arXiv cs.CL· Zeyu Jia, Bo Yao, Zihao Yang·· 10 小时前AI 评分29
TE-BPHD:用子句分解双边状态接地实现反事实开放世界演绎推理
Clause-Factored Bilateral State Grounding and Scoped Passivity for Counterfactual Open-World Deductive Reasoning
AI 导读
TE-BPHD 以 37.85M 参数将开放世界演绎推理拆分为子句分解的双边接地器与演绎审议算子,在 17,036 条 ProofWriter 测试查询上达到 79.17% 的深度-5 反事实一致性,比 Seq2Seq T5、Flan-T5 和 Recurrent-Depth T5 高 23.83 至 38.67 个百分点。
正文 · 原文
Abstract:Open-World Assumption (OWA) deduction requires distinguishing provable facts (True), refutations (False), and unprovable statements (Unknown) across counterfactual edits and unseen domains. Sequence and latent-recurrent transformers rely on distributional shortcuts, whereas chain-of-thought language models incur high autoregressive latency. We decompose OWA deduction into a clause-factored bilateral grounder ($F$) and a deductive deliberation operator ($B$), forming $B \circ F$ in Typed Edge-Factorized Bilateral Port-Hamiltonian Deliberation (TE-BPHD). Trained solely on three-way query labels without parsers or proof-depth annotations, TE-BPHD (37.85M parameters) maps clauses into a 1,440-dimensional Belnap space and propagates support through passivity-balanced implicit Port-Hamiltonian rule diodes. Across 17,036 locked ProofWriter test queries, TE-BPHD reaches 79.17 +/- 5.48% depth-5 counterfactual consistency (+23.83 to +38.67 percentage points over Seq2Seq T5, Flan-T5, and Recurrent-Depth T5) and 94.95 +/- 1.23% out-of-distribution (OOD) accuracy across 5,270 six-domain queries (92.54 +/- 3.38% macro-mean). On a paired 120-query OOD slice, TE-BPHD attains 93.61 +/- 4.59% versus 79.17% for 3-shot Qwen3-1.7B under a 2,048-token reasoning cap (+14.44 percentage points) at 9.44 versus 14,878.4 ms/query batch-16 NVIDIA L4 throughput. Operator interventions show that symmetric single-rule passivity prevents positive two-cycle modes seen in Gain-Matched Unilateral Horn (+50.00 percentage points counterfactual consistency), whereas unit-interval Grounded Product-T-Norm Logic Tensor Networks (LTN) achieve cycle-safe OOD transfer (94.50 +/- 0.87%) without linear solves, and multi-fact ParaRules prose exposes an upstream grounding trade-off (1.33 +/- 1.76% zero-shot vs. 34.11 +/- 5.01% with five-slot optimal-transport joint grounding).
| Comments: | 17 pages, 4 figures, 5 tables. Revised manuscript with expanded 17,036-query ProofWriter evaluation, 3-shot Qwen3-1.7B CoT comparison, Grounded Product-T-Norm LTN operator intervention, and updated Figure 2 |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Report number: | TMU-TJU-PHLD-2026 |
| Cite as: | arXiv:2609.37351 [cs.LG] |
| (or arXiv:2609.37351v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2609.37351 arXiv-issued DOI via DataCite |
Submission history
From: Zeyu Jia [view email]
[v1]
Tue, 29 Sep 2026 12:17:06 UTC (15 KB)
[v2]
Sat, 7 Nov 2026 13:46:51 UTC (138 KB)
[v3]
Thu, 19 Nov 2026 03:47:25 UTC (309 KB)
来源:arXiv cs.CL · arxiv.org