论点坍缩:LLMs 扁平化长篇公共辩论
Argument Collapse: LLMs Flatten Long-Form Public Debate
AI总结:
研究大型语言模型在生成公共辩论文本时导致论点坍缩的现象,即不同模型生成的论文在主要论点、子论点和段落结构上趋于收敛,通过对比人类与LLM生成文本发现LLM的论点多样性显著降低。
摘要:
随着LLMs越来越多地被用于起草面向公众的论点,它们可能通过反复引入相同的、经过修饰的、看似合理的论点来扁平化公共辩论。我们研究了论点坍缩,即不同LLMs生成的论文倾向于收敛到更小的主要论点、子论点和段落级结构集合。我们比较了来自195场《纽约时报》辩论的1,039个人类回复、来自61场更长形式的《波士顿评论》论坛的448个人类回复以及23,384篇LLM生成的论文。在《纽约时报》语料库中,65.3%的人类主要论点在辩论中是唯一的,而LLM主要论点中这一比例为3.4%。要求LLMs生成多样化的答案会增加变异性,但一个典型模型只能恢复大约一半的不同人类主要论点,且增加的变异性大多落在观察到的人类论点空间之外。坍缩也出现在子论点中,在具有相同主要论点的论文中,41.0%的人类子论点是唯一的,而LLM回复中这一比例为9.1%。定性上,LLMs经常重复使用泛化和模糊的子论点,而人类更喜欢更具体和针对主题的子论点。在结构上,LLM生成的论文倾向于遵循更固定的弧线,通常以直接主张开头并迅速转向提议。同样的模式在更长的《波士顿评论》论文中也成立,表明论点坍缩不仅限于短篇回复。
英文摘要:
As LLMs are increasingly used to draft publicfacing arguments, they may flatten public debate by repeatedly introducing the same polished, plausible arguments. We study argument collapse, the tendency of essays generated by different LLMs to converge to a smaller set of main arguments, sub-arguments, and paragraph-level structures. We compare 1,039 human responses from 195 New York Times (NYT) debates, 448 human responses from 61 longer-form Boston Review (BR) forums, and 23,381 LLM-generated essays. In the NYT corpus, 65.3% of human main arguments are unique within a debate, compared to 3.4% of LLM main arguments. Asking LLMs to generate diverse answers adds variation, but a typical model recovers only about half of the distinct human main arguments, with much of the added variation falling outside the observed human argument space. Collapse also appears in sub-arguments, where among essays with the same main argument, 41.0% of human subarguments are unique versus 9.1% from LLM responses. Qualitatively, LLMs often reuse generalized and hedged sub-arguments, while humans prefer more concrete and topic-specific ones. Structure-wise, LLM-generated essays tend to follow a more fixed arc, often opening with a direct claim and moving quickly toward proposals. The same patterns hold in longer BR essays, suggesting that argument collapse extends beyond short-form responses. Finally, human-preference evaluators favor both common arguments and LLM essays, which could reinforce argument collapse.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。