PAST-TIDE: Prototype-Anchored Statement Tuning with Topic-Invariant Normalization for Stance Detection

  • 类型:arxiv
  • 标识:2607.04690
  • 链接:https://arxiv.org/abs/2607.04690
  • 主分类:engineering
  • 形态:method
  • 被引:1
  • 被引来源:Semantic Scholar
  • S2被引:1
  • OpenAlex被引:0
  • 影响力被引:1
  • TLDR:PAST-TIDE is introduced, PAST-TIDE achieves macro-F1 scores of 0.75 for Subtask A and 0.74 for Subtask B on the official leaderboard, indicating that minimal architectural additions to a pre-trained model can remain competitive in low-resource settings.
  • OpenAlex ID:W7167573035
  • OpenAlex DOI:10.48550/arxiv.2607.04690
  • DOI:10.48550/arxiv.2607.04690
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://doi.org/10.48550/arxiv.2607.04690
  • OpenAlex更新:2026-07-19
  • 待LLM分类:否
  • 标题中文:PAST-TIDE:基于原型锚定语句调优与主题不变归一化的立场检测方法
  • TLDR中文:提出 PAST-TIDE,在官方排行榜上 Subtask A 取得 0.75 的 macro-F1,Subtask B 取得 0.74,表明对预训练模型仅做极少的架构改动即可在低资源场景下保持竞争力。
  • 来源文件
  • /inbox/tom/_candidates/2026-07-11-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • /inbox/tom/_candidates/2026-07-12-agent-rag-longcontext-candidates.json
  • /inbox/tom/_candidates/2026-07-13-agent-rag-longcontext-candidates.json
  • /inbox/tom/_candidates/2026-07-13-agent-memory-tool-use-candidates.json
  • [OpenAlex backfill]