Pieter Delobelle

35 papers A* 3A 1C 2Journal 18Unranked 11

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Audit Me If You Can: Query-Efficient Active Fairness Auditing of Black-Box LLMs. CoRR David Hartmann, Lena Pohlmann, Lelia Hanslik, Noah Gießing, Bettina Berendt, Pieter Delobelle
2026	A*	`conf`	ProbLog4Fairness: A Neurosymbolic Approach to Modeling and Mitigating Bias. AAAI Rik Adriaensen, Lucas Van Praet, Jessa Bekker, Robin Manhaeve, Pieter Delobelle, Maarten Buyl
2025	J	`jnl`	ProbLog4Fairness: A Neurosymbolic Approach to Modeling and Mitigating Bias. CoRR Rik Adriaensen, Lucas Van Praet, Jessa Bekker, Robin Manhaeve, Pieter Delobelle, Maarten Buyl
2025	—	`conf`	SHADES: Towards a Multilingual Assessment of Stereotypes in Large Language Models. NAACL (Long Papers) Margaret Mitchell, Giuseppe Attanasio, Ioana Baldini, Miruna Clinciu, Jordan Clive, Pieter Delobelle, Manan Dey, Sil Hamilton, Timm Dill, Jad Doughman, Ritam Dutt, Avijit Ghosh, Jessica Zosa Forde, Carolin Holtermann, Lucie-Aimée Kaffee, Tanmay Laud, Anne Lauscher, Roberto L. Lopez-Davila, Maraim Masoud, Nikita Nangia, Anaelia Ovalle, Giada Pistilli, Dragomir Radev, Beatrice Savoldi, Vipul Raheja, Jeremy Qin, Esther Ploeger, Arjun Subramonian, Kaustubh D. Dhole, Kaiser Sun, Amirbek Djanibekov, Jonibek Mansurov, Kayo Yin, Emilio Villa Cueva, Sagnik Mukherjee, Jerry Huang, Xudong Shen, Jay Gala, Hamdan Al-Ali, Tair Djanibekov, Nurdaulet Mukhituly, Shangrui Nie, Shanya Sharma, Karolina Stanczak, Eliza Szczechla, Tiago Timponi Torrent, Deepak Tunuguntla, Marcelo Viridiano, Oskar van der Wal, Adina Yakefu, Aurélie Névéol, Mike Zhang, Sydney Zink, Zeerak Talat
2024	—	`conf`	BPE-knockout: Pruning Pre-existing BPE Tokenisers with Backwards-compatible Morphological Semi-supervision. NAACL-HLT Thomas Bauwens, Pieter Delobelle
2024	J	`jnl`	ChocoLlama: Lessons Learned From Teaching Llamas Dutch. CoRR Matthieu Meeus, Anthony Rathé, François Remy, Pieter Delobelle, Jens-Joris Decorte, Thomas Demeester
2024	—	`conf`	ItaEval and TweetyIta: A New Extensive Benchmark and Efficiency-First Language Model for Italian. CLiC-it Giuseppe Attanasio, Pieter Delobelle, Moreno La Quatra, Andrea Santilli, Beatrice Savoldi
2024	A*	`conf`	Metrics for What, Metrics for Whom: Assessing Actionability of Bias Evaluation Metrics in NLP. EMNLP Pieter Delobelle, Giuseppe Attanasio, Debora Nozza, Su Lin Blodgett, Zeerak Talat
2024	—	`conf`	OneLove beyond the field - A few-shot pipeline for topic and sentiment analysis during the FIFA World Cup in Qatar. KONVENS Christoph Rauchegger, Sonja Mei Wang, Pieter Delobelle
2024	J	`jnl`	OneLove beyond the field - A few-shot pipeline for topic and sentiment analysis during the FIFA World Cup in Qatar. CoRR Christoph Rauchegger, Sonja Mei Wang, Pieter Delobelle
2024	J	`jnl`	Trans-Tokenization and Cross-lingual Vocabulary Transfers: Language Adaptation of LLMs for Low-Resource NLP. CoRR François Remy, Pieter Delobelle, Hayastan Avetisyan, Alfiya Khabibullina, Miryam de Lhoneux, Thomas Demeester
2024	A*	`conf`	Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models. ICML Xavier Suau, Pieter Delobelle, Katherine Metcalf, Armand Joulin, Nicholas Apostoloff, Luca Zappella, Pau Rodríguez
2024	J	`jnl`	Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models. CoRR Xavier Suau, Pieter Delobelle, Katherine Metcalf, Armand Joulin, Nicholas Apostoloff, Luca Zappella, Pau Rodríguez
