AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Estimating Semantic Alphabet Size for LLM Uncertainty Quantification

Lucas Hurley McCabe, Rimon Melamed, Thomas Hartvigsen, H Howie Huang

ICLR 2026 · Large language models › Language, safety and interpretability · approach: Uncertainty quantification for LLMs · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
adjust DSE for sample coverage using hybrid alphabet size estimatordiscrete semantic entropy · HotpotQA, SQuAD 2.0, POTATO, BioASQ (n=10)MSE vs SE*: BioASQ Gemma-2: 1.64 -> 0.78Improved
use hybrid instead of Good-Turing Chao-Shen coverage adjustmentDSE · SQuAD 2.0 Mistral-v0.3MSE vs SE*: 0.86 -> 0.68Improved
use hybrid estimator on Gemma-3 (12B)DSE · POTATOentropy bias: slightly overshoots SE*Mixed
use hybrid DSE rather than other explicit SE estimators for incorrectness detectionDSE · HotpotQA, SQuAD, BioASQ, POTATOAUROC rank (Bradley-Terry): highest rank among explicit SE estimatorsImproved
use semantic alphabet size estimators (Hybrid, U_EigV) aloneLLM uncertainty · incorrectness detectionBradley-Terry rank: rank CI [1, 4] and [1, 3]Improved
use white-box SE (response probabilities) vs plugin DSESE · incorrectness detectionAUROC: qualitatively similarNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy