A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
This paper investigates whether large reasoning models (LRMs) rely on parametric knowledge or external retrieval for answer attribution, revealing a tendency to favor reasoning over retrieval.
Philipp Alexander Kreer, Wilson Wu, Maxwell Adam, et al.
Proposes Bayesian influence functions (BIF) that replace Hessian inversion with loss landscape statistics from stochastic-gradient MCMC for scalable data attribution in large neural networks.
Unknown
This paper investigates why smaller open-source long-context language models underperform proprietary ones in multi-hop reasoning with attributions.