arXiv Machine Learning By Johannes Zenn, Jonas Geiping

When are likely answers right? On Sequence Probability and Correctness in LLMs

Read the original on arXiv Machine Learning →

arXiv:2606. 27359v1 Announce Type: cross Abstract: Many decoding methods for large language models can be understood as shifting probability mass toward outputs that are more likely under the model, either locally at the token level or globally at the sequence level.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

Hugging Face Trending Papers
Jun 10

Re-evaluating Confidence Remasking in Masked Diffusion Language Models

Masked diffusion language models (dLLMs) have recently emerged as a competitive alternative to autoregressive language models, with the promise of faster inference via parallel token generation. A notable limitation of the masked formulation, however, is that once a token has been unmasked it can no longer be revised, leaving dLLMs vulnerable to early sampling mistakes.