LLM-guided headline rewriting for clickability enhancement without clickbait

• URL: http://arxiv.org/abs/2603.22459v1
• Date: Mon, 23 Mar 2026 18:25:48 GMT
• Title: LLM-guided headline rewriting for clickability enhancement without clickbait
• Abstract summary: Enhancing reader engagement while preserving informational fidelity is a central challenge in controllable text generation for news media.<n>We frame clickbait not as a separate stylistic category, but as an extreme outcome of disproportionate amplification of otherwise legitimate engagement cues.<n>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.
• Score: 40.12543056558646
• License: http://creativecommons.org/licenses/by/4.0/
• 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-attribute model that provides positive guidance aligned with target clickability objectives. Both guides are trained on neutral headlines drawn from a curated real-world news corpus. At the same time, clickbait variants are generated synthetically by rewriting these original headlines using an LLM under controlled activation of predefined engagement tactics. By adjusting guidance weights at inference time, the system generates headlines along a continuum from neutral paraphrases to more engaging yet editorially acceptable formulations. The proposed framework provides a principled approach for studying the trade-off between attractiveness, semantic preservation, and clickbait avoidance, and supports responsible LLM-based headline optimization in journalistic settings.

Related papers

• Automatic Red Teaming for Implicit Vulnerabilities of Text-to-Image Models [58.59008920408855]
  We propose Adversarial Probing for Implicit VulnErabilities (AdvPIE) to expose implicit vulnerabilities without requiring access to the parameters of target models.<n> AdvPIE adopts a policy agent to generate and refine implicit adversarial prompts based on the feedback from a judge agent.<n>Experiments on standard and safety-aligned T2I models show that AdvPIE1 effectively uncovers implicit vulnerabilities.
  arXiv  Detail & Related papers  (2026-09-05T13:45:09Z)
• TAG: Target-Agnostic Guidance for Stable Object-Centric Inference in Vision-Language-Action Models [59.13964209628383]
  Vision-Language--Action (VLA) policies have shown strong progress in mapping language instructions and visual observations to robotic actions, yet their reliability degrades in cluttered scenes with distractors.<n>We propose TAG (Target-Agnostic Guidance), a simple inference-time guidance mechanism that explicitly reduces distractor- and appearance-induced bias in VLA policies.<n>We evaluate TAG on standard manipulation benchmarks, including LIBERO, LIBERO-Plus, and VLABench, where it consistently improves robustness under clutter and reduces near-miss and wrong-object executions.
  arXiv  Detail & Related papers  (2026-03-25T17:56:32Z)
• SEM: Sparse Embedding Modulation for Post-Hoc Debiasing of Vision-Language Models [36.40093869747498]
  We propose Sparse Embedding Modulation (SEM), a post-hoc, zero-shot debiasing framework that operates in a Sparse Autoencoder latent space.<n>SEM identifies and modulates bias-relevant neurons while preserving query-relevant ones.<n>Our results demonstrate that sparse latent representations provide an effective foundation for post-hoc debiasing of vision-language models.
  arXiv  Detail & Related papers  (2026-03-19T15:28:08Z)
• Click it or Leave it: Detecting and Spoiling Clickbait with Informativeness Measures and Large Language Models [1.5658704610960574]
  We present a hybrid approach to clickbait detection that combines transformer-based text embeddings with linguistically motivated informativeness features.<n>Our best-performing model, XGBoost over embeddings augmented with 15 explicit features, achieves an F1-score of 91%.<n>The proposed feature set enhances interpretability by highlighting salient linguistic cues such as second-person pronouns, superlatives, numerals, and attention-oriented punctuation.
  arXiv  Detail & Related papers  (2026-02-20T12:16:08Z)
• Explicit Uncertainty Modeling for Active CLIP Adaptation with Dual Prompt Tuning [51.99383151474742]
  We propose a robust uncertainty modeling framework for active CLIP adaptation based on dual-prompt tuning.<n>We show that our method consistently outperforms existing active learning methods under the same annotation budget.
  arXiv  Detail & Related papers  (2026-02-04T09:01:55Z)
• Acting Flatterers via LLMs Sycophancy: Combating Clickbait with LLMs Opposing-Stance Reasoning [10.782330552067664]
  Sycophancy is a tendency to produce reasoning that matches users' beliefs over truthful ones.<n>This work proposes a novel approach that harnesses this behavior to generate contrastive reasoning from opposing perspectives.<n>We develop a local Opposing Reasoning-based Clickbait Detection model that integrates three BERT encoders to represent the title and its associated reasoning.
  arXiv  Detail & Related papers  (2026-01-17T11:57:23Z)
• What's Left Unsaid? Detecting and Correcting Misleading Omissions in Multimodal News Previews [31.373823254968315]
  Even when factually correct, social-media news previews can induce interpretation drift.<n>This covert harm is harder to detect than explicit misinformation yet remains underexplored.<n>We develop a multi-stage pipeline that disentangles and simulates preview-based versus context-based understanding.
  arXiv  Detail & Related papers  (2026-01-09T06:29:19Z)
• DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models [55.30555646945055]
  Text-to-Image (T2I) models are vulnerable to semantic leakage.<n>We introduce DeLeaker, a lightweight approach that mitigates leakage by directly intervening on the model's attention maps.<n>SLIM is the first dataset dedicated to semantic leakage.
  arXiv  Detail & Related papers  (2025-10-16T17:39:21Z)
• An Interpretable Benchmark for Clickbait Detection and Tactic Attribution [37.86790434630698]
  The proliferation of clickbait headlines poses significant challenges to the credibility of information and user trust in digital media.<n>This paper presents a model for explainable clickbait detection that not only identifies clickbait titles but also attributes them to specific linguistic manipulation strategies.<n>We present a two-stage framework for automatic clickbait analysis comprising detection and tactic attribution.
  arXiv  Detail & Related papers  (2025-09-13T18:26:49Z)
• Analysing Zero-Shot Readability-Controlled Sentence Simplification [54.09069745799918]
  We investigate how different types of contextual information affect a model's ability to generate sentences with the desired readability.<n>Results show that all tested models struggle to simplify sentences due to models' limitations and characteristics of the source sentences.<n>Our experiments also highlight the need for better automatic evaluation metrics tailored to RCTS.
  arXiv  Detail & Related papers  (2024-09-30T12:36:25Z)
• Prompt Highlighter: Interactive Control for Multi-Modal LLMs [50.830448437285355]
  This study targets a critical aspect of multi-modal LLMs' (LLMs&VLMs) inference: explicit controllable text generation. We introduce a novel inference method, Prompt Highlighter, which enables users to highlight specific prompt spans to interactively control the focus during generation. We find that, during inference, guiding the models with highlighted tokens through the attention weights leads to more desired outputs.
  arXiv  Detail & Related papers  (2023-12-07T13:53:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.