Mitigating Bias in Locally Constrained Decoding via Tractable Proposals
Generations from large language models often fail to conform to desired constraints such as JSON schema. Existing locally constrained decoding (LCD) approaches enforce constraints by myopically masking out next tokens, resulting in biased sampling and degradation in performance. Recent work uses sequential Monte Carlo (SMC) methods to mitigate such biases, but designing effective proposal distributions or potential functions remains a key challenge. In this work, we propose a generic approach to construct proposals and potentials for SMC sampling from $p_{\mathrm{lm}}( \cdot \mid \mathrm{constraint})$. First, we show that constraints specified as finite automata can be tensorized for effi...
| Authors | Meihua Dang, Linxin Song, Honghua Zhang et al. |
|---|---|
| Primary category | cs.CL |
| Published | 1 June 2026 |
| Last updated at source | 16 August 2026 |
Connected in the knowledge graph
- mhdang/gelatwo-common-gen-gpt2-largeModel · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.