从未完成悖论到 Moorean 荒诞:Qwen3-8B 上的单链推理锁定与多候选言语化研究
From Imperfective Paradox to Moorean Absurdity: Single-Chain Reasoning Lock-In and Multi-Candidate Verbalization Across Aspectual and Pragmatic Ambiguity
AI 导读
该论文在 Qwen3-8B-Q8_0 上开展 4 项预注册实验(16,640 个正式单元,temperature=0.0),检验单链过早锁定假说,16 个假设槽位中 15 个保持验证性结果。
正文 · 原文
Abstract:Natural language entailment and coherence judgments often depend on whether an event merely occurred, reached a telic culmination, satisfied a plan, or was evaluated under multiple pragmatic standards. We test observable consequences of the single-chain premature lock-in hypothesis across four preregistered, sealed formal experiments on Qwen3-8B-Q8_0 (16,640 formal units, temperature=0.0): 15 of 16 hypothesis slots retain confirmatory status (12 rejecting H0 under within-experiment Holm control at alpha_fam=0.05; E3_H3 demoted to descriptive status). In Experiment 1, Direct-CoT vs. MCU differs by 25.00 pp on telic high-confidence completion (Holm p=1.31239e-05), while NLI-CoT collapses by -91.25 pp on uninterrupted atelic items (Holm p=1.81805e-21). Multi-Candidate Verbalization (MCV) elicits K=5 weighted estimates in one call, separating the prompt from unweighted (MCU) and self-weighted (MCW) readouts. Mandarin (E2) and English (E3) expose an Interruption-Anchored Realis Paradox under NLI-CoT. In Experiment 4, MCU-CF raises perceived coherence on implicit Moorean sentences by 26.64 pp over Direct-CoT (Holm p=0.0006), alongside Direct-CF - Direct-CoT = 29.15 pp and MCU-CoT - Direct-CoT = 17.31 pp. A 1,800-call OpenAI ablation and a stage="dev" P16.7 cross-model extension (4,240 planned/collected units across five external models: 4,222 valid, 18 format-missing, 0 transport-missing; <2% missing per slice; OpenAI gpt-4o-mini at top_logprobs=20 achieves 1,000/1,000 valid units) show that discrete NLI-CoT and scalar Direct-CoT judgments dissociate across models. Confirmatory effects concern observable prompt-and-readout protocols; internal premature lock-in remains a hypothesis. All code, stimuli, preregistered analysis plans, and verification tools are available at this https URL.
| Comments: | 21 pages, 4 figures, 25 tables (single-column arXiv preprint; includes 16,640 Qwen3-8B formal units across 4 preregistered experiments, 1,800 OpenAI format-ablation calls, and 4,240 P16.7 development-slice units across 5 external models) |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.22188 [cs.CL] |
| (or arXiv:2611.22188v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.22188 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: An-Sheng Jhang [view email]
[v1]
Tue, 17 Nov 2026 04:20:45 UTC (148 KB)
来源:arXiv cs.AI · arxiv.org