default search action
Paul Röttger
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2024
- [j1]Hannah Rose Kirk
, Bertie Vidgen, Paul Röttger, Scott A. Hale:
The benefits, risks and bounds of personalizing the alignment of large language models to individuals. Nat. Mac. Intell. 6(4): 383-392 (2024) - [c18]Fabio Pernisi, Dirk Hovy, Paul Röttger:
Compromesso! Italian Many-Shot Jailbreaks undermine the safety of Large Language Models. ACL (Student Research Workshop) 2024: 339-345 - [c17]Carolin Holtermann, Paul Röttger, Timm Dill, Anne Lauscher:
Evaluating the Elementary Multilingual Capabilities of Large Language Models with MultiQ. ACL (Findings) 2024: 4476-4494 - [c16]Xinpeng Wang, Bolei Ma, Chengzhi Hu, Leon Weber-Genzel, Paul Röttger, Frauke Kreuter, Dirk Hovy, Barbara Plank:
"My Answer is C": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models. ACL (Findings) 2024: 7407-7416 - [c15]Paul Röttger, Valentin Hofmann, Valentina Pyatkin, Musashi Hinck, Hannah Kirk, Hinrich Schütze, Dirk Hovy:
Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models. ACL (1) 2024: 15295-15311 - [c14]Donya Rooein, Paul Röttger, Anastassia Shaitarova, Dirk Hovy:
Beyond Flesch-Kincaid: Prompt-based Metrics Improve Difficulty Classification of Educational Texts. BEA 2024: 54-67 - [c13]Federico Bianchi, Mirac Suzgun, Giuseppe Attanasio, Paul Röttger, Dan Jurafsky, Tatsunori Hashimoto, James Zou:
Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions. ICLR 2024 - [c12]Francisco Eiras, Aleksandar Petrov, Bertie Vidgen, Christian Schröder de Witt, Fabio Pizzati, Katherine Elkins, Supratik Mukhopadhyay, Adel Bibi, Botos Csaba, Fabro Steibel, Fazl Barez, Genevieve Smith, Gianluca Guadagni, Jon Chun, Jordi Cabot, Joseph Marvin Imperial, Juan A. Nolazco-Flores, Lori Landay, Matthew Thomas Jackson, Paul Röttger, Philip H. S. Torr, Trevor Darrell, Yong Suk Lee, Jakob N. Foerster:
Position: Near to Mid-term Risks and Opportunities of Open-Source Generative AI. ICML 2024 - [c11]Janis Goldzycher, Paul Röttger, Gerold Schneider:
Improving Adversarial Data Collection by Supporting Annotators: Lessons from GAHD, a German Hate Speech Dataset. NAACL-HLT 2024: 4405-4424 - [c10]Paul Röttger, Hannah Kirk, Bertie Vidgen, Giuseppe Attanasio, Federico Bianchi, Dirk Hovy:
XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models. NAACL-HLT 2024: 5377-5400 - [i28]Xinpeng Wang, Bolei Ma, Chengzhi Hu, Leon Weber-Genzel, Paul Röttger, Frauke Kreuter, Dirk Hovy, Barbara Plank:
"My Answer is C": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models. CoRR abs/2402.14499 (2024) - [i27]Paul Röttger, Valentin Hofmann, Valentina Pyatkin, Musashi Hinck, Hannah Rose Kirk, Hinrich Schütze, Dirk Hovy:
Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models. CoRR abs/2402.16786 (2024) - [i26]Carolin Holtermann, Paul Röttger, Timm Dill, Anne Lauscher:
Evaluating the Elementary Multilingual Capabilities of Large Language Models with MultiQ. CoRR abs/2403.03814 (2024) - [i25]Janis Goldzycher, Paul Röttger, Gerold Schneider:
Improving Adversarial Data Collection by Supporting Annotators: Lessons from GAHD, a German Hate Speech Dataset. CoRR abs/2403.19559 (2024) - [i24]Paul Röttger, Fabio Pernisi, Bertie Vidgen, Dirk Hovy:
SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety. CoRR abs/2404.05399 (2024) - [i23]Xinpeng Wang, Chengzhi Hu, Bolei Ma, Paul Röttger, Barbara Plank:
Look at the Text: Instruction-Tuned Language Models are More Robust Multiple Choice Selectors than You Think. CoRR abs/2404.08382 (2024) - [i22]Bertie Vidgen, Adarsh Agrawal, Ahmed M. Ahmed, Victor Akinwande, Namir Al-Nuaimi, Najla Alfaraj, Elie Alhajjar, Lora Aroyo, Trupti Bavalatti, Borhane Blili-Hamelin, Kurt D. Bollacker, Rishi Bomassani, Marisa Ferrara Boston, Siméon Campos, Kal Chakra, Canyu Chen, Cody Coleman, Zacharie Delpierre Coudert, Leon Derczynski, Debojyoti Dutta, Ian Eisenberg, James Ezick, Heather Frase, Brian Fuller, Ram Gandikota, Agasthya Gangavarapu, Ananya Gangavarapu, James Gealy, Rajat Ghosh, James Goel, Usman Gohar, Subhra S. Goswami, Scott A. Hale, Wiebke Hutiri, Joseph Marvin Imperial, Surgan Jandial, Nick Judd
Introducing v0.5 of the AI Safety Benchmark from MLCommons. CoRR abs/2404.12241 (2024) - [i21]Hannah Rose Kirk, Alexander Whitefield, Paul Röttger, Andrew M. Bean
The PRISM Alignment Project: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models. CoRR abs/2404.16019 (2024) - [i20]Francisco Eiras, Aleksandar Petrov, Bertie Vidgen, Christian Schröder de Witt, Fabio Pizzati, Katherine Elkins, Supratik Mukhopadhyay, Adel Bibi
Near to Mid-term Risks and Opportunities of Open Source Generative AI. CoRR abs/2404.17047 (2024) - [i19]Manuel Tonneau, Diyi Liu, Samuel Fraiberger, Ralph Schroeder, Scott A. Hale, Paul Röttger:
From Languages to Geographies: Towards Evaluating Cultural Bias in Hate Speech Datasets. CoRR abs/2404.17874 (2024) - [i18]Donya Rooein, Paul Röttger, Anastassia Shaitarova, Dirk Hovy:
Beyond Flesch-Kincaid: Prompt-based Metrics Improve Difficulty Classification of Educational Texts. CoRR abs/2405.09482 (2024) - [i17]Kobi Hackenburg, Ben M. Tappin, Paul Röttger, Scott Hale, Jonathan Bright, Helen Z. Margetts:
Evidence of a log scaling law for political persuasion with large language models. CoRR abs/2406.14508 (2024) - [i16]Fabio Pernisi, Dirk Hovy, Paul Röttger:
Compromesso! Italian Many-Shot Jailbreaks Undermine the Safety of Large Language Models. CoRR abs/2408.04522 (2024) - [i15]Xinpeng Wang, Chengzhi Hu, Paul Röttger, Barbara Plank:
Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation. CoRR abs/2410.03415 (2024) - 2023
- [c9]Matthias Orlikowski, Paul Röttger, Philipp Cimiano, Dirk Hovy:
The Ecological Fallacy in Annotation: Modeling Human Label Variation goes beyond Sociodemographics. ACL (2) 2023: 1017-1029 - [c8]Janosch Haber, Bertie Vidgen, Matthew Chapman, Vibhor Agarwal, Roy Ka-Wei Lee, Yong Keong Yap
Improving the Detection of Multilingual Online Attacks with Rich Social Media Data from Singapore. ACL (1) 2023: 12705-12721 - [c7]Hannah Kirk, Andrew M. Bean, Bertie Vidgen, Paul Röttger, Scott A. Hale:
The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values. EMNLP 2023: 2409-2430 - [c6]Hannah Kirk, Wenjie Yin, Bertie Vidgen, Paul Röttger:
SemEval-2023 Task 10: Explainable Detection of Online Sexism. SemEval@ACL 2023: 2193-2210 - [i14]Hannah Rose Kirk
SemEval-2023 Task 10: Explainable Detection of Online Sexism. CoRR abs/2303.04222 (2023) - [i13]Hannah Rose Kirk
Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback. CoRR abs/2303.05453 (2023) - [i12]Matthias Orlikowski, Paul Röttger, Philipp Cimiano, Dirk Hovy:
