# Between the Layers Lies the Truth: Uncertainty Estimation in LLMs Using Intra-Layer Local Information Scores

arXiv: https://arxiv.org/abs/2603.22299 · HTML: https://mlsanity.com/paper/2603.22299/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 43 references that are in the map.
- First posted on arXiv 17 Mar 2026.

## Builds on (most cited first, 26 of 26)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs](https://mlsanity.com/paper/2503.01743/) (2025)
- [Opening the Black Box of Deep Neural Networks via Information](https://mlsanity.com/paper/1703.00810/) (2017)
- [Analysis Methods in Neural Language Processing: A Survey](https://mlsanity.com/paper/1812.08951/) (2018)
- [LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations](https://mlsanity.com/paper/2410.02707/) (2024)
- [Emergence of Invariance and Disentanglement in Deep Representations](https://mlsanity.com/paper/1706.01350/) (2017)
- [What Large Language Models Know and What People Think They Know](https://mlsanity.com/paper/2401.13835/) (2024)
- [Cognitive Dissonance: Why Do Language Model Outputs Disagree with Internal Representations of Truthfulness?](https://mlsanity.com/paper/2312.03729/) (2023)
- [Estimating Knowledge in Large Language Models Without Generating a Single Token](https://mlsanity.com/paper/2406.12673/) (2024)
- [Faster Minimum Bayes Risk Decoding with Confidence-based Pruning](https://mlsanity.com/paper/2311.14919/) (2023)
- [On Uncertainty Calibration and Selective Generation in Probabilistic Neural Summarization: A Benchmark Study](https://mlsanity.com/paper/2304.08653/) (2023)
- [Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT](https://mlsanity.com/paper/2510.00296/) (2025)
- [Out-of-Distribution Detection by Leveraging Between-Layer Transformation Smoothness](https://mlsanity.com/paper/2310.02832/) (2023)
- [HeRo: RoBERTa and Longformer Hebrew Language Models](https://mlsanity.com/paper/2304.11077/) (2023)
- [Uncertainty-Aware Decoding with Minimum Bayes Risk](https://mlsanity.com/paper/2503.05318/) (2025)
- [Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning](https://mlsanity.com/paper/2411.02344/) (2024)

## Abstract (arXiv)

Large language models (LLMs) are often confidently wrong, making reliable uncertainty estimation (UE) essential. Output-based heuristics are cheap but brittle, while probing internal representations is effective yet high-dimensional and hard to transfer. We propose a compact, per-instance UE method that scores cross-layer agreement patterns in internal representations using a single forward pass. Across three models, our method matches probing in-distribution, with mean diagonal differences of at most -1.8 AUPRC percentage points and +4.9 Brier score points. Under cross-dataset transfer, it consistently outperforms probing, achieving off-diagonal gains up to +2.86 AUPRC and +21.02 Brier points. Under 4-bit weight-only quantization, it remains robust, improving over probing by +1.94 AUPRC points and +5.33 Brier points on average. Beyond performance, examining specific layer--layer interactions reveals differences in how disparate models encode uncertainty. Altogether, our UE method offers a lightweight, compact means to capture transferable uncertainty in LLMs.