Pith. sign in

REVIEW 1 cited by

Controllable Generation via Locally Constrained Resampling

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.13111 v1 pith:HNSLU5ZX submitted 2024-10-17 cs.LG cs.CLstat.ML

classification cs.LGcs.CLstat.ML
keywords constraintdistributionapproachsamplessubjectautoregressiveconstrainedconstraints
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Autoregressive models have demonstrated an unprecedented ability at modeling the intricacies of natural language. However, they continue to struggle with generating complex outputs that adhere to logical constraints. Sampling from a fully-independent distribution subject to a constraint is hard. Sampling from an autoregressive distribution subject to a constraint is doubly hard: We have to contend not only with the hardness of the constraint but also the distribution's lack of structure. We propose a tractable probabilistic approach that performs Bayesian conditioning to draw samples subject to a constraint. Our approach considers the entire sequence, leading to a more globally optimal constrained generation than current greedy methods. Starting from a model sample, we induce a local, factorized distribution which we can tractably condition on the constraint. To generate samples that satisfy the constraint, we sample from the conditional distribution, correct for biases in the samples and resample. The resulting samples closely approximate the target distribution and are guaranteed to satisfy the constraints. We evaluate our approach on several tasks, including LLM detoxification and solving Sudoku puzzles. We show that by disallowing a list of toxic expressions our approach is able to steer the model's outputs away from toxic generations, outperforming similar approaches to detoxification. We conclude by showing that our approach achieves a perfect accuracy on Sudoku compared to <50% for GPT4-o and Gemini 1.5.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Probabilistic Circuits for Knowledge Graph Completion with Reduced Rule Sets

    cs.AI 2025-08 conditional novelty 6.0 of 10

    A probabilistic-circuit model over rule subsets lets knowledge graph completion use 70-96% fewer rules while retaining about 91% of full-rule-set accuracy.

Pith tools