Publications – The LESSEN Project

2023

Jirui Qi, Raquel Fernández, Arianna Bisazza, “Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models,”
EMNLP 2023 Main, December, 2023
vol. long/658, pp. 10650–10666
DOI: 10.18653/v1/2023.emnlp-main.658
URL: https://aclanthology.org/2023.emnlp-main.658/
Open Access: Yes

Suzan Verberne, “Service-Chatbots voor het Nederlands: De Onderzoeksagenda van het LESSEN Project,”
DIXIT magazine, December, 2023
vol. , pp. 32-33
DOI: No DOI
URL: https://notas.nl/dixit/dixit_2023_conversational_ai.pdf
Open Access: Yes

Heydar Soudani, Evangelos Kanoulas, Faegheh Hasibi, “Data Augmentation for Conversational AI,”
Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, CIKM 2023, October 2023
vol. , pp. 5220–5223
DOI: 10.1145/3583780.3615291
URL: https://dl.acm.org/doi/10.1145/3583780.3615291
Open Access: Yes

Xinyi Chen, Raquel Fernández, Sandro Pezzelle, “The BLA Benchmark: Investigating Basic Language Abilities of Pre-Trained Multimodal Models,”
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023
vol. , pp. 5817–5830
DOI: 10.18653/v1/2023.emnlp-main.356
URL: https://aclanthology.org/2023.emnlp-main.356/
Open Access: YES

2024

Mert Yazan, Frederik Situmeang, Ruilin Xiao, “Rethinking Conversation Styles of Chatbots from the Customer Perspective: Relationships between Conversation Styles of Chatbots, Chatbot Acceptance, and Perceived Tie Strength and Perceived Risk,”
International Journal of Human–Computer Interaction, February 2024
vol. 41(2), pp. 1342-1363
DOI: 10.1080/10447318.2024.2314348
URL: https://www.tandfonline.com/doi/abs/10.1080/10447318.2024.2314348
Open Access: No

Mohanna Hoveyda, Arjen de Vries, Maarten de Rijke, Faegheh Hasibi, “Real World Conversational Entity Linking Requires More Than Zero-Shots,”
Findings of the Association for Computational Linguistics ACL 2024, May 2024
vol. , pp.
DOI: 10.18653/v1/2024.findings-acl.829
URL: https://aclanthology.org/2024.findings-acl.829.pdf
Open Access: Yes

Heydar Soudani, Roxana Petcu, Evangelos Kanoulas, and Faegheh Hasibi., “Data Augmentation for Conversational AI,”
Proceedings of the ACM Web Conference 2024 (WWW ’24), May 2024
vol. , pp.
DOI: https://doi.org/10.1145/3589335.3641238
URL: https://dl.acm.org/doi/10.1145/3589335.3641238
Open Access: Yes

Andreas Paraskeva, Joao Pedro Reis, Suzan Verberne, Jan N. van Rijn, “Resource-constrained Neural Architecture Search on Language Models: A Case Study,”
WANT@ICML2024 workshop, June 2024
vol. , pp.
DOI: No DOI
URL: https://openreview.net/forum?id=ksdbauVu00¬eId=ksdbauVu00
Open Access: Yes

Mert Yazan, Frederik Situmeang, Suzan Verberne, “The Impact of Quantization on Retrieval-Augmented Generation: An Analysis of Small LLMs,”
IR-RAG@SIGIR’24, July 2024
vol. 3784, pp. 77-81
DOI: https://doi.org/10.48550/arXiv.2406.10251
URL: https://ceur-ws.org/Vol-3784/
Open Access: Yes

Vera Neplenbroek, Arianna Bisazza, Raquel Fernández, “MBBQ: A Dataset for Cross-Lingual Comparison of Stereotypes in Generative LLMs,”
Conference on Language Modeling (COLM), October 2024
vol. , pp.
DOI: https://doi.org/10.48550/arXiv.2406.07243
URL: https://openreview.net/forum?id=X9yV4lFHt4#discussion
Open Access: Yes

Yumeng Wang, “Towards Intent-Driven Transparency in Conversational Search Systems,”
ECIR 2025; Doctoral Consortium, November 2024
vol. , pp.
DOI: No DOI
URL: https://link.springer.com/chapter/10.1007/978-3-031-88720-8_37
Open Access: Yes

