用一个模型同时完成三类事实核查任务，大幅降低部署成本。
One LLM to Train Them All: Multi-Task Learning Framework for Fact-Checking
- 用单一模型联合训练三类事实核查任务，避免多模型维护
- 相比零样本设置，三项任务分别提升44%、54%、31%准确率
- 适合资源有限但需高效部署的新闻审核与信息验证场景
大型语言模型正在重塑自动化事实核查，实现端到端统一验证。尽管闭源大模型表现优异，但其权重封闭、复杂且成本高昂，难以持续使用。微调小型开源模型虽可降低成本，但需为每项任务单独训练，仍具高开销。本文提出多任务学习（MTL）框架，仅用一个模型同时完成断言检测、证据排序和立场识别。基于Qwen3-4b等小规模解码器模型，探索分类头、因果语言建模头与指令微调三种策略，在不同模型规模、任务顺序及非LLM基线中评估。虽然多任务模型未在所有情况下超越单任务基线，但显著提升性能：相较于零/少样本设置，断言检测、证据重排序、立场识别分别获得44%、54%、31%的相对增益。最后，提供实用、实证支持的MTL应用指南，助力从业者高效部署事实核查系统。
原文摘要 · Abstract (English)
Large language models (LLMs) are reshaping automated fact-checking (AFC) by enabling unified, end-to-end verification pipelines rather than isolated components. While large proprietary models achieve strong performance, their closed weights, complexity, and high costs limit sustainability. Fine-tuning smaller open weight models for individual AFC tasks can help but requires multiple specialized models resulting in high costs. We propose \textbf{multi-task learning (MTL)} as a more efficient alternative that fine-tunes a single model to perform claim detection, evidence ranking, and stance detection jointly. Using small decoder-only LLMs (e.g., Qwen3-4b), we explore three MTL strategies: classification heads, causal language modeling heads, and instruction-tuning, and evaluate them across model sizes, task orders, and standard non-LLM baselines. While multitask models do not universally surpass single-task baselines, they yield substantial improvements, achieving up to \textbf{44\%}, \textbf{54\%}, and \textbf{31\%} relative gains for claim detection, evidence re-ranking, and stance detection, respectively, over zero-/few-shot settings. Finally, we also provide practical, empirically grounded guidelines to help practitioners apply MTL with LLMs for automated fact-checking.
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。