Acting Flatterers via LLMs Sycophancy: Combating Clickbait with LLMs Opposing-Stance Reasoning
Chaowei Zhang, Xiansheng Luo, Zewei Zhang, Yi Zhu, Jipeng Qiang, Longwei Wang
Abstract
The widespread proliferation of online content has intensified concerns about clickbait-deceptive or exaggerated headlines designed to attract attention. While Large Language Models (LLMs) offer a promising avenue for addressing this issue, their effectiveness is often hindered by Sycophancy, a tendency to produce reasoning that matches users' beliefs over truthful ones, which deviates from instruction-following principles. Rather than treating sycophancy as a flaw to be eliminated, this work proposes a novel approach that initially harnesses this behavior to generate contrastive reasoning from opposing perspectives. Specifically, we design a Self-renewal Opposing-stance Reasoning Generation (SORG) framework that prompts LLMs to produce high-quality "agree" and "disagree" reasoning pairs for a given news title without requiring groundtruth labels. To utilize the generated reasoning, we develop a local Opposing Reasoning-based Clickbait Detection (ORCD) model that integrates three BERT encoders to represent the title and its associated reasoning. The model leverages contrastive learning, guided by soft labels derived from LLM-generated credibility scores, to enhance detection robustness. Experimental evaluations on three benchmark datasets demonstrate that our method consistently outperforms LLM prompting, fine-tuned smaller language models, and state-of-the-art clickbait detection baselines. Our code is available in https://github.com/126541/ORCD .
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Training language models to follow instructions with human feedback cites Language Models are Few-Shot Learners
- Towards Understanding Sycophancy in Language Models cites Training language models to follow instructions with human feedback
Builds on13
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- Training language models to follow instructions with human feedbackLong Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida et al.NeurIPS 2022 · 24,707 citations
- ALBERT: A Lite BERT for Self-supervised Learning of Language RepresentationsZhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel et al.ICLR 2020 · 7,418 citations
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionMike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad et al.ACL 2020 · 1,224 citations
- Towards Understanding Sycophancy in Language ModelsMrinank Sharma, Meg Tong, Tomasz Korbak, David Duvenaud et al.ICLR 2024 · 762 citations
Related papers
- A Novel Contrastive Learning Method for Clickbait Detection on RoCliCo: A Romanian Clickbait Corpus of News ArticlesDaria-Mihaela Broscoteanu, Radu Tudor IonescuEMNLP Findings 2023 · 9 citations
- Measuring Sycophancy of Language Models in Multi-turn DialoguesJiseung Hong, Grace Byun, Seungone Kim, Kai ShuEMNLP Findings 2025 · 19 citations
- Challenging the Evaluator: LLM Sycophancy Under User RebuttalSung Won Kim, Daniel KhashabiEMNLP Findings 2025 · 6 citations
- Evaluating and Mitigating Sycophancy in Large Vision-Language ModelsJiayi Gao, Huaiwen ZhangACM MM 2025
- MAR: Metacognitive Agentic Reasoning for Multimodal Fake News DetectionWenyu Chen, Hengbing Dong, Junhao Wa, Ping Wei et al.KDD 2026
