The paper introduces CanLegalRAGBench, a new Canadian legal QA benchmark, and evaluates RAG systems, finding that while open-source models are competitive, automatic evaluations struggle with nuanced…

The paper introduces RefWalk, a novel framework designed to improve regulatory compliance question answering by ensuring rigorous citation traceability and explicit per-rule attribution across complex…

The paper introduces UA-Legal-Bench, a comprehensive Ukrainian legal reasoning benchmark built from a massive judicial corpus, demonstrating that LLM performance is highly task-dependent and that simp…

The paper introduces BenGER, a comprehensive benchmark for evaluating LLMs on German legal reasoning, demonstrating that closed-flagship models perform best and that human-AI co-creation significantly…

The paper introduces Citation Grounding (CG), a novel metric and framework, to systematically detect and reduce the hallucination of legal citations by verifying LLM outputs against a massive, structu…

The paper introduces CITETRACE, a large-scale dataset and evaluation framework that systematically measures structural citation failures in search-augmented LLMs, revealing a pattern called Verified M…

The paper introduces a Deep Research pipeline that significantly improves literature search recall and demonstrates that human-curated citation lists are often unreliable and do not serve as a true gr…

Xetrieval introduces an embedding-level framework to mechanistically explain dense retrieval decisions by decomposing high-dimensional embeddings into sparse, human-interpretable features.

The paper introduces 'bundesrecht,' an open-source, end-to-end pipeline for processing complex German statutory references, which parses, normalizes, and resolves raw citation strings into structured,…

The paper introduces Multi-Legal-Bench, a novel cross-jurisdictional benchmark evaluating LLMs on five standardized legal reasoning tasks across six diverse countries, demonstrating that cross-lingual…

The paper systematically compares multiple content representations for RAG pipelines and finds that answer retention—the ability of the representation to preserve the original answer-bearing content—i…

This paper proposes CompRank, a token-efficient reranking framework for large language models that reduces redundant computation and achieves strong reranking performance.

LegalGraphRAG introduces a multi-agent, hierarchical graph retrieval-augmented generation framework to overcome the limitations of traditional RAG in legal domains, achieving state-of-the-art reliable…

Persona prompting does not universally improve LLM performance; instead, it systematically trades increased expertise depth for reduced clarity, making multi-metric evaluation essential.

This paper demonstrates that targeted adaptation of the small language model Phi Silica, using dataset curation and fine-tuning, significantly improves its performance in short-form text rewriting, na…

The paper introduces a novel, training-free method to automatically generate fine-grained evaluation rubrics for LLM-as-a-Judge, and further proposes an iterative fine-tuning strategy that significant…

The paper proposes a comprehensive benchmark to systematically audit how varying persona prompts and model choices affect the technical quality and social representativeness of scholar recommendations…

The paper introduces CERA, a novel contrastive retrieval framework that improves RAG factuality and interpretability by using subjectivity-based hard negative selection and an auxiliary attention alig…