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

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…

SkillPager is a novel two-stage framework that efficiently selects minimal, execution-sufficient context from large procedural skill documents by leveraging typed semantic nodes, significantly reducin…

The paper proposes DART, a test-time adaptation method that enhances zero-resource dense retrieval reranking by adaptively tuning a bilinear scoring matrix using pseudo-positive and pseudo-negative ex…

The paper introduces Self-Conditioned Positional HNSW (SCP-HNSW), a method that modifies chunk embeddings and retrieval process to mitigate redundant evidence retrieval from overlapping document chunk…

The paper proposes BiRD, a bidirectional ranking defense mechanism that enhances the robustness of Retrieval-Augmented Generation (RAG) against adversarial attacks by analyzing the alignment between f…

HiKEY proposes a hierarchical, tree-based multimodal retrieval framework that significantly improves open-domain document question answering by addressing document routing and evidence fragmentation.

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…

This paper proposes a multi-turn retrieval-augmented generation pipeline for conversational systems across four domains.

The paper introduces Dr. DocBench, a difficulty-aware, comprehensive benchmark designed to rigorously test expert-level and challenging document parsing capabilities for VLMs, demonstrating that curre…

The paper proposes a novel KAN-enhanced BiGRU architecture to improve legal document classification and summarization in a low-resource, multilingual setting using Bengali and English legal texts.

This paper presents methods for ranking and unranking permutations avoiding a pattern of length three in lexicographic or colexicographic order.

The paper introduces SPECTRA, a scalable framework for generating large, synthetic, and controllable information retrieval test collections, demonstrating its ability to expose system scaling and fail…

This paper proposes Tail-Aware Adaptive-k (TAA-k), a training-free framework for adaptive context selection in retrieval-augmented generation systems using Extreme Value Theory.

The paper introduces TorchSight, an open-source local system using a fine-tuned Qwen 3.5 27B model that achieves high accuracy (95.0%) in classifying sensitive security documents without relying on ex…

The paper proposes a graph-constrained approach to scale multi-hop training data by decoupling path discovery from path verbalization, significantly expanding the usable corpus size for LLMs.

The paper introduces FOSSIL, a new multilingual dataset and specialized workflow designed to significantly improve the extraction of citations embedded within complex footnotes common in law and human…

This paper introduces a new benchmark dataset and evaluation framework for 'data snapshot extraction,' focusing on identifying and localizing semantically meaningful analytical artifacts within operat…

The paper introduces a typed claim network that models cross-document references by explicitly labeling the stance (e.g., agreement, disagreement) of a citation, significantly improving downstream tas…