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…

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…

The paper introduces PaSBench-Video, a comprehensive streaming video benchmark designed to rigorously test multimodal LLMs' ability to issue proactive safety warnings, finding that current models stru…

This paper presents an open-source computer vision pipeline for classifying vehicle body types from naturalistic roadway video.

The paper introduces a new benchmark (BGTD) and a multimodal framework (mmTraffic) that enables explainable, evidence-grounded interpretation of encrypted network traffic using LLMs.

The paper introduces TWGuard, a linguistic context-optimized safety guardrail model, demonstrating that tailoring AI safety mechanisms to specific local linguistic contexts significantly improves perf…

The paper addresses the difficulty of using general vision-language models (VLMs) for fine-grained driver behavior recognition by creating a new, richly described dataset and demonstrating that fine-t…

The paper proposes a training-free framework, Visual Representation-Guided Video-LLM Reasoning, to perform composed video retrieval by using visual examples and text instructions, achieving strong per…

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 introduces Prosecution Decision Prediction (PDP), a new legal AI task that assesses prosecutorial review decisions, showing that current state-of-the-art LLMs perform significantly worse on…

The paper introduces CyberJurors, a multi-agent framework and the VerdictBench benchmark to simulate and solve complex e-commerce dispute verdicts by modeling the reasoning and consensus process of cr…

The paper evaluates the inconsistency of using LLMs as automated judges for multi-dimensional safety evaluations, finding that LLMs are unreliable for nuanced safety issues like financial advice but m…

The paper proposes CSMR, a cognitive scheduling framework that allows a language model to dynamically decide when to acquire task-relevant visual evidence, significantly improving multimodal reasoning…

The paper proposes InSemRAG, an enhanced RAG framework that improves retrieval accuracy and knowledge integrity by incorporating intent-aware retrieval and semantics-preserving chunking, achieving sta…

The paper introduces TechGraphRAG, an advanced, agentic RAG framework that enhances technical literature reasoning by integrating multi-step query refinement, external database searching, and knowledg…

The paper proposes a zero-shot reason-then-retrieve pipeline using Qwen3.5-27B to solve the challenging task of composed video retrieval (CoVR-R), achieving high performance on both validation and bli…

KidsNanny is a two-stage multimodal content moderation pipeline that achieves high accuracy and efficiency in detecting child safety threats, particularly excelling in text-embedded content.

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 TVIR, a new benchmark and multi-agent framework for deep research, to evaluate and improve the generation of factually reliable, text-visual interleaved reports.

The paper introduces a novel guardrail orchestration layer that improves the compliance and efficiency of high-stakes multimodal document generation by scoring multiple generated candidates against we…