Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Depth-Wise Activation Steering for Honest Language Models
Gracjan Góral, Marysia Winkels, Steven Basart
Large language models sometimes assert falsehoods despite internally representing the correct answer, failures of honesty rather than accuracy, which undermines auditability and sa…
cs.LG2024
What Matters in Hierarchical Search for Combinatorial Reasoning Problems?
Michał Zawalski, Gracjan Góral, Michał Tyrolski +5
Efficiently tackling combinatorial reasoning problems, particularly the notorious NP-hard tasks, remains a significant challenge for AI research. Recent efforts have sought to enha…