semantic-entropy

Tag

Cards List
#semantic-entropy

SAGE: Answer-Conditioned Uncertainty Targets for Verbal Uncertainty Alignment

arXiv cs.CL · 19h ago Cached

SAGE proposes a group-level uncertainty target that constructs an answer-conditioned uncertainty geometry over sampled responses to improve verbal uncertainty alignment in LLMs, and introduces GUPO for training. Experiments across reasoning tasks show improved uncertainty ranking and reduced overconfidence.

0 favorites 0 likes
#semantic-entropy

When Does Delegation Beat Majority? A Delegation-Based Aggregator for Multi-Sample LLM Inference

arXiv cs.AI · 2d ago Cached

The paper proposes a delegation-based aggregator called Propagational Proxy Voting (PPV) that uses letter entropy and reasoning geometry to improve over majority voting for multi-sample LLM inference, achieving gains on MMLU-Pro without requiring gold labels or auxiliary training.

0 favorites 0 likes
#semantic-entropy

Mind the Unseen Mass: Unmasking LLM Hallucinations via Soft-Hybrid Alphabet Estimation

arXiv cs.CL · 2026-04-22 Cached

Researchers introduce SHADE, a hybrid estimator that combines Good-Turing coverage with graph-spectral cues to quantify semantic uncertainty and detect LLM hallucinations when only a few black-box samples are available.

0 favorites 0 likes
← Back to home

Submit Feedback