arXiv cs.CL· Hannah VanderHoeven, Abhijnan Nath, Nikhil Krishnaswamy·· 13 小时前AI 评分27
研究：LLM 在信息不对称下难以遵循合作原则
Flout at Your Own Risk: LLMs Struggle with Pragmatic Cooperativity Under Epistemic Asymmetry
AI 导读
一项新研究考察 LLM 在多方可协作任务、部分信息条件下的语用推理能力，形式化了"协作认知不对称"概念，并证明可执行指令需遵循 Grice 合作原则。实证评估显示，LLM 作为说话者和听者虽具备一定语用能力，但在信息不完整时仍难以进行语用沟通，且 Grice 准则可预测不同的失败模式。
正文 · 原文
Abstract:Fruitful collaborations require effective communication of privately-held information. The increasing use of LLMs as "collaborators" raises questions about the extent to which they exhibit these pragmatic capabilities. In this paper, we perform a novel investigation into the pragmatic reasoning capabilities of LLMs in a multiparty collaborative task under partial information conditions. We first formalize a notion of collaborative epistemic asymmetry and prove that fully actionable instructions in this context requires adherence to Grice's cooperative principle. We then empirically assess various LLMs' abilities to act cooperatively as both speakers and listeners, including both prompting and post-training strategies. Our results show that while LLMs exhibit certain pragmatic capabilities in collaborative settings, they still face challenges in pragmatic communication with incomplete information, and that Grice's maxims predict distinct failure modes.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2607.11053 [cs.CL] |
| (or arXiv:2607.11053v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2607.11053 arXiv-issued DOI via DataCite |
Submission history
From: Hannah VanderHoeven [view email]
[v1]
Mon, 13 Jul 2026 03:31:56 UTC (11,946 KB)
[v2]
Wed, 21 Oct 2026 03:10:45 UTC (10,785 KB)
来源：arXiv cs.CL · arxiv.org