Jirui Qi*, Gabriele Sarti*, Raquel Fernández, Arianna Bisazza, “Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation,”
EMNLP 2024 Main, December 2024
vol. , pp.
DOI: https://doi.org/10.48550/arXiv.2406.13663
URL: https://arxiv.org/abs/2406.13663
Open Access: Yes

Xinyi Chen, Baohao Liao, Jirui Qi, Panagiotis Eustratiadis, Christof Monz, Arianna Bisazza, Maarten de Rijke, “The SIFo Benchmark: Investigating the Sequential Instruction Following Ability of Large Language Models,”
Findings of the 2024 Conference on Empirical Methods in Natural Language Processing, December 2024
vol. , pp.
DOI: https://doi.org/10.48550/arXiv.2406.19999
URL: https://arxiv.org/abs/2406.19999
Open Access: Yes

I-Fan Lin, Faegheh Hasibi, Suzan Verberne, “Generate then Refine: Data Augmentation for Zero-shot Intent Detection,”
Findings of the Association for Computational Linguistics: EMNLP 2024., December 2024
vol. , pp.
DOI: https://aclanthology.org/2024.findings-emnlp.768
URL: https://aclanthology.org/2024.findings-emnlp.768/
Open Access: Yes

Heydar Soudani, Evangelos Kanoulas, Faegheh Hasibi, “Fine Tuning vs. Retrieval Augmented Generation for Less Popular Knowledge,”
Proceedings of International ACM SIGIR Conference on Information Retrieval in the Asia Pacific, December 2024
vol. , pp.
DOI: https://doi.org/10.1145/3673791.369841
URL: https://arxiv.org/abs/2403.01432
Open Access: Yes

Tianyu Liu*, Jirui Qi*, Paul He, Arianna Bisazza, Mrinmaya Sachan, Ryan Cotterell, “Likelihood as a Performance Gauge for Retrieval-Augmented Generation,”
NAACL 2025 Main, November 2024
vol. , pp.
DOI: No DOI
URL: https://aclanthology.org/2025.naacl-long.78
Open Access: Yes

Nonkes, N., Agaronian, S., Kanoulas, E., Petcu, R., “Leveraging graph structures to detect hallucinations in large language models.,”
Proceedings of the TextGraphs-17 Workshop, ACL 2024, August 2024
vol. , pp. 93–104
DOI: https://doi.org/10.48550/arXiv.2407.04485
URL: https://aclanthology.org/2024.textgraphs-1.7/
Open Access: Yes

2025

Yumeng Wang, Xiuying Chen, and Suzan Verberne., “QUIDS: Query Intent Description for Exploratory Search via Dual Space Modeling,”
EMNLP 2025 Main, May 2025
vol. , pp.
DOI: https://arxiv.org/abs/2410.12400
URL: https://arxiv.org/abs/2410.12400
Open Access:

I-Fan Lin, Faegheh Hasibi, Suzan Verberne, “SPILL: Zero-shot Intent Clustering with Large Language Models ,”
Findings of the Association for Computational Linguistics ACL 2025, March 2025
vol. , pp.
DOI: No DOI
URL: No URL
Open Access:

Vera Neplenbroek, Arianna Bisazza, Raquel Fernández, “Cross-Lingual Transfer of Debiasing and Detoxification in Multilingual LLMs: An Extensive Investigation,”
Findings of the Association for Computational Linguistics ACL 2025, August 2025
vol. , pp. 2805–2830
DOI: https://doi.org/10.18653/v1/2025.findings-acl.145
URL: https://aclanthology.org/2025.findings-acl.145/
Open Access: Yes

Mert Yazan, Suzan Verberne, Frederik Situmeang, “Improving RAG for Personalization with Author Features and Contrastive Examples,”
ECIR 2025, April 2025
vol. 15574, pp. 408-416
DOI: 10.1007/978-3-031-88714-7_40
URL: https://link.springer.com/chapter/10.1007/978-3-031-88714-7_40#citeas
Open Access: Yes

Mohanna Hoveyda, Harrie Oosterhuis, Arjen P. de Vries, Maarten de Rijke, Faegheh Hasibi, “Adaptive Orchestration of Modular Generative Information Access Systems,”
SIGIR 2025; Perspective Track, April 2025
vol. , pp.
DOI: https://doi.org/10.1145/3726302.3730351
URL: https://arxiv.org/abs/2504.17454
Open Access: Yes