The Ecological Fallacy in Annotation: Modelling Human Label Variation goes beyond Sociodemographics. CoRR abs/2306.11559 (2023) - [i11]Paul Röttger, Hannah Rose Kirk, Bertie Vidgen, Giuseppe Attanasio, Federico Bianchi, Dirk Hovy:
XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models. CoRR abs/2308.01263 (2023) - [i10]Federico Bianchi, Mirac Suzgun, Giuseppe Attanasio, Paul Röttger, Dan Jurafsky, Tatsunori Hashimoto, James Zou:
Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions. CoRR abs/2309.07875 (2023) - [i9]Hannah Rose Kirk, Bertie Vidgen, Paul Röttger, Scott A. Hale:
The Empty Signifier Problem: Towards Clearer Paradigms for Operationalising "Alignment" in Large Language Models. CoRR abs/2310.02457 (2023) - [i8]Hannah Rose Kirk, Andrew M. Bean
The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values. CoRR abs/2310.07629 (2023) - [i7]Bertie Vidgen, Hannah Rose Kirk, Rebecca Qian, Nino Scherrer, Anand Kannappan, Scott A. Hale, Paul Röttger:
SimpleSafetyTests: a Test Suite for Identifying Critical Safety Risks in Large Language Models. CoRR abs/2311.08370 (2023) - 2022
- [c5]Paul Röttger, Debora Nozza, Federico Bianchi, Dirk Hovy:
Data-Efficient Strategies for Expanding Hate Speech Detection into Under-Resourced Languages. EMNLP 2022: 5674-5691 - [c4]Paul Röttger, Bertie Vidgen, Dirk Hovy, Janet B. Pierrehumbert:
Two Contrasting Data Annotation Paradigms for Subjective NLP Tasks. NAACL-HLT 2022: 175-190 - [c3]Hannah Kirk
Hatemoji: A Test Suite and Adversarially-Generated Dataset for Benchmarking and Detecting Emoji-Based Hate. NAACL-HLT 2022: 1352-1368 - [i6]Paul Röttger, Haitham Seelawi, Debora Nozza
Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models. CoRR abs/2206.09917 (2022) - [i5]Paul Röttger, Debora Nozza, Federico Bianchi, Dirk Hovy:
Data-Efficient Strategies for Expanding Hate Speech Detection into Under-Resourced Languages. CoRR abs/2210.11359 (2022) - 2021
- [c2]Paul Röttger, Bertie Vidgen, Dong Nguyen
HateCheck: Functional Tests for Hate Speech Detection Models. ACL/IJCNLP (1) 2021: 41-58 - [c1]Paul Röttger, Janet B. Pierrehumbert:
Temporal Adaptation of BERT and Performance on Downstream Document Classification: Insights from Social Media. EMNLP (Findings) 2021: 2400-2412 - [i4]Paul Röttger, Janet B. Pierrehumbert:
Temporal Adaptation of BERT and Performance on Downstream Document Classification: Insights from Social Media. CoRR abs/2104.08116 (2021) - [i3]Hannah Rose Kirk
Hatemoji: A Test Suite and Adversarially-Generated Dataset for Benchmarking and Detecting Emoji-based Hate. CoRR abs/2108.05921 (2021) - [i2]Paul Röttger, Bertie Vidgen, Dirk Hovy, Janet B. Pierrehumbert:
Two Contrasting Data Annotation Paradigms for Subjective NLP Tasks. CoRR abs/2112.07475 (2021) - 2020
- [i1]Paul Röttger, Bertram Vidgen, Dong Nguyen, Zeerak Waseem, Helen Z. Margetts, Janet B. Pierrehumbert:
HateCheck: Functional Tests for Hate Speech Detection Models. CoRR abs/2012.15606 (2020)
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from ,
, and
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and
to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from .
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-11-13 23:52 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by: