Mixture-of-Expert Blocks Contain Strong Hallucination Detection Signals

Joao Fonseca; Rodrigo Rodrigues; Paolo Romano

cs.AIAug 18, 2026

Mixture-of-Expert Blocks Contain Strong Hallucination Detection Signals

Authors: Joao Fonseca, Rodrigo Rodrigues, Paolo Romano

Organizations: INESC-ID, Rua Alves Redol, 9, Lisbon, 1000-029 Portugal · Instituto Superior Técnico

Abstract

Despite their widespread use, Large Language Models (LLMs) remain limited by a fundamental problem: the generation of plausible but false content, known as hallucinations. Most existing detection methods operate at the answer or sentence level, yet per-token detection is essential for localizing hallucinated spans and enabling fine-grained interventions. In this paper, we explore the use of the Mixture-of-Experts (MoE) paradigm to address this gap. In MoE architectures, a single forward pass activates a sparse subset of experts (i.e., distinct feedforward networks per layer) via a routing mechanism, producing internal signals (e.g., router entropy, expert disagreement, and expert usage patterns) that are unavailable in dense architectures and have not been previously exploited for hallucination detection. To this end, we introduce InnerExpert, the first method to leverage these MoE-specific signals for per-token hallucination detection. InnerExpert combines routing-level and standard transformer signals into compact per-token feature vectors, classified by a lightweight detector trained on labels produced by an LLM-as-a-judge pipeline, which enables continuous model updates without manual annotation. Our results show that InnerExpert outperforms existing methods across five datasets and two MoE architectures, achieving up to 0.91 answer-level and 0.76 token-level AUROC, while requiring only a single forward pass.

Figures & tables

Figure 1: Overview of InnerExpert . A single forward pass through the MoE model exposes internal signals ( i.e., router distributions, per-expert hidden states, and expert usage patterns) which are combined into per-token hallucination scores.

	FQA	NQO	RTQA	SQuAD	TQA	Rank	Avg
Gemma-4-26B
IE (LR)	0.705	0.635	0.759	0.785	0.740	3.0	0.725
IE (MLP)	0.710	0.662	0.756	0.806	0.715	2.6	0.730
IE (RF)	0.638	0.651	0.749	0.788	0.724	3.6	0.710
IE (Transf.)	0.656	0.619	0.716	0.760	0.722	4.6	0.694
IE (XGB)	0.711	0.678	0.805	0.802	0.767	1.2	0.753

Table 1: Token-level results (AUROC) across datasets and host models.

	FQA	NQO	RTQA	SQuAD	TQA	Rank	Avg
Gemma-4-26B
HaluNet	0.836	0.835	0.937	0.945	0.952	3.2	0.901
IE (LR)	0.847	0.790	0.927	0.933	0.963	3.8	0.892
IE (MLP)	0.866	0.780	0.939	0.943	0.952	3.0	0.896
IE (RF)	0.752	0.832	0.870	0.919	0.937	5.8	0.862
IE (Transf.)	0.813	0.854	0.902	0.883	0.947	5.0	0.880

Table 2: Answer-level results (AUROC) across datasets and host models.

Figure 2: Inference time (per 100 tokens) vs. answer-level AUROC (averaged across five evaluation datasets) for each detection method, measured on 50 RealTimeQA questions per host model. The gray, dashed line represents the pareto frontier.

	OLMoE-1B-7B		Gemma-4-26B
Method	Answer	Token	Answer	Token
Inv. Herfindahl	0.685	0.675	0.784	0.602
Exp. Entropy	0.613	0.574	0.884	0.591
Exp. Gini	0.599	0.561	0.824	0.626
Expert Hidden	0.693	0.640	0.722	0.466
Expert Similarity	0.397	0.442	0.717	0.437

Table 3: Average AUROC for individual MoE signals, baselines, InnerExpert (XGB). Each value is averaged across all five evaluation datasets per host model. Answer-level scores use the best aggregation per method. Methods without a token-level counterpart are marked “—”.

Appendix figures & tables12 assets

Supplementary material from the paper’s appendix.

Appendix

Signal	Notation	Category	Description	Per-token dim.
Hidden state score	$\phi^{\mathrm{hid}}_{t,l}$	Standard	Mean log-singular-value of hidden state covariance	$L$
Attention score	$\phi^{\mathrm{att}}_{t,l,h}$	Standard	Log-cumulative sum of attention kernel diagonal	$LH$
Router entropy	$\phi^{\mathrm{rout}}_{t,l}$	MoE	Shannon entropy of gating distribution	$L$
Expert hidden score	$\phi^{\mathrm{exp\text{-}hid}}_{t,l}$	MoE	Routing-weighted hidden score of selected experts	$L$
Expert similarity	$\phi^{\mathrm{sim}}_{t,l}$	MoE	Routing-weighted pairwise cosine similarity of experts	$L$
Expert usage	$\mathbf{u}_{t,l}$	MoE	Cumulative routing-weighted usage distribution	$LN$

Appendix

Table 4: Summary of signals extracted by InnerExpert . Each signal is computed cumulatively over the generated prefix up to position

t

, yielding a per-token value. The total per-token feature dimensionality is the sum of all signal dimensions.

