BayesRAG: Probabilistic Mutual Evidence Corroboration for Multimodal Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) has become a pivotal paradigm for Large Language Models (LLMs), yet current approaches struggle with visually rich documents by treating text and images as isolated retrieval targets. Existing methods relying solely on cosine similarity often fail to capture the semantic reinforcement provided by cross-modal alignment and layout-induced coherence. To address these limitations, we propose BayesRAG, a novel multimodal retrieval framework grounded in Bayesian inference and Dempster-Shafer evidence theory. Unlike traditional approaches that rank candidates strictly by similarity, BayesRAG models the intrinsic consistency of retrieved candidates across modalities as probabilistic evidence to refine retrieval confidence. Specifically, our method computes the posterior association probability for combinations of multimodal retrieval results, prioritizing text-image pairs that mutually corroborate each other in terms of both semantics and layout. Extensive experiments demonstrate that BayesRAG significantly outperforms state-of-the-art (SOTA) methods on challenging multimodal benchmarks. This study establishes a new paradigm for multimodal retrieval fusion that effectively resolves the isolation of heterogeneous modalities through an evidence fusion mechanism and enhances the robustness of retrieval outcomes. Our code is available at https://github.com/TioeAre/BayesRAG.

PARL: Position-Aware Relation Learning Network for Document Layout Analysis

Document layout analysis aims to detect and categorize structural elements (e.g., titles, tables, figures) in scanned or digital documents. Popular methods often rely on high-quality Optical Character Recognition (OCR) to merge visual features with extracted text. This dependency introduces two major drawbacks: propagation of text recognition errors and substantial computational overhead, limiting the robustness and practical applicability of multimodal approaches. In contrast to the prevailing multimodal trend, we argue that effective layout analysis depends not on text-visual fusion, but on a deep understanding of documents' intrinsic visual structure. To this end, we propose PARL (Position-Aware Relation Learning Network), a novel OCR-free, vision-only framework that models layout through positional sensitivity and relational structure. Specifically, we first introduce a Bidirectional Spatial Position-Guided Deformable Attention module to embed explicit positional dependencies among layout elements directly into visual features. Second, we design a Graph Refinement Classifier (GRC) to refine predictions by modeling contextual relationships through a dynamically constructed layout graph. Extensive experiments show PARL achieves state-of-the-art results. It establishes a new benchmark for vision-only methods on DocLayNet and, notably, surpasses even strong multimodal models on M6Doc. Crucially, PARL (65M) is highly efficient, using roughly four times fewer parameters than large multimodal models (256M), demonstrating that sophisticated visual structure modeling can be both more efficient and robust than multimodal fusion.

FocalOrder: Focal Preference Optimization for Reading Order Detection

Reading order detection is the foundation of document understanding. Most existing methods rely on uniform supervision, implicitly assuming a constant difficulty distribution across layout regions. In this work, we challenge this assumption by revealing a critical flaw: \textbf{Positional Disparity}, a phenomenon where models demonstrate mastery over the deterministic start and end regions but suffer a performance collapse in the complex intermediate sections. This degradation arises because standard training allows the massive volume of easy patterns to drown out the learning signals from difficult layouts. To address this, we propose \textbf{FocalOrder}, a framework driven by \textbf{Focal Preference Optimization (FPO)}. Specifically, FocalOrder employs adaptive difficulty discovery with exponential moving average mechanism to dynamically pinpoint hard-to-learn transitions, while introducing a difficulty-calibrated pairwise ranking objective to enforce global logical consistency. Extensive experiments demonstrate that FocalOrder establishes new state-of-the-art results on OmniDocBench v1.0 and Comp-HRDoc. Our compact model not only outperforms competitive specialized baselines but also significantly surpasses large-scale general VLMs. These results demonstrate that aligning the optimization with intrinsic structural ambiguity of documents is critical for mastering complex document structures.

