[2603.22459] LLM-guided headline rewriting for clickability enhancement without clickbait

Computer Science > Computation and Language arXiv:2603.22459 (cs) [Submitted on 23 Mar 2026] Title:LLM-guided headline rewriting for clickability enhancement without clickbait Authors:Yehudit Aperstein, Linoy Halifa, Sagiv Bar, Alexander Apartsin View a PDF of the paper titled LLM-guided headline rewriting for clickability enhancement without clickbait, by Yehudit Aperstein and 3 other authors View PDF Abstract:Enhancing reader engagement while preserving informational fidelity is a central challenge in controllable text generation for news media. Optimizing news headlines for reader engagement is often conflated with clickbait, resulting in exaggerated or misleading phrasing that undermines editorial trust. We frame clickbait not as a separate stylistic category, but as an extreme outcome of disproportionate amplification of otherwise legitimate engagement cues. Based on this view, we formulate headline rewriting as a controllable generation problem, where specific engagement-oriented linguistic attributes are selectively strengthened under explicit constraints on semantic faithfulness and proportional emphasis. We present a guided headline rewriting framework built on a large language model (LLM) that uses the Future Discriminators for Generation (FUDGE) paradigm for inference-time control. The LLM is steered by two auxiliary guide models: (1) a clickbait scoring model that provides negative guidance to suppress excessive stylistic amplification, and (2) an engagement-at...