Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

REDE: Denoising Reasoning Traces to Boost Hallucination Detection in Large Reasoning Models

AI By Crimson AI Hugging Face Papers 28 July 2026 · 00:00 12 views
Share: X Telegram

Researchers propose REDE, a framework that denoises reasoning traces by removing irrelevant and repetitive steps, improving hallucination detection in large reasoning models by up to 18.69 AUROC points.

REDE: Denoising Reasoning Traces to Boost Hallucination Detection in Large Reasoning Models

Key points

Large reasoning models (LRMs) generate long chains of thought before arriving at final answers. While these reasoning traces contain valuable signals for detecting hallucinations—incorrect or fabricated outputs—they are often polluted by noisy steps that obscure truthfulness cues. In a new paper, researchers from Hugging Face and collaborators introduce REDE (Reasoning Denoiser), a learning framework designed to filter out such noise automatically.

The team identifies two primary types of reasoning noise: irrelevant steps that contribute little to solving the problem, and repetitive steps whose information is already captured elsewhere. Both types degrade the performance of existing hallucination detectors, which rely on confidence scores or naive embedding-based filtering that fail to reliably separate noisy from informative steps.

REDE leverages final-answer attention as an automatic supervision signal to shape step-level representations. This allows the model to learn embeddings where noisy steps can be identified and removed without requiring human step-level annotations. The filtered reasoning trajectory can then be fed into any existing hallucination detector—whether probing-based, uncertainty-based, or verbalization-based—to improve its accuracy.

Experiments on benchmarks including TruthfulQA, MATH, CodeElo, and MultiHopQA show consistent improvements across Qwen3 and DeepSeek-R1 models. On TruthfulQA, REDE boosts AUROC by up to 18.69 percentage points, reaching 87.32 AUROC. The paper is available on arXiv and has been shared with the Hugging Face community for feedback.

BenchmarkModelBaseline AUROCREDE AUROCImprovement
TruthfulQAQwen3 / DeepSeek-R1~68.6387.32+18.69 pp
MATHQwen3 / DeepSeek-R1Consistent improvement
CodeEloQwen3 / DeepSeek-R1Consistent improvement
MultiHopQAQwen3 / DeepSeek-R1Consistent improvement
Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 31 Aug 2026

Hugging Face Unveils StepGuard: Step-Level Guardrails for Safer AI Agents

StepGuard, a new step-level guard model from Hugging Face, audits agent actions before execution, reducing attack success rates by...

1
Research paper
Hugging Face 31 Aug 2026

Hugging Face Researchers Unveil ABot-Recon for Stable Long-Horizon 3D Reconstruction

ABot-Recon, a new streaming 3D reconstruction model from Hugging Face, achieves stable long-horizon performance using only local t...

1
Research paper
Hugging Face 31 Aug 2026

ContextPilot: Teaching Agents Proactive Context Management via Fine-Grained RL

Hugging Face researchers introduce ContextPilot, a framework that enhances long-horizon agent reasoning by expanding context-editi...

1