Intent-Triggered Anchoring for Multi-Token Format Units in Parallel Decoding of Diffusion Language Models

arXiv:2610.16516v1 Announce Type: new Abstract: In parallel decoding, diffusion language models commit several tokens per forward pass, so co-committed tokens cannot see each other, breaking multi-token format units that parsers need. On ECHO, an open-weight one-step chest X-ray (CXR) report generator, 32.7-36.7% of evaluation reports lack a parseable Impression heading and score as empty. We propose intent-triggered anchoring, a training-free decoding rule that completes a format unit once the model commits its first token, inserting only units with a unique, content-free completion; fallbacks write the unit when the model stops or loops without starting it. On three CXR evaluation sets, the rule raises readable rates from 63.3-67.3% to 100.0% with no regressions and a 95th-percentile latency ratio of 0.68-1.28 against official decoding. Broken headings state findings absent from the reference; adding the heading at the end leaves them in 15.5-31.0% of reports, our rule in at most 0.6%. For math answer markers, the rule raises accuracy in the most parallel setting of five diffusion language models by 5.8-20.8 points on GSM8K and 5.1-17.1 on GSM-Symbolic, held out from tuning. With lenient answer extraction, gains are 3.3-12.5 and 2.7-6.3 points; the rule adds 1.4-8.6 points over a stop-only fallback for four of the five models.

Abstract:In parallel decoding, diffusion language models commit several tokens per forward pass, so co-committed tokens cannot see each other, breaking multi-token format units that parsers need. On ECHO, an open-weight one-step chest X-ray (CXR) report generator, 32.7-36.7% of evaluation reports lack a parseable Impression heading and score as empty. We propose intent-triggered anchoring, a training-free decoding rule that completes a format unit once the model commits its first token, inserting only units with a unique, content-free completion; fallbacks write the unit when the model stops or loops without starting it. On three CXR evaluation sets, the rule raises readable rates from 63.3-67.3% to 100.0% with no regressions and a 95th-percentile latency ratio of 0.68-1.28 against official decoding. Broken headings state findings absent from the reference; adding the heading at the end leaves them in 15.5-31.0% of reports, our rule in at most 0.6%. For math answer markers, the rule raises accuracy in the most parallel setting of five diffusion language models by 5.8-20.8 points on GSM8K and 5.1-17.1 on GSM-Symbolic, held out from tuning. With lenient answer extraction, gains are 3.3-12.5 and 2.7-6.3 points; the rule adds 1.4-8.6 points over a stop-only fallback for four of the five models.

Computation and Language (cs.CL)

arXiv:2610.16516 [cs.CL]

(or arXiv:2610.16516v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2610.16516 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

analiza aiqbench

Intent-Triggered Anchoring for Multi-Token Format Units in Parallel Decoding of Diffusion Language Models

Subiecte conexe