CRIL - Centre de Recherche en Informatique de Lens


Nov 15, 2024 Video [KR'24] Collective Satisfaction Semantics for Opinion Based Argumentation Paper: Juliete Rossie, Jérôme Delobelle, Sébastien Konieczny, Clément Lens, Srdjan Vesic. “Collective Satisfaction Semantics for Opinion Based Argumentation”. In Proceedings of the 21st International Conference on Principles of Knowledge Representation and Reasoning — Main Track. Pages 631–641. (2024). https://doi.org/10.24963/kr.2024/59 Abstract: Voting on arguments in a debate is a natural approach for reaching a consensual decision. Despite this, there are few formal methods of abstract argumentation dealing with the use of votes in the process of selecting accepted arguments.
Oct 19, 2024 Demonstration RefineLM: Mitigating Language Model Stereotypes via Reinforcement Learning REFINE-LM is a novel approach to mitigate stereotypical biases in large language models (LLMs) using reinforcement learning. Unlike existing methods that require extensive fine-tuning or manual annotations, REFINE-LM debiases models by acting on the word probability distributions, reducing biases related to gender, ethnicity, religion, and nationality without impacting performance of the model. It is efficient, scalable, and applicable to various LLMs, providing a versatile solution for reducing harmful stereotypes in NLP applications.
Jul 20, 2023 Video The Silent (R)evolution of SAT This is a video promoting an article of the same name by Johannes K. Fichte, Daniel Le Berre, Markus Hecher, and Stefan Szeider published in Communications of the ACM, June 2023, Vol. 66 No. 6, Pages 64-72 10.1145/3560469. The propositional satisfiability problem (SAT) was the first to be shown NP-complete by Cook and Levin. SAT remained the embodiment of theoretical worst-case hardness. However, in stark contrast to its theoretical hardness, SAT has emerged as a central target problem for efficiently solving a wide variety of computational problems.

Nov 15, 2024 Video [KR'24] Collective Satisfaction Semantics for Opinion Based Argumentation

Paper: Juliete Rossie, Jérôme Delobelle, Sébastien Konieczny, Clément Lens, Srdjan Vesic. “Collective Satisfaction Semantics for Opinion Based Argumentation”. In Proceedings of the 21st International Conference on Principles of Knowledge Representation and Reasoning — Main Track. Pages 631–641. (2024). https://doi.org/10.24963/kr.2024/59 Abstract: Voting on arguments in a debate is a natural approach for reaching a consensual decision. Despite this, there are few formal methods of abstract argumentation dealing with the use of votes in the process of selecting accepted arguments.

Oct 19, 2024 Demonstration RefineLM: Mitigating Language Model Stereotypes via Reinforcement Learning

REFINE-LM is a novel approach to mitigate stereotypical biases in large language models (LLMs) using reinforcement learning. Unlike existing methods that require extensive fine-tuning or manual annotations, REFINE-LM debiases models by acting on the word probability distributions, reducing biases related to gender, ethnicity, religion, and nationality without impacting performance of the model. It is efficient, scalable, and applicable to various LLMs, providing a versatile solution for reducing harmful stereotypes in NLP applications.

Jul 20, 2023 Video The Silent (R)evolution of SAT

This is a video promoting an article of the same name by Johannes K. Fichte, Daniel Le Berre, Markus Hecher, and Stefan Szeider published in Communications of the ACM, June 2023, Vol. 66 No. 6, Pages 64-72 10.1145/3560469. The propositional satisfiability problem (SAT) was the first to be shown NP-complete by Cook and Levin. SAT remained the embodiment of theoretical worst-case hardness. However, in stark contrast to its theoretical hardness, SAT has emerged as a central target problem for efficiently solving a wide variety of computational problems.

Scientific mediation

Contact Us

Our Addresses