GenProve: Learning to Generate Text with Fine-Grained Provenance

Large language models (LLM) often hallucinate, and while adding citations is a common solution, it is frequently insufficient for accountability as users struggle to verify how a cited source supports a generated claim. Existing methods are typically coarse-grained and fail to distinguish between direct quotes and complex reasoning. In this paper, we introduce Generation-time Fine-grained Provenance, a task where models must generate fluent answers while simultaneously producing structured, sentence-level provenance triples. To enable this, we present ReFInE (Relation-aware Fine-grained Interpretability & Evidence), a dataset featuring expert verified annotations that distinguish between Quotation, Compression, and Inference. Building on ReFInE, we propose GenProve, a framework that combines Supervised Fine-Tuning (SFT) with Group Relative Policy Optimization (GRPO). By optimizing a composite reward for answer fidelity and provenance correctness, GenProve significantly outperforms 14 strong LLMs in joint evaluation. Crucially, our analysis uncovers a reasoning gap where models excel at surface-level quotation but struggle significantly with inference-based provenance, suggesting that verifiable reasoning remains a frontier challenge distinct from surface-level citation.

Context-Adaptive Synthesis and Compression for Enhanced Retrieval-Augmented Generation in Complex Domains

Large Language Models (LLMs) excel in language tasks but are prone to hallucinations and outdated knowledge. Retrieval-Augmented Generation (RAG) mitigates these by grounding LLMs in external knowledge. However, in complex domains involving multiple, lengthy, or conflicting documents, traditional RAG suffers from information overload and inefficient synthesis, leading to inaccurate and untrustworthy answers. To address this, we propose CASC (Context-Adaptive Synthesis and Compression), a novel framework that intelligently processes retrieved contexts. CASC introduces a Context Analyzer & Synthesizer (CAS) module, powered by a fine-tuned smaller LLM, which performs key information extraction, cross-document consistency checking and conflict resolution, and question-oriented structured synthesis. This process transforms raw, scattered information into a highly condensed, structured, and semantically rich context, significantly reducing the token count and cognitive load for the final Reader LLM. We evaluate CASC on SciDocs-QA, a new challenging multi-document question answering dataset designed for complex scientific domains with inherent redundancies and conflicts. Our extensive experiments demonstrate that CASC consistently outperforms strong baselines.

MIRAGE: Scaling Test-Time Inference with Parallel Graph-Retrieval-Augmented Reasoning Chains

Large reasoning models (LRMs) have shown significant progress in test-time scaling through chain-of-thought prompting. Current approaches like search-o1 integrate retrieval augmented generation (RAG) into multi-step reasoning processes but rely on a single, linear reasoning chain while incorporating unstructured textual information in a flat, context-agnostic manner. As a result, these approaches can lead to error accumulation throughout the reasoning chain, which significantly limits its effectiveness in medical question-answering (QA) tasks where both accuracy and traceability are critical requirements. To address these challenges, we propose MIRAGE (Multi-chain Inference with Retrieval-Augmented Graph Exploration), a novel test-time scalable reasoning framework that performs dynamic multi-chain inference over structured medical knowledge graphs. Specifically, MIRAGE 1) decomposes complex queries into entity-grounded sub-questions, 2) executes parallel inference chains, 3) retrieves evidence adaptively via neighbor expansion and multi-hop traversal, and 4) integrates answers using cross-chain verification to resolve contradictions. Experiments on three medical QA benchmarks (GenMedGPT-5k, CMCQA, and ExplainCPE) show that MIRAGE consistently outperforms GPT-4o, Tree-of-Thought variants, and other retrieval-augmented baselines in both automatic and human evaluations. Additionally, MIRAGE improves interpretability by generating explicit reasoning chains that trace each factual claim to concrete chains within the knowledge graph, making it well-suited for complex medical reasoning scenarios. The code will be available for further research.

ChartReasoner: Code-Driven Modality Bridging for Long-Chain Reasoning in Chart Question Answering

Recently, large language models have shown remarkable reasoning capabilities through long-chain reasoning before responding. However, how to extend this capability to visual reasoning tasks remains an open challenge. Existing multimodal reasoning approaches transfer such visual reasoning task into textual reasoning task via several image-to-text conversions, which often lose critical structural and semantic information embedded in visualizations, especially for tasks like chart question answering that require a large amount of visual details. To bridge this gap, we propose ChartReasoner, a code-driven novel two-stage framework designed to enable precise, interpretable reasoning over charts. We first train a high-fidelity model to convert diverse chart images into structured ECharts codes, preserving both layout and data semantics as lossless as possible. Then, we design a general chart reasoning data synthesis pipeline, which leverages this pretrained transport model to automatically and scalably generate chart reasoning trajectories and utilizes a code validator to filter out low-quality samples. Finally, we train the final multimodal model using a combination of supervised fine-tuning and reinforcement learning on our synthesized chart reasoning dataset and experimental results on four public benchmarks clearly demonstrate the effectiveness of our proposed ChartReasoner. It can preserve the original details of the charts as much as possible and perform comparably with state-of-the-art open-source models while using fewer parameters, approaching the performance of proprietary systems like GPT-4o in out-of-domain settings.

TableEval: A Real-World Benchmark for Complex, Multilingual, and Multi-Structured Table Question Answering

LLMs have shown impressive progress in natural language processing. However, they still face significant challenges in TableQA, where real-world complexities such as diverse table structures, multilingual data, and domain-specific reasoning are crucial. Existing TableQA benchmarks are often limited by their focus on simple flat tables and suffer from data leakage. Furthermore, most benchmarks are monolingual and fail to capture the cross-lingual and cross-domain variability in practical applications. To address these limitations, we introduce TableEval, a new benchmark designed to evaluate LLMs on realistic TableQA tasks. Specifically, TableEval includes tables with various structures (such as concise, hierarchical, and nested tables) collected from four domains (including government, finance, academia, and industry reports). Besides, TableEval features cross-lingual scenarios with tables in Simplified Chinese, Traditional Chinese, and English. To minimize the risk of data leakage, we collect all data from recent real-world documents. Considering that existing TableQA metrics fail to capture semantic accuracy, we further propose SEAT, a new evaluation framework that assesses the alignment between model responses and reference answers at the sub-question level. Experimental results have shown that SEAT achieves high agreement with human judgment. Extensive experiments on TableEval reveal critical gaps in the ability of state-of-the-art LLMs to handle these complex, real-world TableQA tasks, offering insights for future improvements. We make our dataset available here: https://github.com/wenge-research/TableEval.

ChartMind: A Comprehensive Benchmark for Complex Real-world Multimodal Chart Question Answering

Chart question answering (CQA) has become a critical multimodal task for evaluating the reasoning capabilities of vision-language models. While early approaches have shown promising performance by focusing on visual features or leveraging large-scale pre-training, most existing evaluations rely on rigid output formats and objective metrics, thus ignoring the complex, real-world demands of practical chart analysis. In this paper, we introduce ChartMind, a new benchmark designed for complex CQA tasks in real-world settings. ChartMind covers seven task categories, incorporates multilingual contexts, supports open-domain textual outputs, and accommodates diverse chart formats, bridging the gap between real-world applications and traditional academic benchmarks. Furthermore, we propose a context-aware yet model-agnostic framework, ChartLLM, that focuses on extracting key contextual elements, reducing noise, and enhancing the reasoning accuracy of multimodal large language models. Extensive evaluations on ChartMind and three representative public benchmarks with 14 mainstream multimodal models show our framework significantly outperforms the previous three common CQA paradigms: instruction-following, OCR-enhanced, and chain-of-thought, highlighting the importance of flexible chart understanding for real-world CQA. These findings suggest new directions for developing more robust chart reasoning in future research.

What are they talking about? Benchmarking Large Language Models for Knowledge-Grounded Discussion Summarization

In this work, we investigate the performance of LLMs on a new task that requires combining discussion with background knowledge for summarization. This aims to address the limitation of outside observer confusion in existing dialogue summarization systems due to their reliance solely on discussion information. To achieve this, we model the task output as background and opinion summaries and define two standardized summarization patterns. To support assessment, we introduce the first benchmark comprising high-quality samples consistently annotated by human experts and propose a novel hierarchical evaluation framework with fine-grained, interpretable metrics. We evaluate 12 LLMs under structured-prompt and self-reflection paradigms. Our findings reveal: (1) LLMs struggle with background summary retrieval, generation, and opinion summary integration. (2) Even top LLMs achieve less than 69% average performance across both patterns. (3) Current LLMs lack adequate self-evaluation and self-correction capabilities for this task.