LegalSearchLM:重新構思法律案例檢索為法律要素生成
LegalSearchLM: Rethinking Legal Case Retrieval as Legal Elements Generation
May 28, 2025
作者: Chaeeun Kim, Jinu Lee, Wonseok Hwang
cs.AI
摘要
法律案例檢索(Legal Case Retrieval, LCR)是法律專業人士在研究和決策過程中檢索相關案例的基本任務。然而,現有的LCR研究面臨兩大限制。首先,這些研究通常在規模相對較小的檢索語料庫(例如100至55K案例)上進行評估,並使用範圍狹窄的刑事查詢類型,這無法充分反映現實世界法律檢索場景的複雜性。其次,它們依賴於基於嵌入或詞彙匹配的方法,往往導致有限的表示和與法律無關的匹配。為解決這些問題,我們提出了:(1)LEGAR BENCH,首個大規模韓語LCR基準,涵蓋411種多樣化的犯罪類型,查詢範圍超過120萬個法律案例;以及(2)LegalSearchLM,一種檢索模型,該模型對查詢案例進行法律要素推理,並通過約束解碼直接生成基於目標案例的內容。實驗結果顯示,LegalSearchLM在LEGAR BENCH上比基準模型高出6-20%,達到了最先進的性能。它還展現出對域外案例的強大泛化能力,比在域內數據上訓練的簡單生成模型高出15%。
English
Legal Case Retrieval (LCR), which retrieves relevant cases from a query case,
is a fundamental task for legal professionals in research and decision-making.
However, existing studies on LCR face two major limitations. First, they are
evaluated on relatively small-scale retrieval corpora (e.g., 100-55K cases) and
use a narrow range of criminal query types, which cannot sufficiently reflect
the complexity of real-world legal retrieval scenarios. Second, their reliance
on embedding-based or lexical matching methods often results in limited
representations and legally irrelevant matches. To address these issues, we
present: (1) LEGAR BENCH, the first large-scale Korean LCR benchmark, covering
411 diverse crime types in queries over 1.2M legal cases; and (2)
LegalSearchLM, a retrieval model that performs legal element reasoning over the
query case and directly generates content grounded in the target cases through
constrained decoding. Experimental results show that LegalSearchLM outperforms
baselines by 6-20% on LEGAR BENCH, achieving state-of-the-art performance. It
also demonstrates strong generalization to out-of-domain cases, outperforming
naive generative models trained on in-domain data by 15%.