← 研踪 PaperTrailarXiv: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
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 (, same model family as the generators) driving an internal critique loop, and an independent reporting judge (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 MQM against a monolithic baseline of (, , 95% CI ), and isolated discourse restoration alone accounts for MQM (), outperforming a call-count-matched self-refinement baseline by MQM (). Severe per-verse failures (MQM) fall from to , at roughly the per-verse inference cost of the baseline. Additionally, scores its own family's outputs - MQM higher than 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
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 (, same model family as the generators) driving an internal critique loop, and an independent reporting judge (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 MQM against a monolithic baseline of (, , 95% CI ), and isolated discourse restoration alone accounts for MQM (), outperforming a call-count-matched self-refinement baseline by MQM (). Severe per-verse failures (MQM) fall from to , at roughly the per-verse inference cost of the baseline. Additionally, scores its own family's outputs - MQM higher than 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 ↗