跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.14675 · v1

MITRA-Swarm: Injecting Explicit Linguistic Structure into Foundation Models for Classical Machine Translation

首次提交 2026-11-11 03:31
版本更新 2026-11-11 03:31
雷达观测 2026-11-13 10:09
arXiv ↗PDF ↗

摘要

Classical Sanskrit poses three challenges unresolved by single-call monolithic models: morphophonemic fusion Sandhi, dense nominal compounding Samāsa, and discourse-level zero-anaphora forced by poetic meter. We present MITRA-Swarm, a multi-agent architecture injecting explicit linguistic structure into an otherwise monolithic pipeline: a Sandhi-splitting agent, a parallel array of generalist gemma-4-26B-A4B-it and domain-specialized gemma-2-mitra-it translators, and a discourse-aware Ellipsis Restorer that consults corpus-derived register tags to avoid inventing active-voice subjects in impersonal legal and philosophical registers. Two separated judges evaluate quality: a routing judge (JrouteJ_{\text{route}}, same model family as the generators) driving an internal critique loop, and an independent reporting judge (Jreport=J_{\text{report}}=gpt-4o-mini, no shared vendor lineage) scoring every output exactly once. On a stratified benchmark of 1,000 verses across five registers (23,990 scored verdicts, 12-condition pre-registered ablation), the full swarm reaches 85.9085.90 MQM against a monolithic baseline of 85.2785.27 (Δ=+0.63Δ=+0.63, padj=0.0018p_{\text{adj}}=0.0018, 95% CI [+0.30,+0.97][+0.30,+0.97]), and isolated discourse restoration alone accounts for +0.44+0.44 MQM (padj=0.0288p_{\text{adj}}=0.0288), outperforming a call-count-matched self-refinement baseline by +0.51+0.51 MQM (padj=0.0288p_{\text{adj}}=0.0288). Severe per-verse failures (MQM<80<80) fall from 9.0%9.0\% to 7.6%7.6\%, at roughly 9×9\times the per-verse inference cost of the baseline. Additionally, JrouteJ_{\text{route}} scores its own family's outputs 22-77 MQM higher than JreportJ_{\text{report}} on every one of the 12 conditions, empirically motivating the two-judge split; and a preflight screen of a 192,151-entry retrieval index against all 12 evaluation works verifies 0 reference leaks across 269 runtime checks. These are small gains on a metric saturating near 85-86.

作者备注:17 pages, accepted to NeurIPS 2026 LP4FM Workshop

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-11 03:31 · 最新观测版本

MITRA-Swarm: Injecting Explicit Linguistic Structure into Foundation Models for Classical Machine Translation

Classical Sanskrit poses three challenges unresolved by single-call monolithic models: morphophonemic fusion Sandhi, dense nominal compounding Samāsa, and discourse-level zero-anaphora forced by poetic meter. We present MITRA-Swarm, a multi-agent architecture injecting explicit linguistic structure into an otherwise monolithic pipeline: a Sandhi-splitting agent, a parallel array of generalist gemma-4-26B-A4B-it and domain-specialized gemma-2-mitra-it translators, and a discourse-aware Ellipsis Restorer that consults corpus-derived register tags to avoid inventing active-voice subjects in impersonal legal and philosophical registers. Two separated judges evaluate quality: a routing judge (JrouteJ_{\text{route}}, same model family as the generators) driving an internal critique loop, and an independent reporting judge (Jreport=J_{\text{report}}=gpt-4o-mini, no shared vendor lineage) scoring every output exactly once. On a stratified benchmark of 1,000 verses across five registers (23,990 scored verdicts, 12-condition pre-registered ablation), the full swarm reaches 85.9085.90 MQM against a monolithic baseline of 85.2785.27 (Δ=+0.63Δ=+0.63, padj=0.0018p_{\text{adj}}=0.0018, 95% CI [+0.30,+0.97][+0.30,+0.97]), and isolated discourse restoration alone accounts for +0.44+0.44 MQM (padj=0.0288p_{\text{adj}}=0.0288), outperforming a call-count-matched self-refinement baseline by +0.51+0.51 MQM (padj=0.0288p_{\text{adj}}=0.0288). Severe per-verse failures (MQM<80<80) fall from 9.0%9.0\% to 7.6%7.6\%, at roughly 9×9\times the per-verse inference cost of the baseline. Additionally, JrouteJ_{\text{route}} scores its own family's outputs 22-77 MQM higher than JreportJ_{\text{report}} on every one of the 12 conditions, empirically motivating the two-judge split; and a preflight screen of a 192,151-entry retrieval index against all 12 evaluation works verifies 0 reference leaks across 269 runtime checks. These are small gains on a metric saturating near 85-86.

查看此版本解读 →查看此版本原文 ↗