From Sub-Ability Diagnosis to Human-Aligned Generation: Bridging the Gap for Text Length Control via MarkerGen
Abstract: Despite the rapid progress of large language models (LLMs), their length-controllable text generation (LCTG) ability remains below expectations, posing a major limitation for practical applications.
Existing methods mainly focus on end-to-end training to reinforce adherence to length constraints.
However, the lack of decomposition and targeted enhancement of LCTG sub-abilities restricts further progress.
To bridge this gap, we conduct a bottom-up decomposition of LCTG sub-abilities with human patterns as reference and perform a detailed error analysis.
On this basis, we propose MarkerGen, a simple-yet-effective plug-and-play approach that:
(1) mitigates LLM fundamental deficiencies via external tool integration;
(2) conducts explicit length modeling with
dynamically inserted markers;
(3) employs a three-stage generation scheme to better align length constraints while maintaining content quality.
Comprehensive experiments demonstrate that MarkerGen significantly improves LCTG across various settings, exhibiting outstanding effectiveness and generalizability.
Paper Type: Long
Research Area: NLP Applications
Research Area Keywords: length-controllable, text generation, large language model
Contribution Types: NLP engineering experiment
Languages Studied: English, Chinese
Submission Number: 6697
Loading