Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Thinking Like a Scientist? A Structural Study of LLM-Generated Research Methods
Francesca Carlon, Brecht Verbeken, Vincent Ginis +1
Large Language Models (LLMs) are increasingly used to guide research methodology, yet their default methodological tendencies under minimal prompting remain unclear. Here, we promp…
cs.CL2025
Compromising Honesty and Harmlessness in Language Models via Deception Attacks
Laurène Vaugrante, Francesca Carlon, Maluna Menke +1
Recent research on large language models (LLMs) has demonstrated their ability to understand and employ deceptive behavior, even without explicit prompting. However, such behavior…