BE - Belgio 1
BH - Bahrain 1
CH - Svizzera 1
CR - Costa Rica 1
CU - Cuba 1
DK - Danimarca 1
EG - Egitto 1
GR - Grecia 1
KE - Kenya 1
KG - Kirghizistan 1
KZ - Kazakistan 1
LT - Lituania 1
MA - Marocco 1
MZ - Mozambico 1
OM - Oman 1
PA - Panama 1
PT - Portogallo 1
PY - Paraguay 1
RO - Romania 1
SE - Svezia 1
SY - Repubblica araba siriana 1
TH - Thailandia 1
TN - Tunisia 1
TW - Taiwan 1
UZ - Uzbekistan 1
Totale 2.254
Salva come PNG Salva come JPEG
Città #
Helsinki 371
Ashburn 107
Hong Kong 83
San Jose 76
Moscow 69
Singapore 54
New York 47
The Dalles 42
Milan 39
Hefei 38
Los Angeles 36
Beijing 34
Dublin 28
Ho Chi Minh City 25
Johannesburg 24
Boardman 22
Edison 22
Dallas 21
Hanoi 21
Orem 16
São Paulo 13
Frankfurt am Main 12
London 11
Council Bluffs 10
Tokyo 10
Brooklyn 8
Denver 8
Düsseldorf 8
Montreal 8
Warsaw 8
Lauterbourg 7
Chennai 6
Da Nang 6
Haiphong 6
Rio de Janeiro 6
Santa Clara 6
Tel Aviv 6
Atlanta 5
Belo Horizonte 5
Cabanatuan City 5
Chicago 5
Jakarta 5
Munich 5
Seoul 5
Trento 5
Mexico City 4
Rome 4
Vienna 4
Baghdad 3
Bexley 3
Boston 3
Calvenzano 3
Cape Town 3
Guayaquil 3
Lappeenranta 3
Lima 3
Manchester 3
Marseille 3
Portsmouth 3
San Francisco 3
Toronto 3
Ankara 2
Anápolis 2
Baku 2
Bari 2
Buenos Aires 2
Buffalo 2
Campinas 2
Florence 2
Houston 2
Kingston 2
Las Vegas 2
Maceió 2
Madrid 2
Memphis 2
Montevideo 2
Mumbai 2
Naples 2
Porto Alegre 2
Providence 2
Riyadh 2
Rostov-on-Don 2
Roubaix 2
Santiago 2
Seattle 2
Shanghai 2
Streatham 2
Thái Bình 2
Topeka 2
Vancouver 2
Vũng Tàu 2
Acalanes Ridge 1
Albuquerque 1
Amritsar 1
Ancona 1
Aracaju 1
Araguari 1
Athens 1
Bangkok 1
Bauru 1
Totale 1.474
Salva come PNG Salva come JPEG
Nome #
The benefits, risks and bounds of personalizing the alignment of large language models to individuals 170
XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models 158
Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions 148
Improving Adversarial Data Collection by Supporting Annotators: Lessons from GAHD, a German Hate Speech Dataset 139
Data-efficient strategies for expanding hate speech detection into under-resourced languages 139
Two contrasting data annotation paradigms for subjective NLP tasks 137
Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models 133
The ecological fallacy in annotation: modeling human label variation goes beyond sociodemographics 127
Multilingual HateCheck: functional tests for multilingual hate speech detection models 118
“My answer is C”: first-token probabilities do not match text answers in instruction-tuned language models 103
Beyond Flesch-Kincaid: Prompt-based Metrics Improve Difficulty Classification of Educational Texts 102
Near to Mid-term Risks and Opportunities of Open-Source Generative AI 94
Evaluating the Elementary Multilingual Capabilities of Large Language Models with MultiQ 89
Look at the Text: Instruction-Tuned Language Models are More Robust Multiple Choice Selectors than You Think 86
The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models 84
From Languages to Geographies: Towards Evaluating Cultural Bias in Hate Speech Datasets 84
The Empty Signifier Problem: Towards Clearer Paradigms for Operationalising "Alignment" in Large Language Models 82
Improving Covert Toxicity Detection by Retrieving and Generating References 82
Personalization up to a Point: Why Personalized Content Moderation Needs Boundaries, and How We Can Enforce Them 76
The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values 74
Compromesso! Italian Many-Shot Jailbreaks undermine the safety of Large Language Models 73
Totale 2.298
Salva come PNG Salva come JPEG
Categoria #
all - tutte 6.545
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 6.545
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
2024/2025396 1 4 4 0 4 11 49 37 84 87 65 50
2025/20261.804 123 96 41 150 128 55 110 204 474 259 96 68
Totale 2.298