L

= number of MoE layers,

H

= number of attention heads,

N

= number of experts.

Model	$L$	$H$	$N$	$\|\Phi_{t}\|$	Params	Act.
OLMoE-1B-7B-0924-Instruct	16	16	64	1 360	$\sim$ 7B	$\sim$ 1B
Gemma-4-26B-A4B-it	30	16	129	4 470	$\sim$ 26B	$\sim$ 4B

Appendix

Table 5: Feature dimensionality for each host model.

L

: number of layers,

H

: number of attention heads,

N

: number of experts,

|\Phi_{t}|

: per-token feature dimensionality, Params: total model parameters, Act.: number of active parameters per token.

Dataset	N	Base	Eviden.	Halluc.	Grounded	Halluc. %	Ans.
Gemma-4-26B
SQuAD	400	200	200	172	228	43.0	17.1
TQA	399	199	200	194	205	48.6	19.2
NQO	400	200	200	233	167	58.2	16.0
FQA	400	200	200	226	174	56.5	13.3
RTQA	730	365	365	397	333	54.4	15.3

Appendix

Table 6: Dataset statistics for all evaluation datasets and host models. Labels are from the LLM-as-a-judge approach (GLM-5.1). “Ans.” is the average number of words in the generated answer.

Classifier	Hyperparameter	Grid
Logistic Regression	$C$	$\{0.01,\underline{0.1},1.0,$ $\textbf{10.0}\}$
Random Forest	n_estimators	$\{\underline{300},500,\textbf{1000}\}$
	max_depth	$\{3,6,\underline{\textbf{10}}\}$
	min_samples_leaf	$\{\underline{\textbf{1}},5\}$
XGBoost	n_estimators	$\{300,500,\underline{\textbf{1000}}\}$
	max_depth	$\{3,6,\underline{\textbf{10}}\}$

Appendix

Table 7: Hyperparameter grids for each classifier family. Hyperparameters used for OLMoE are boldfaced, the ones used for Gemma are underlined.

LLM-as-a-judge	Grounded	Hallucinated	Total
Human
Grounded	93	20	113
Hallucinated	7	80	87
Total	100	100	200
Weak heuristic	Grounded	Hallucinated	Total
Human

Appendix

Table 8: Confusion matrix between human annotations and LLM-as-a-judge labels/Weak labeling on the 200-sample validation set (pooled across both host models, 25 per

2{\times}2

contingency cell per model).

Confidence	OLMoE (%)	Gemma (%)
[0.0, 0.2[	36 (0.9 %)	220 (9.6 %)
[0.2, 0.4[	598 (15.5 %)	88 (3.8 %)
[0.4, 0.6[	230 (6.0 %)	33 (1.4 %)
[0.6, 0.8[	121 (3.1 %)	71 (3.1 %)
[0.8, 1.0]	2862 (74.4 %)	1877 (82.0 %)
Total	3847 ( 100 %)	2289 ( 100 %)

Appendix

Table 9: Confidence distribution, based on the weak labeling approach, for hallucinated labels (label=1)

Confidence	OLMoE (%)	Gemma (%)
[0.0, 0.2[	196 (24.9 %)	1764 (75.2 %)
[0.2, 0.4[	531 (67.5 %)	301 (12.8 %)
[0.4, 0.6[	44 (5.6 %)	50 (2.1 %)
[0.6, 0.8[	6 (0.8 %)	42 (1.8 %)
[0.8, 1.0]	10 (1.3 %)	189 (8.1 %)
Total	787 ( 100 %)	2346 ( 100 %)

Appendix

Table 10: Confidence distribution, based on the weak labeling approach, for grounded labels (label=0)

Condition	N	Halluc.	Grounded	Halluc. %
OLMoE-1B-7B
Base	2318	2312	6	99.7 %
Evidence	2318	1535	783	66.2 %
Overall	4636	3847	789	83.0 %
Gemma-4-26B
Base	2318	1980	338	85.4 %

Appendix

Table 11: Label distribution by model and evidence condition

	FQA	NQO	RTQA	SQuAD	TQA	Rank	Avg
Gemma-4-26B
IE (LR)	0.648	0.629	0.751	0.705	0.730	2.6	0.693
IE (MLP)	0.646	0.625	0.681	0.718	0.706	4.0	0.675
IE (RF)	0.571	0.575	0.756	0.706	0.774	3.2	0.676
IE (Transf.)	0.586	0.544	0.726	0.653	0.671	5.2	0.636
IE (XGB)	0.175	0.116	0.782	0.139	0.168	6.6	0.276

Appendix

Table 12: Token-level results (F1) across datasets and host models.

