# DRIFT: Detecting Representational Inconsistencies for Factual Truthfulness

arXiv: https://arxiv.org/abs/2601.14210 · HTML: https://mlsanity.com/paper/2601.14210/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 18 references that are in the map.
- First posted on arXiv 20 Jan 2026.

## Builds on (most cited first, 10 of 10)

- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation](https://mlsanity.com/paper/2302.09664/) (2023)
- [INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection](https://mlsanity.com/paper/2402.03744/) (2024)
- [Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models](https://mlsanity.com/paper/2305.19187/) (2023)
- [Out-of-Distribution Detection and Selective Generation for Conditional Language Models](https://mlsanity.com/paper/2209.15558/) (2022)
- [Truth is Universal: Robust Detection of Lies in LLMs](https://mlsanity.com/paper/2407.12831/) (2024)
- [The Geometry of Truth: Layer-wise Semantic Dynamics for Hallucination Detection in Large Language Models](https://mlsanity.com/paper/2510.04933/) (2025)
- [Annotation-Efficient Universal Honesty Alignment](https://mlsanity.com/paper/2510.17509/) (2025)

## Built on by (most cited first, 4 of 4)

- [Reasoning Denoiser: Denoising Reasoning Traces for Hallucination Detection in Large Reasoning Models](https://mlsanity.com/paper/2607.22098/) (2026)
- [DeMTS: Denoising Trajectories as Multivariate Time Series for Hallucination Detection in Diffusion Language Models](https://mlsanity.com/paper/2608.14632/) (2026)
- [The Hallucination Signal Is a Mean Shift: Why Simple Probes Suffice](https://mlsanity.com/paper/2608.28930/) (2026)
- [SingProbe Technical Report](https://mlsanity.com/paper/2608.30703/) (2026)

## Abstract (arXiv)

LLMs often produce fluent but incorrect answers, yet detecting such hallucinations typically requires multiple sampling passes or post-hoc verification, adding significant latency and cost. We hypothesize that intermediate layers encode confidence signals that are lost in the final output layer, and propose a lightweight probe to read these signals directly from hidden states. The probe adds less than 0.1% computational overhead and can run fully in parallel with generation, enabling hallucination detection before the answer is produced. Building on this, we develop an LLM router that answers confident queries immediately while delegating uncertain ones to stronger models. Despite its simplicity, our method achieves SOTA AUROC on 10 out of 12 settings across four QA benchmarks and three LLM families, with gains of up to 13 points over prior methods, and generalizes across dataset shifts without retraining.