2023	A	`conf`	How Far Can It Go? On Intrinsic Gender Bias Mitigation for Text Classification. EACL Ewoenam Kwaku Tokpo, Pieter Delobelle, Bettina Berendt, Toon Calders
2023	J	`jnl`	How Far Can It Go?: On Intrinsic Gender Bias Mitigation for Text Classification. CoRR Ewoenam Kwaku Tokpo, Pieter Delobelle, Bettina Berendt, Toon Calders
2023	—	`conf`	ResumeTailor: Improving Resume Quality Through Co-Creative Tools. HHAI Pieter Delobelle, Sonja Mei Wang, Bettina Berendt
2023	J	`jnl`	Tik-to-Tok: Translating Language Models One Token at a Time: An Embedding Initialization Strategy for Efficient Language Adaptation. CoRR François Remy, Pieter Delobelle, Bettina Berendt, Kris Demuynck, Thomas Demeester
2022	—	`conf`	Algorithmic Tools in Public Employment Services: Towards a Jobseeker-Centric Perspective. FAccT Kristen M. Scott, Sonja Mei Wang, Milagros Miceli, Pieter Delobelle, Karolina Sztandar-Sztanderska, Bettina Berendt
2022	—	`conf`	FairDistillation: Mitigating Stereotyping in Language Models. ECML/PKDD (2) Pieter Delobelle, Bettina Berendt
2022	J	`jnl`	FairDistillation: Mitigating Stereotyping in Language Models. CoRR Pieter Delobelle, Bettina Berendt
2022	—	`conf`	Measuring Fairness with Biased Rulers: A Comparative Study on Bias Metrics for Pre-trained Language Models. NAACL-HLT Pieter Delobelle, Ewoenam Kwaku Tokpo, Toon Calders, Bettina Berendt
2022	J	`jnl`	RobBERT-2022: Updating a Dutch Language Model to Account for Evolving Language Use. CoRR Pieter Delobelle, Thomas Winters, Bettina Berendt
2022	J	`jnl`	RobBERTje: a Distilled Dutch BERT Model. CoRR Pieter Delobelle, Thomas Winters, Bettina Berendt
2021	J	`jnl`	Ethical Adversaries: Towards Mitigating Unfairness with Adversarial Machine Learning. SIGKDD Explor. Pieter Delobelle, Paul Temple, Gilles Perrouin, Benoît Frénay, Patrick Heymans, Bettina Berendt
2021	C	`conf`	Learning to Rank Generated Portmanteaus. ICCC Lara Pollet, Thomas Winters, Pieter Delobelle
2021	J	`jnl`	Measuring Fairness with Biased Rulers: A Survey on Quantifying Biases in Pretrained Language Models. CoRR Pieter Delobelle, Ewoenam Kwaku Tokpo, Toon Calders, Bettina Berendt
2021	J	`jnl`	Measuring Shifts in Attitudes Towards COVID-19 Measures in Belgium Using Multilingual BERT. CoRR Kristen M. Scott, Pieter Delobelle, Bettina Berendt
2021	C	`conf`	Survival of the Wittiest: Evolving Satire with Language Models. ICCC Thomas Winters, Pieter Delobelle
2020	J	`jnl`	Dutch Humor Detection by Generating Negative Examples. CoRR Thomas Winters, Pieter Delobelle
2020	J	`jnl`	Ethical Adversaries: Towards Mitigating Unfairness with Adversarial Machine Learning. CoRR Pieter Delobelle, Paul Temple, Gilles Perrouin, Benoît Frénay, Patrick Heymans, Bettina Berendt
2020	—	`conf`	RobBERT: a Dutch RoBERTa-based Language Model. EMNLP (Findings) Pieter Delobelle, Thomas Winters, Bettina Berendt
2020	J	`jnl`	RobBERT: a Dutch RoBERTa-based Language Model. CoRR Pieter Delobelle, Thomas Winters, Bettina Berendt
2019	—	`conf`	Computational Ad Hominem Detection. ACL (2) Pieter Delobelle, Murilo Cunha, Eric Massip Cano, Jeroen Peperkamp, Bettina Berendt
2019	—	`conf`	Time to Take Emoji Seriously: They Vastly Improve Casual Conversational Models. BNAIC/BENELEARN Pieter Delobelle, Bettina Berendt
2019	J	`jnl`	Time to Take Emoji Seriously: They Vastly Improve Casual Conversational Models. CoRR Pieter Delobelle, Bettina Berendt