用结构化微调+偏好优化提升社交媒体极化检测效果
BITS Pilani at SemEval-2026 Task 9: Structured Supervised Fine-Tuning with DPO Refinement for Polarization Detection
- 用槽位填充模板和LoRA微调模型，提升可解释性
- 通过自动构建偏好对优化，将错误漏检率降低至0.8162
- 适合关注社会媒体分析与大模型推理优化的研究者
POLAR SemEval-2026 共享任务旨在检测在线极化现象，聚焦多语言、多文化、多事件的极化分类与识别。由于修辞微妙、隐含框架以及人工标注成本高昂，精准计算检测极具挑战。基于近期发现：上下文提示使大语言模型可作为强极化检测器，我们提出一种两阶段方法：先使用结构化监督微调（结合目标、主张类型、表现检查清单与理由）对 Qwen 2.5-7B-Instruct 进行 LoRA 微调；再利用自动生成的偏好对进行直接偏好优化（DPO），以减少昂贵的假阴性。所提交系统在英文测试集上取得 0.7664 的 Macro-F1。后续实验采用 Mistral-Nemo-Instruct-2407 与由 LLM 判定过滤后的偏好对，进一步提升至 0.8162（未提交 CodaBench），超越组织方基线 0.7802。
原文摘要 · Abstract (English)
The POLAR SemEval-2026 Shared Task aims to detect online polarization and focuses on the classification and identification of multilingual, multicultural, and multi-event polarization. Accurate computational detection of online polarization is challenging due to nuanced rhetoric, implicit framing, and the high cost of human-in-the-loop annotation. Building on recent findings that contextual prompting enables large language models to function as strong polarization detectors, we present a two-stage approach for detecting polarization in social media text that combines structured supervised fine tuning with Direct Preference Optimization (DPO) refinement. We fine tune Qwen 2.5-7B-Instruct with LoRA using an interpretable slot-filling template (target, claim type, manifestation checklist, and justification). We then apply DPO with automatically generated preference pairs to reduce costly false negatives. Our submitted system achieves 0.7664 Macro-F1 on the English test set. Post-submission experiments with Mistral-Nemo-Instruct-2407 and LLM-judge-filtered preference pairs further improve to 0.8162 Macro-F1 (not submitted to CodaBench), surpassing the organiser baseline of 0.7802.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。