Tag
This paper proposes Logical Graph Uncertainty (LGU), a framework that models implication and incompatibility among answers to improve uncertainty estimation in LLMs, outperforming semantic entropy baselines by up to 7.1% AUROC and 3.5% AUARC across benchmarks.
This paper proposes diversity-oriented fine-tuning strategies to improve uncertainty-based hallucination detection in LLMs by encouraging varied generations, making hallucinations more detectable via semantic entropy.
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.
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.
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.