A 7B writing model trained on plan-write-refine thinking data with multi-stage preference optimization matches or beats several larger models on long-form generation benchmarks.
PAIR: Planning and Iterative Refinement in Pre-trained Transformers for Long Text Generation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Pre-trained Transformers have enabled impressive breakthroughs in generating long and fluent text, yet their outputs are often "rambling" without coherently arranged content. In this work, we present a novel content-controlled text generation framework, PAIR, with planning and iterative refinement, which is built upon a large model, BART. We first adapt the BERT model to automatically construct the content plans, consisting of keyphrase assignments and their corresponding sentence-level positions. The BART model is employed for generation without modifying its structure. We then propose a refinement algorithm to gradually enhance the generation quality within the sequence-to-sequence framework. Evaluation with automatic metrics shows that adding planning consistently improves the generation quality on three distinct domains, with an average of 20 BLEU points and 12 METEOR points improvements. In addition, human judges rate our system outputs to be more relevant and coherent than comparisons without planning.
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
SuperWriter: Reflection-Driven Long-Form Generation with Large Language Models
A 7B writing model trained on plan-write-refine thinking data with multi-stage preference optimization matches or beats several larger models on long-form generation benchmarks.