Pith. sign in

REVIEW 14 cited by

Estimating LLM Uncertainty with Evidence

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2502.00290 v5 pith:H7IOBD4N submitted 2025-02-01 cs.CL cs.AI

Estimating LLM Uncertainty with Evidence

classification cs.CL cs.AI
keywords uncertaintytokenevidencellmslogtokureliabilityestimatingestimation
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Over the past few years, Large Language Models (LLMs) have developed rapidly and are widely applied in various domains. However, LLMs face the issue of hallucinations, generating responses that may be unreliable when the models lack relevant knowledge. To be aware of potential hallucinations, uncertainty estimation methods have been introduced, and most of them have confirmed that reliability lies in critical tokens. However, probability-based methods perform poorly in identifying token reliability, limiting their practical utility. In this paper, we reveal that the probability-based method fails to estimate token reliability due to the loss of evidence strength information which is accumulated in the training stage. Therefore, we present Logits-induced token uncertainty (LogTokU), a framework for estimating decoupled token uncertainty in LLMs, enabling real-time uncertainty estimation without requiring multiple sampling processes. We employ evidence modeling to implement LogTokU and use the estimated uncertainty to guide downstream tasks. The experimental results demonstrate that LogTokU has significant effectiveness and promise.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 14 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. LLM Doesn't Know What It Doesn't Know: Detecting Epistemic Blind Spots via Cross-Model Attribution Divergence on Clinical Tabular Data

    cs.AI 2026-06 unverdicted novelty 7.0

    LLMs exhibit epistemically vacuous confidence on clinical tabular data, but cross-model attribution divergence with XGBoost enables a calibrator that reduces expected calibration error from 0.254 to 0.080.

  2. Quantifying Consistency in LLM Logical Reasoning via Structural Uncertainty

    cs.AI 2026-06 unverdicted novelty 7.0

    Structural uncertainty from self-preference-induced rankings of LLM reasoning paths complements answer dispersion for identifying unreliable instances on logical tasks while collapsing on factual retrieval.

  3. Can You Trust the Confidence? ConfBench for Vision-Language Models on Document Extraction

    cs.AI 2026-08 conditional novelty 6.0

    Vision-language models vary widely in how trustworthy their confidence scores are on document extraction, with stronger models and OCR-plus-image input helping most, as measured on the new ConfBench benchmark.

  4. Uncertainty Quantification for Flow-Based Vision-Language-Action Models

    cs.RO 2026-06 unverdicted novelty 6.0

    Velocity-field disagreement yields calibrated epistemic uncertainty for flow-based VLAs, supporting failure detection and uncertainty-guided active fine-tuning that cuts required samples by ≥22%.

  5. Integrating Local and Global Entropy for Uncertainty Quantification in LLMs

    cs.LG 2026-06 unverdicted novelty 6.0

    GLU is a single-pass unsupervised uncertainty score for LLMs formed by multiplying global hidden-state geometric entropy with local token entropy, shown to match or beat baselines on three model families and six bench...

  6. VIHD: Visual Intervention-based Hallucination Detection for Medical Visual Question Answering

    cs.CV 2026-05 unverdicted novelty 6.0

    VIHD detects hallucinations in medical MLLMs by identifying visually dominant decoder layers via probing and applying visual token masking to calibrate semantic entropy as a detection signal.

  7. Towards Generation-Efficient Uncertainty Estimation in Large Language Models

    cs.LG 2026-05 unverdicted novelty 6.0

    Uncertainty estimation for LLM hallucinations can be done effectively with partial generations or input-only predictors, reducing the need for full autoregressive sampling.

  8. Estimating the Black-box LLM Uncertainty with Distribution-Aligned Adversarial Distillation

    cs.CL 2026-05 unverdicted novelty 6.0

    DisAAD trains a 1%-sized proxy model via adversarial distillation to quantify uncertainty in black-box LLMs by aligning with their output distributions.

  9. Complementing Self-Consistency with Cross-Model Disagreement for Uncertainty Quantification

    cs.AI 2026-04 unverdicted novelty 6.0

    Cross-model semantic disagreement adds an epistemic uncertainty term that improves total uncertainty estimation over self-consistency alone, helping flag confident errors in LLMs.

  10. INSIGHT: INference-time Sequence Introspection for Generating Help Triggers in Vision-Language-Action Models

    cs.RO 2025-10 conditional novelty 6.0

    Token-level uncertainty sequences from a VLA policy, classified by a small transformer, predict when a robot should request human help better than static uncertainty scores.

  11. VIHD: Visual Intervention-based Hallucination Detection for Medical Visual Question Answering

    cs.CV 2026-05 unverdicted novelty 5.0

    VIHD detects hallucinations in medical MLLMs via visual dependency probing, token masking intervention, and calibrated semantic entropy on VQA benchmarks.

  12. From Accuracy to Auditability: A Survey of Determinism in Financial AI Systems

    cs.AI 2026-05 unverdicted novelty 5.0

    Financial AI systems using tabular models, graph networks, and LLM agents exhibit nondeterminism that undermines reproducibility, quantified via experiments on public datasets and addressed by a proposed layered evalu...

  13. Uncertainty-Aware Exploratory Direct Preference Optimization for Multimodal Large Language Models

    cs.LG 2026-05 unverdicted novelty 5.0

    UE-DPO quantifies epistemic uncertainty from grounding failures to direct more learning pressure on hard visual tokens in preferred samples while easing penalties on dispreferred ones.

  14. WebUncertainty: Dual-Level Uncertainty Driven Planning and Reasoning For Autonomous Web Agent

    cs.AI 2026-04 unverdicted novelty 4.0

    WebUncertainty improves web agent performance on benchmarks by adaptively selecting planning modes based on task uncertainty and using confidence-induced action uncertainty in MCTS to quantify aleatoric and epistemic ...