OCR
-
CRITICS - Critical Science Without Borders: Language Models to Promote Critical Thinking in Science Education
2026-09-12 13:37:10Rodrigo Agerri, Itziar Aldabe, Elena Cabrio, Mark Cieliebak, Jan Deriu, Mariana Flores, Jurgita Kapociute-Dzikiene, Dovile Kuiziniene, Arantza Rico, Aritz Ruiz-Gonzalez, Aitor Soroa, Mantas Vaskevicius, Serena VillataAbstract
The CRITICS project addresses science accessibility and literacy by converging advanced Machine Translation (MT) based on Large Language Models (LLMs) with educational technology. By leveraging MT systems specifically optimized for scientific content, educational institutions can provide accurate, culturally relevant translations of scientific materials in students' native languages, ensuring that complex scientific concepts are comprehensible while maintaining technical accuracy. Building on these translations, the project explores the design and evaluation of innovative science teaching-learning proposals grounded in curriculum-aligned teaching-learning. Thus, CRITICS will investigate key components of scientific argumentation and critical thinking practices together with textual feedback aligned with learning objectives and assessment criteria inspired by competence-based evaluation frameworks. CRITICS aims to break down language barriers to accessing cutting-edge research and educational materials currently available only in high-resourced languages, thereby facilitating the democratization of scientific knowledge and fostering critical thinking in science education.
Abstract (translated)
URL
https://arxiv.org/abs/2609.13942
PDF
-
LePlanner: An Iterative Amortized Controller For World Models
2026-09-12 10:01:21Saksham Bansal, Om Naphade, Chayan Aggarwal, Vrishin MAbstract
World models trained with joint-embedding predictive architectures learn compact, structured latent representations from physical interaction, yet planning in these latent spaces typically relies on one of two costly approaches. Search-based planners such as CEM, MPPI, and iCEM optimize action sequences through many predictor rollouts, achieving strong performance at the cost of high per-decision compute and latency. Policy-based methods amortize inference into a single forward pass but can degrade on contact-rich tasks where the demonstration distribution is multimodal. We propose LePlanner, an amortized iterative controller that learns to construct and refine latent action sequences through a frozen world-model predictor. LePlanner is trained with an arrival-and-hold objective that encourages the controller to reach the goal at the earliest feasible horizon and remain there. This addresses horizon-reset procrastination, a failure mode in which repeated receding-horizon replanning continually postpones goal arrival. An additional action-Gaussian loss keeps generated actions near the support of the offline dataset. Across navigation, contact-rich manipulation, and continuous-control environments, LePlanner matches or exceeds search-based planners while requiring an order of magnitude fewer predictor evaluations and 3-49x lower wall-clock time per decision. It achieves success rates of 98% on PushT, 100% on Reacher, 100% on TwoRooms, and 92% on the OGBench Cube task. These results show that much of the structure discovered through online search can be amortized into a lightweight iterative policy, enabling fast, horizon-aware, nonlinear physical control without online optimization.
Abstract (translated)
URL
https://arxiv.org/abs/2609.13845
PDF
-
Beyond OCR Accuracy: Text-Centric VQA Under Image Degradation with Modular and End-to-End
2026-09-12 08:57:29Ritali Vatsi, Rachapudi Jagadeesh, