Controllable Text Generation with Neurally-Decomposed Oracle
We propose a general and efficient framework to control auto-regressive generation models with NeurAlly-Decomposed Oracle (NADO). Given a pre-trained base language model and a sequence-level boolean oracle function, we propose to decompose the oracle function into token-level guidance to steer the base model in text generation. Specifically, the token-level guidance is approximated by a neural model trained with examples sampled from the base model, demanding no additional auxiliary labeled data. Based on posterior regularization, we present the closed-form optimal solution to incorporate the token-level guidance into the base model for controllable generation. We further provide a theoretical analysis of how the approximation quality of NADO affects the controllable generation results. Experiments conducted on two applications: (1) text generation with lexical constraints and (2) machine translation with formality control demonstrate that our framework efficiently guides the base model towards the given oracle while maintaining high generation quality.
Code (1)
Tasks
Language ModelingLanguage ModellingMachine TranslationText GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
DiNADO: Norm-Disentangled Neurally-Decomposed Oracles for Controlling Language Models
NeurAlly-Decomposed Oracle (NADO) is a powerful approach for controllable generation with large language models. It is designed to avoid catastrophic forgetting while achieving guaranteed convergence to an entropy-maximi…
Machine TranslationAssessing the Stylistic Properties of Neurally Generated Text in Authorship Attribution
Recent applications of neural language models have led to an increased interest in the automatic generation of natural language. However impressive, the evaluation of neurally generated text has so far remained rather in…
AttributeAuthorship AttributionText GenerationAssessing the Stylistic Properties of Neurally Generated Text in Authorship Attribution
Recent applications of neural language models have led to an increased interest in the automatic generation of natural language. However impressive, the evaluation of neurally generated text has so far remained rather in…
AttributeAuthorship AttributionData AugmentationLanguage Modeling+2DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimization
Recently, 3D generative models have shown promising performances in structure-based drug design by learning to generate ligands given target binding sites. However, only modeling the target-ligand distribution can hardly…
Drug DesignDrug DiscoveryDiff-Oracle: Deciphering Oracle Bone Scripts with Controllable Diffusion Model
Deciphering oracle bone scripts plays an important role in Chinese archaeology and philology. However, a significant challenge remains due to the scarcity of oracle character images. To overcome this issue, we propose Di…
Image GenerationImage-to-Image Translation