	FQA	NQO	RTQA	SQuAD	TQA	Rank	Avg
Gemma-4-26B
HaluNet	0.778	0.769	0.849	0.825	0.897	3.2	0.824
IE (LR)	0.790	0.763	0.849	0.873	0.904	2.4	0.836
IE (MLP)	0.828	0.780	0.876	0.890	0.868	2.0	0.849
IE (RF)	0.689	0.679	0.809	0.837	0.912	4.6	0.785
IE (Transf.)	0.751	0.787	0.840	0.760	0.884	3.6	0.804

Appendix

Table 13: Answer-level results (F1) across datasets and host models.

	OLMoE-1B-7B		Gemma-4-26B
Method	Time per 100 tok (s)	Peak GPU (GB)	Time per 100 tok (s)	Peak GPU (GB)
Vanilla	1.146	12.660	3.825	46.810
Logit Entropy	1.152	12.670	3.830	46.880
Perplexity	1.152	12.670	3.830	47.010
LC (att.)	1.198	12.680	3.965	46.880
LC (hid.)	1.246	12.670	4.133	46.830

Appendix

Table 14: Inference time (per 100 tokens) and peak GPU memory for each detection method, measured on 50 RealTimeQA questions per host model. InnerExpert times include MoE feature extraction (SVD-based hidden scores, attention scores, expert routing signals) as well as classifier inference.

	OLMoE-1B-7B		Gemma-4-26B
Method	Answer	Token	Answer	Token
Inv. Herfindahl	0.940	0.731	0.697	0.619
Exp. Entropy	0.881	0.639	0.748	0.671
Exp. Gini	0.869	0.597	0.745	0.671
Expert Hidden	0.945	0.698	0.707	0.667
Expert Similarity	0.945	0.634	0.740	0.523

Appendix

Table 15: Average F1 for individual MoE signals, baselines, InnerExpert (XGB). Each value is averaged across all five evaluation datasets per host model. Answer-level scores use the best aggregation per method. Methods without a token-level counterpart are marked “—”.

LLM Hallucination Detection

Large language model hallucination detection identifies unsupported, incorrect, or fabricated claims in model outputs and traces.

See all 208 papers

HalluSAE: Detecting Hallucinations in Large Language Models via Sparse Auto-Encoders
Apr 6, 2026Boshui Chen, Zhaoxin Fan, Ke Wang +5LLM Hallucination Detection
Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, School of Artificial Intelligence, Beihang University, Beijing, China. · State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China. · Beijing Academy of Blockchain and Edge Computing, Beijing, China. +1
LLM Hallucination Detection via Low-rank Multilinear Decomposition
Oct 26, 2026Devansh Sharma, Faizul Rakib Sayem, Shahana IbrahimLLM Hallucination Detection Hallucination in Language Models
Department of Electrical & Computer Engineering, University of Central Florida
External Observers May See More Clearly: Cross-Model Span-Level Hallucination Detection in Large Language Models via Hidden State Probing
Oct 1, 2026Kingshuk Gupta, Davide BuscaldiHallucination Detection LLM Hallucination Detection
LIX, École Polytechnique · School of Electrical and Electronic Engineering, Nanyang Technological University · LIPN, Sorbonne Paris Nord

Apr 6, 2026J/K move · Enter open · S save

HalluSAE: Detecting Hallucinations in Large Language Models via Sparse Auto-Encoders

Boshui Chen, Zhaoxin Fan, Ke Wang, Zhiying Leng+4

Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, School of Artificial Intelligence, Beihang University, Beijing, China. · State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China. · Beijing Academy of Blockchain and Edge Computing, Beijing, China.+1

LLM Hallucination Detection

Open paper AskPDF arXiv

Large Language Models (LLMs) are powerful and widely adopted, but their practical impact is limited by the well-known hallucination phenomenon. While recent hallucination detection methods have made notable progress, we find most of them overlook the dynamic nature and underlying mechanisms of it. To address this gap, we propose HalluSAE, a phase transition-inspired framework that models hallucination as a critical shift in the model's latent dynamics. By modeling the generation process as a trajectory through a potential energy landscape, HalluSAE identifies critical transition zones and attributes factual errors to specific high-energy sparse features. Our approach consists of three stages: (1) Potential Energy Empowered Phase Zone Localization via sparse autoencoders and a geometric potential energy metric; (2) Hallucination-related Sparse Feature Attribution using contrastive logit attribution; and (3) Probing-based Causal Hallucination Detection through linear probes on disentangled features. Extensive experiments on Gemma-2-9B demonstrate that HalluSAE achieves state-of-the-art hallucination detection performance.

Abstract

LLM Hallucination Detection

Explore similar work

HalluSAE: Detecting Hallucinations in Large Language Models via Sparse Auto-Encoders

LLM Hallucination Detection via Low-rank Multilinear Decomposition

External Observers May See More Clearly: Cross-Model Span-Level Hallucination Detection in Large Language Models via Hidden State Probing