用大模型集成提升政治问答清晰度识别，效果优于传统微调方法。
CLaC at SemEval-2026 Task 6: Response Clarity Detection in Political Discourse
- 采用提示工程的LLM集成，无需任务微调即可实现高精度
- 在3类和9类任务上分别取得80和59的宏F1分数，排名领先
- 输入信息增强能提升大模型表现，但对编码器无效，揭示方法差异
本文介绍我们在SemEval-2026 Task 6（CLARITY）中的系统，旨在检测美国总统访谈中问答对的回应清晰度与回避行为。我们对比了微调编码器与基于提示的大型语言模型（LLM）。LLM集成在3类任务（第9/41名）上达到80的宏F1，9类任务（第3/33名）上达59。通过四阶段优化的8个Transformer编码器中，部分层解冻优于全量微调。结合英文与多语言编码器进一步提升集成性能，尽管多语言模型个体表现较弱。无需参数更新的提示型LLM在少数类上表现更优；开放权重模型中，参数量无法预测性能。丰富输入（拼接完整提问句）可提升LLM表现，但对编码器无效，该现象在使用长上下文窗口的Longformer下仍存在，表明差异不单纯由序列长度导致。清晰回复与模糊回答的边界仍是主要失败模式，与人工标注者分歧一致。代码、提示、模型配置及结果均已公开。
原文摘要 · Abstract (English)
In this paper, we present our system for SemEval-2026 Task 6 (CLARITY) on response clarity and evasion detection in question-answer pairs from U.S. presidential interviews, comparing fine-tuned encoders with prompt-based LLMs. Our LLM ensemble achieves 80 macro-F1 on the 3-class Task 1 (9th/41) and 59 on the 9-class Task 2 (3rd/33). Across 8 transformer encoders optimized through a four-stage pipeline, partial encoder layer unfreezing outperforms full fine-tuning by a wide margin. Combining English and multilingual encoders further improves ensemble performance over either family alone, despite multilingual models being individually weaker. Prompt-based LLMs, without any task-specific parameter updates, outperform fine-tuned encoders, particularly on minority classes; among open-weight LLMs, parameter count does not predict performance. Enriched input, concatenating the full interviewer turn, improves LLM performance but not that of encoders, an effect that persists with Longformer's extended context window, suggesting the divergence is not attributable to sequence-length capacity alone in our settings. The Clear Reply/Ambivalent boundary remains the dominant failure mode, mirroring the disagreement among human annotators. Our code, prompts, model configurations, and results are publicly available.
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。