| title | When Confidence Misleads: Suffix Anchoring and Anchor-Proximity Confidence Modulation for Diffusion Language Models |
|---|---|
| authors | Jungwon Park, Jimyeong Kim, Jungmin Ko, Nojun Kwak, Wonjong Rhee |
| date | 2026-05-27 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.28181 |
| affiliation | Seoul National University |
| upvotes | 1 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | Diffusion language models decode text by iteratively denoising masked token sequences, making the choice of which positions to decode a central inference-time decision. Most training-free decoding strategies use model confidence for position selection, assuming that high-confidence positions are ready to be decoded. In this work, we revisit this assumption by studying when confidence misleads fully non-autoregressive (fully non-AR) decoding. EOT tokens can receive high confidence and cause incomplete generation; inserting a suffix anchor can mitigate this issue but introduces local overconfidence near the anchor, causing anchor-adjacent tokens to be decoded too early. To address these issues, we propose Suffix-Anchored Confidence Modulation, a simple training-free method that inserts a short suffix anchor to encourage response completion and modulates confidence near the anchor according to decoding progress. This preserves the response-completion benefit of suffix anchoring while reducing premature decoding of anchor-adjacent tokens. Across text-only reasoning, vision-language reasoning, and code-generation benchmarks, our method consistently improves confidence-based fully non-AR decoding, outperforms explicit EOT suppression, and preserves the parallel decoding advantage of fully non-AR generation. |
cite
@misc{park2026when,
title={When Confidence Misleads: Suffix Anchoring and Anchor-Proximity Confidence Modulation for Diffusion Language Models},
author={Jungwon Park and Jimyeong Kim and Jungmin Ko and Nojun Kwak and Wonjong Rhee},
year={2026},
eprint={2605.28181},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.28181}
}