2 citations · 2 across the 4 of their papers we have counts for
Showing 2025Show all
2 papers · 1 filter
cs.AI2025
Don't Think Twice! Over-Reasoning Impairs Confidence Calibration
Romain Lacombe, Kerrie Wu, Eddie Dilworth
Large Language Models deployed as question answering tools require robust calibration to avoid overconfidence. We systematically evaluate how reasoning capabilities and budget affe…
q-bio.BM2025
Non-Canonical Crosslinks Confound Evolutionary Protein Structure Models
Romain Lacombe
Evolution-based protein structure prediction models have achieved breakthrough success in recent years. However, they struggle to generalize beyond evolutionary priors and on seque…