6 papers · 1 filter
GAMBIT: A Three-Mode Benchmark for Adversarial Robustness in Multi-Agent LLM Collectives
Alexandre Le Mercier, Chris Develder, Thomas Demeester
In multi-agent systems (MAS), a single deceptive agent can nullify all gains of an agentic AI collective and evade deployed defenses. However, existing adversarial studies on MAS t…
CLASP: Defending Hybrid Large Language Models Against Hidden State Poisoning Attacks
Alexandre Le Mercier, Thomas Demeester, Chris Develder
State space models (SSMs) like Mamba have gained significant traction as efficient alternatives to Transformers, achieving linear complexity while maintaining competitive performan…
Hidden State Poisoning Attacks against Mamba-based Language Models
Alexandre Le Mercier, Chris Develder, Thomas Demeester
State space models (SSMs) like Mamba offer efficient alternatives to Transformer-based language models, with linear time complexity. Yet, their adversarial robustness remains criti…
Single- vs. Dual-Prompt Dialogue Generation with LLMs for Job Interviews in Human Resources
Joachim De Baer, A. Seza DoÄruöz, Thomas Demeester +1
Optimizing language models for use in conversational agents requires large quantities of example dialogues. Increasingly, these dialogues are synthetically generated by using power…
Efficient Text Encoders for Labor Market Analysis
Jens-Joris Decorte, Jeroen Van Hautte, Chris Develder +1
Labor market analysis relies on extracting insights from job advertisements, which provide valuable yet unstructured information on job titles and corresponding skill requirements.…
SkillMatch: Evaluating Self-supervised Learning of Skill Relatedness
Jens-Joris Decorte, Jeroen Van Hautte, Thomas Demeester +1
Accurately modeling the relationships between skills is a crucial part of human resources processes such as recruitment and employee development. Yet, no benchmarks exist to evalua…