Unsure but Certain: Uncovering the Representation-Confidence Gap in Diffusion Language Models
Saurabh Yadav, Badri Narayana Patro, Vijay Srinivas Agneeswaran
cs.CL
Submitted: 2026-08-09
Updated: 2026-08-11
License: http://creativecommons.org/licenses/by/4.0/
The gist: Diffusion language models use broad context to create text, suggesting they might handle input noise better than standard models.
Terminology
Abstract
Diffusion language models use broad context to create text, suggesting they might handle input noise better than standard models. Testing reveals this is only partially true. Internally, diffusion models detect text errors highly accurately. Externally, their reported certainty ignores this signal. As accuracy drops due to noise, confidence stays near its maximum and the ability to correctly rank answers degrades toward random chance. We call this mismatch the representation confidence gap. The visible concentration of high certainty scores is a misleading surface symptom. Standard math adjustments remove this concentration but fail to fix the underlying loss of ranking order. This ranking deficit favors standard models under noisy conditions and resists common remedies. Matching training recovers accuracy but not ranking, while score recalibration and input level error signals cannot reorder the final answers. However, the information needed to properly evaluate an answer survives in the hidden states. A lightweight extraction tool uses this signal to improve ranking. This approach is highly efficient because it leaves the base model completely frozen and requires zero additional text generation steps. We present this tool to prove the signal exists, while clearly noting its limits. Ultimately, certainty reliability is a more pressing limit than overall accuracy under noisy conditions.
Sources
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Training Verifiers to Solve Math Word Problems
- Language Models (Mostly) Know What They Know
- Noise Augmented Fine Tuning for Mitigating Hallucinations in Large Language Models
- Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs
- The Llama 3 Herd of Models
- Large Language Diffusion Models
- Qwen2.5 Technical Report
- Corrective Diffusion Language Models
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering