English(EN)Beyond Probabilistic Similarity: Structural, Temporal, and Causal Limitations of Retrieval-Augmented Generation in the Legal Domain
新的RAG研究解决了证据冲突、领域特异性和时间限制问题
作者PulseAugur 编辑部·[12 个来源]·
arXiv上发表的多篇研究论文探讨了检索增强生成（RAG）系统的进展。这些研究解决了多语言环境中处理冲突证据（X-MADAM-RAG）、通过面向领域的（DCD）和跨查询一致性（CQC-RAG）设计提高鲁棒性，以及通过自适应方法优化上下文选择（Tail-Aware Adaptive-k）等挑战。此外，研究还探讨了用于丰富和重新排序的基于图的方法（GraphER），并强调了RAG在法律AI等专业领域由于结构性、时间性和因果性复杂性而存在的局限性。
AI
arXiv:2606.14269v1 Announce Type: cross Abstract: Fixed-cardinality retrieval injects a constant top-K chunks into the generator regardless of query complexity, causing over-retrieval for narrow queries and under-retrieval for compositional ones. We describe ScoreGate, a lightwei…
Fixed-cardinality retrieval injects a constant top-K chunks into the generator regardless of query complexity, causing over-retrieval for narrow queries and under-retrieval for compositional ones. We describe ScoreGate, a lightweight score-space decision mechanism that controls r…
arXiv cs.AI
TIER_1English(EN)·Valerii Kovalskii, Nikita Belov, Nikita Miteyko, Igor Reshetnikov, Maksim Maksimov·
arXiv:2604.07590v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) is widely used to ground large language models in external knowledge sources. However, when applied to heterogeneous corpora and multi-step queries, Naive RAG pipelines often degrade in…
arXiv:2606.12903v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) systems may receive evidence that is not merely noisy but mutually contradictory. This issue becomes particularly salient in multilingual settings, where retrieved Chinese and English evidence ma…
Retrieval-Augmented Generation (RAG) has become a common approach for improving the factuality of Large Language Models (LLMs), yet its reliability remains highly sensitive to how external evidence is retrieved and used. Semantically equivalent queries with different syntactic fo…
Retrieval-augmented generation (RAG) systems may receive evidence that is not merely noisy but mutually contradictory. This issue becomes particularly salient in multilingual settings, where retrieved Chinese and English evidence may support incompatible answer candidates. We stu…
Adaptive context selection is critical for retrieval-augmented generation (RAG) systems, as fixed Top-K retrieval fails under query-dependent and heavy-tailed similarity distributions. While Extreme Value Theory (EVT) offers a principled framework for adaptive truncation, existin…
arXiv cs.LG
TIER_1English(EN)·Ruizhong Miao, Yuying Wang, Rongguang Wang, Chenyang Li, Tao Sheng, Sujith Ravi, Dan Roth·
arXiv:2603.24925v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) systems that rely on semantic search often fail to retrieve the complete set of evidence for complex queries, particularly when information is distributed across multiple sources. Existing ap…
arXiv:2606.09724v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) has become a standard architectural response to unreliability in legal AI, yet high-profile failures, including fabricated citations submitted to courts and anachronistic legal content presented …
arXiv cs.AI
TIER_1English(EN)·Chenyu Wang, Yueyuan Li, Yingmin Liu, Yang Shu·
arXiv:2605.17301v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) systems implicitly assume mutual consistency among retrieved documents -- an assumption that frequently fails in practice. We present ConflictRAG, a conflict-aware RAG framework that de…
arXiv:2606.07523v1 Announce Type: cross Abstract: Legal domains in high-resource languages like English have widely adopted artificial intelligence for legal question answering. However, data scarcity in low resource languages such as Nepali has limited the training of large lang…
Retrieval-Augmented Generation (RAG) has become a standard architectural response to unreliability in legal AI, yet high-profile failures, including fabricated citations submitted to courts and anachronistic legal content presented as current, continue to appear across jurisdicti…
