Re-ranking retrieval candidates via a cross-encoder trained on continuous perturbation-based attribution scores improves citation faithfulness and gold-answer alignment in legal QA over semantic similarity.
2408.10343 , archivePrefix =
14 Pith papers cite this work, alongside 7 external citations. Polarity classification is still indexing.
14
Pith papers citing it
7
external citations · external index
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
MAP-Law dynamically controls retrieval depth in legal AI by computing element coverage, evidence coverage, and marginal gain on a joint node graph, reaching 0.86 element coverage with 58% fewer rounds than fixed baselines on 50 labor-law cases.
SAT-Graph RAG is a new ontology-driven temporal graph framework for legal RAG that models Works vs. Expressions, reuses versioned components for temporal states, and treats legislative events as queryable Action nodes to support deterministic point-in-time and causal queries.
A section-aware hybrid retrieval system segments legal cases with an LLM, fuses BM25 and dense search via RRF, then applies Z-score normalized section-weighted comparisons to outperform baselines on a large benchmark.
Process supervision via RAG-Gym produces more reliable and generalizable search agents, with gains driven by higher-quality queries on out-of-domain multi-hop tasks.
The survey organizes RAG methods via a taxonomy of query-based, logits-based, latent, and parametric fusion with comparisons on accessibility, efficiency, applications, and challenges.
Legal AI benchmarks must evaluate robustness to pro se litigant inputs rather than expert-preprocessed ones to support access-to-justice claims.
Maat is a ReAct agent that orchestrates tools and RAG for competition law research, outperforming baselines on case-specific tasks while providing official citations.
Deepchecks is a new multi-faceted evaluation framework for RAG that incorporates root cause analysis and production monitoring to assess reliability, relevance, and user satisfaction.
A RAG system for global AI regulation with type-specific chunking, conditional routing, and priority re-ranking achieves 0.87 average faithfulness and 0.84 relevancy on 50 test queries.
ReLeVAnT achieves 99.3% accuracy and 98.7% F1 in binary legal document classification on LexGLUE via n-gram processing, contrastive score matching, and a shallow neural network after one-time keyword extraction.
LexPath combines IRAC-guided sparse retrieval, structure-guided dense retrieval, and intent-aware reranking to outperform standard lexical, dense, hybrid, and RAG baselines on legal article retrieval benchmarks.
citing papers explorer
-
Re-Ranking Through an Attribution Lens for Citation Quality in Legal QA
Re-ranking retrieval candidates via a cross-encoder trained on continuous perturbation-based attribution scores improves citation faithfulness and gold-answer alignment in legal QA over semantic similarity.
-
MAP-Law: Coverage-Driven Retrieval Control for Multi-Turn Legal Consultation
MAP-Law dynamically controls retrieval depth in legal AI by computing element coverage, evidence coverage, and marginal gain on a joint node graph, reaching 0.86 element coverage with 58% fewer rounds than fixed baselines on 50 labor-law cases.
-
An Ontology-Driven Graph RAG for Legal Norms: A Structural, Temporal, and Deterministic Approach
SAT-Graph RAG is a new ontology-driven temporal graph framework for legal RAG that models Works vs. Expressions, reuses versioned components for temporal states, and treats legislative events as queryable Action nodes to support deterministic point-in-time and causal queries.
-
Section-Weighted Hybrid Approach for Legal Case Retrieval
A section-aware hybrid retrieval system segments legal cases with an LLM, fuses BM25 and dense search via RRF, then applies Z-score normalized section-weighted comparisons to outperform baselines on a large benchmark.
-
Supervising the search process produces reliable and generalizable information-seeking agents
Process supervision via RAG-Gym produces more reliable and generalizable search agents, with gains driven by higher-quality queries on out-of-domain multi-hop tasks.
-
Retrieval-Augmented Generation for Natural Language Processing: A Survey
The survey organizes RAG methods via a taxonomy of query-based, logits-based, latent, and parametric fusion with comparisons on accessibility, efficiency, applications, and challenges.
-
Legal Reasoning Is Not Lawyering: Rethinking Legal Benchmarks for Pro Se Access to Justice
Legal AI benchmarks must evaluate robustness to pro se litigant inputs rather than expert-preprocessed ones to support access-to-justice claims.
-
Maat: The Agentic Legal Research Assistant for Competition Protection
Maat is a ReAct agent that orchestrates tools and RAG for competition law research, outperforming baselines on case-specific tasks while providing official citations.
-
Deepchecks: Evaluating Retrieval-Augmented Generation (RAG)
Deepchecks is a new multi-faceted evaluation framework for RAG that incorporates root cause analysis and production monitoring to assess reliability, relevance, and user satisfaction.
-
Navigating Global AI Regulation: A Multi-Jurisdictional Retrieval-Augmented Generation System
A RAG system for global AI regulation with type-specific chunking, conditional routing, and priority re-ranking achieves 0.87 average faithfulness and 0.84 relevancy on 50 test queries.
-
ReLeVAnT: Relevance Lexical Vectors for Accurate Legal Text Classification
ReLeVAnT achieves 99.3% accuracy and 98.7% F1 in binary legal document classification on LexGLUE via n-gram processing, contrastive score matching, and a shallow neural network after one-time keyword extraction.
-
LexPath: A domain-oriented multi-path framework for legal article retrieval
LexPath combines IRAC-guided sparse retrieval, structure-guided dense retrieval, and intent-aware reranking to outperform standard lexical, dense, hybrid, and RAG baselines on legal article retrieval benchmarks.
- CanLegalRAGBench: Evaluating Retrieval-Augmented Generation on Canadian Case Law
- Fine-grained Claim-level RAG Benchmark for Law