Sub-network Laplace approximations always underestimate full-model predictive variance, and two new gradient-based and greedy selection rules provide theoretically grounded improvements.
Efficient exploration for llms
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
other 1
citation-polarity summary
polarities
unclear 2representative citing papers
UG-TTT adds epistemic uncertainty measured by adapter disagreement as an exploration bonus in RL for LLMs, raising maximum reward and diversity on scientific discovery benchmarks.
HyRe personalizes reward models at test time by reweighting an ensemble of heads trained on aggregate preferences, using few target examples to outperform uniform averaging and prior methods on RewardBench and 32 tasks.
citing papers explorer
-
Optimality of Sub-network Laplace Approximations: New Results and Methods
Sub-network Laplace approximations always underestimate full-model predictive variance, and two new gradient-based and greedy selection rules provide theoretically grounded improvements.
-
Epistemic Uncertainty for Test-Time Discovery
UG-TTT adds epistemic uncertainty measured by adapter disagreement as an exploration bonus in RL for LLMs, raising maximum reward and diversity on scientific discovery benchmarks.
-
Test-Time Alignment via Hypothesis Reweighting
HyRe personalizes reward models at test time by reweighting an ensemble of heads trained on aggregate preferences, using few target examples to outperform uniform averaging and prior methods on RewardBench and 32 tasks.