The identification of political actors who put forward claims in public debate is a crucial step in the construction of discourse networks, which are helpful to analyze societal debates. Actor identification is, however, rather challenging: Often, the locally mentioned speaker of a claim is only a pronoun ("He proposed that [claim]"), so recovering the canonical actor name requires discourse understanding. We compare a traditional pipeline of dedicated NLP components (similar to those applied to the related task of coreference) with a LLM, which appears a good match for this generation task. Evaluating on a corpus of German actors in newspaper reports, we find surprisingly that the LLM performs worse. Further analysis reveals that the LLM is very good at identifying the right reference, but struggles to generate the correct canonical form. This points to an underlying issue in LLMs with controlling generated output. Indeed, a hybrid model combining the LLM with a classifier to normalize its output substantially outperforms both initial models.

翻译：识别公开辩论中提出主张的政治行为主体，是构建话语网络的关键步骤，这类网络有助于分析社会性辩论。然而，行为主体识别颇具挑战性：通常，主张的局部发言者仅以代词形式出现（“他提出[主张]”），因此恢复规范行为主体名称需要对话语层面的理解。我们将传统专用自然语言处理组件流水线（类似应用于共指消解相关任务的技术）与大型语言模型进行对比，后者看似适合此类生成任务。在德语报纸报道语料库上的评估中，我们惊讶地发现大型语言模型表现更差。进一步分析表明，该模型在识别正确指代方面表现优异，但难以生成准确的规范形式。这暴露出大型语言模型在控制生成输出方面的根本问题。实际上，将大型语言模型与分类器结合的混合模型通过输出规范化，其性能显著优于两种初始模型。