15 citations · 33 across the 4 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.AI2026
Opening the Box Changes the Cat: LLMs Detect Chain-of-Thought Monitoring - What now?
Amir Jalilifard, Marcos Medeiros Raimundo, Anderson Rocha
Chain-of-thought (CoT) reasoning allows large language models (LLMs) to generate intermediate reasoning traces in natural language while solving complex tasks. These traces can sup…
cs.LG2026
PCE: Model-Agnostic Plausible Pareto-Optimal Counterfactual Explanations
Arthur Hendricks Mendes de Oliveira, Giovani Valdrighi, Marcos Medeiros Raimundo
The increasing use of machine learning algorithms in social applications has raised concerns about fairness and transparency, leading to the development of counterfactual explanati…