Jirui Qi, Raquel Fernández, Arianna Bisazza, “On the Consistency of Multilingual Context Utilization in Retrieval-Augmented Generation,”
Workshop on Multilingual Representation Learning (MRL) at EMNLP 2025, November 2025
vol. , pp.
DOI: 10.18653/v1/2025.mrl-main.15
URL: https://aclanthology.org/2025.mrl-main.15/
Open Access: Yes

Vera Neplenbroek, Arianna Bisazza, Raquel Fernández, “Reading Between the Prompts: How Stereotypes Shape LLM’s Implicit Personalization,”
EMNLP 2025 Main, November 2025
vol. , pp. 20378–20411
DOI: https://doi.org/10.18653/v1/2025.emnlp-main.1029
URL: https://aclanthology.org/2025.emnlp-main.1029/
Open Access: Yes

Heydar Soudani, “Enhancing Knowledge Injection in Large Language Models for Efficient and Trustworthy Responses,”
SIGIR 2025; Doctoral Consortium, April 2025
vol. , pp.
DOI: https://dl.acm.org/doi/10.1145/3726302.3730130
URL: https://dl.acm.org/doi/10.1145/3726302.3730130
Open Access: Yes

Heydar Soudani, Evangelos Kanoulas, Faegheh Hasibi, “Why Uncertainty Estimation Methods Fall Short in RAG: An Axiomatic Analysis,”
Findings of the Association for Computational Linguistics ACL 2025, May 2025
vol. , pp.
DOI: https://aclanthology.org/2025.findings-acl.852.pdf
URL: https://aclanthology.org/2025.findings-acl.852/
Open Access:

Jirui Qi†, Shan Chen†, Zidi Xiong, Raquel Fernández, Danielle S Bitterman‡, Arianna Bisazza‡, “When Models Reason in Your Language: Controlling Thinking Language Comes at the Cost of Accuracy,”
EMNLP 2025 Findings, November 2025
vol. , pp.
DOI: 10.18653/v1/2025.findings-emnlp.1103
URL: https://aclanthology.org/2025.findings-emnlp.1103/
Open Access:

Kudzai Sauka, Yitong Wang, Frederik Situmeang, “Anthropomorphism and transparency interplay on consumer behaviour in generative AI-driven marketing communication,”
Journal of Consumer Marketing, May 2025
vol. Volume 42 Issue 4, pp.
DOI: https://doi.org/10.1108/JCM-04-2024-6806
URL: https://www.emerald.com/insight/content/doi/10.1108/jcm-04-2024-6806/full/html
Open Access: Yes

Kudzai Sauka, Youssef Saou, Frederik Situmeang, Monika Kackovic, “A Nexus of Explainability and Anthropomorphism in AI-Chatbots,”
Communications in Computer and Information Science , October 2025
vol. CCIS,volume 2576, pp. pp 115–138
DOI: https://doi.org/10.1007/978-3-032-08317-3_6
URL: https://rdcu.be/eKD1E
Open Access: Yes

Ali Satvaty, Anna Visman, Dan Seidel, Suzan Verberne, Fatih Turkmen, “Memorization is Language-Sensitive: Analyzing Memorization and Inference Risks of LLMs in a Multilingual Setting,”
L2M2 Workshop at ACL, August 2025
vol. , pp.
DOI: No DOI
URL: No URL
Open Access:

Paraskeva, Andreas and van Duijn, Max Johannes and de Rijke, Maarten and Verberne, Suzan and van Rijn, Jan Nicolaas, “Data Efficient Pre-training for Language Models: An Empirical Study of Compute Efficiency and Linguistic Competence,”
ICLR 2025 Workshop on Navigating and Addressing Data Problems for Foundation Models, 2025
vol. , pp.
DOI: https://openreview.net/pdf?id=putz3ezpMa
URL: https://openreview.net/forum?id=putz3ezpMa
Open Access:

Xinyi Chen, Yifei Yuan, Jiaang Li, Serge Belongie, Maarten de Rijke, Anders Søgaard, “What if Othello-Playing Language Models Could See?,”
ENMLP 2025, 2025
vol. , pp.
DOI: No DOI
URL: https://aclanthology.org/2025.findings-emnlp.673/
Open Access:

Arian Askari, Roxana Petcu, Chuan Meng, Mohammad Aliannejadi, Amin Abolghasemi, Evangelos Kanoulas, Suzan Verberne, “SOLID: Self-seeding and Multi-intent Self-instructing LLMs for Generating Intent-aware Information-Seeking Dialogs,”
https://aclanthology.org/2025.findings-naacl.357/, 2025
vol. , pp.
DOI: 10.18653/v1/2025.findings-naacl.357
URL: https://aclanthology.org/2025.findings-naacl.357.pdf
Open Access: Yes

Jakub Podolak, Leon Perić, Mina Janićijević, Roxana Petcu, “Beyond Reproducibility: Advancing Zero-shot LLM Reranking Efficiency with Setwise Insertion,”
SIGIR 2025, 2025
vol. , pp.
DOI: No DOI
URL: https://dl.acm.org/doi/abs/10.1145/3726302.3730323
Open Access:

Oliver Savolainen, Dur e Najaf Amjad, Roxana Petcu, “Interpreting Multilingual and Document-Length Sensitive Relevance Computations in Neural Retrieval Models through Axiomatic Causal Interventions,”
SIGIR 2025, 2025
vol. , pp.
DOI: No DOI
URL: https://dl.acm.org/doi/pdf/10.1145/3726302.3730327
Open Access:

Cile van Marken, Roxana Petcu, “Reproducing and Extending Causal Insights Into Term Frequency Computation in Neural Rankers,”
SIGIR-AP 2025, 2025
vol. , pp. 189 – 198
DOI: https://doi.org/10.1145/3767695.3769507
URL: https://dl.acm.org/doi/10.1145/3767695.3769507
Open Access: Yes

Roxana Petcu, Samarth Bhargav, Maarten de Rijke, Evangelos Kanoulas, “A comprehensive taxonomy of negation for nlp and neural retrievers,”
EMNLP 2025, 2025
vol. , pp. 15511–15533
DOI: 10.18653/v1/2025.findings-emnlp.839
URL: https://aclanthology.org/anthology-files/anthology-files/pdf/findings/2025.findings-emnlp.839.pdf
Open Access: Yes

Yongkang Li, Panagiotis Eustratiadis, Simon Lupart, and Evangelos Kanoulas. 2025. , “Unsupervised Corpus Poisoning Attacks in Continuous Space for Dense Retrieval.,”
SIGIR 2025, 2025
vol. , pp. 2452 – 2462
DOI: https://doi.org/10.1145/3726302.3730110
URL: https://dl.acm.org/doi/10.1145/3726302.3730110
Open Access: Yes

Li, Y., Eustratiadis, P., Kanoulas, E., “Reproducing HotFlip for Corpus Poisoning Attacks in Dense Retrieval.,”
ECIR 2025, 2025
vol. , pp. 95–111
DOI: https://doi.org/10.1007/978-3-031-88717-8_8
URL: https://link.springer.com/chapter/10.1007/978-3-031-88717-8_8
Open Access: yes

Antonios Tragoudaras, Theofanis Aslanidis, Emmanouil Georgios Lionis, Marina Orozco González, and Panagiotis Eustratiadis., “Information Leakage of Sentence Embeddings via Generative Embedding Inversion Attacks,”
SIGIR 2025, 2025
vol. , pp. 3234 – 3243
DOI: https://doi.org/10.1145/3726302.3730303
URL: https://dl.acm.org/doi/10.1145/3726302.3730303
Open Access: yes

Sidiropoulos, Georgios, Samarth Bhargav, Panagiotis Eustratiadis, and Evangelos Kanoulas., “Multivariate dense retrieval: A reproducibility study under a memory-limited setup.,”
TMLR, 2025
vol. , pp.
DOI: No DOI
URL: https://openreview.net/forum?id=wF3ZtSlOcT
Open Access:

Kanoulas, E., Eustratiadis, P., Sanderson, M., & Callan, J, “Overview of the TREC 2025 Million Large Language Models Track,”
NIST TREC, 2025
vol. , pp.
DOI: No DOI
URL: No URL
Open Access: