BAS aggregates utility from an answer-or-abstain model across risk thresholds and is uniquely maximized by truthful confidence estimates.
The llama 3 herd of models
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
SAM 3 introduces promptable concept segmentation that doubles accuracy of prior systems on images and videos while improving standard SAM segmentation performance.
ZeroSiam is an asymmetric architecture using a learnable predictor and stop-gradient that prevents collapse in test-time entropy minimization while also regularizing biased signals for improved performance.
TPCs allow term-by-term progressive polynomial evaluation on LLM activations for flexible safety monitoring that supports both stronger guardrails and low-cost adaptive cascades.
PROF curates RL training data via PRM-ORM consistency to improve both final-answer accuracy and intermediate reasoning quality while reducing reliance on strong process reward models.
citing papers explorer
-
BAS: A Decision-Theoretic Approach to Evaluating Large Language Model Confidence
BAS aggregates utility from an answer-or-abstain model across risk thresholds and is uniquely maximized by truthful confidence estimates.
-
SAM 3: Segment Anything with Concepts
SAM 3 introduces promptable concept segmentation that doubles accuracy of prior systems on images and videos while improving standard SAM segmentation performance.
-
ZeroSiam: An Efficient Asymmetry for Test-Time Entropy Optimization without Collapse
ZeroSiam is an asymmetric architecture using a learnable predictor and stop-gradient that prevents collapse in test-time entropy minimization while also regularizing biased signals for improved performance.
-
Beyond Linear Probes: Dynamic Safety Monitoring for Language Models
TPCs allow term-by-term progressive polynomial evaluation on LLM activations for flexible safety monitoring that supports both stronger guardrails and low-cost adaptive cascades.
-
Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training
PROF curates RL training data via PRM-ORM consistency to improve both final-answer accuracy and intermediate reasoning quality while reducing reliance on strong process reward models.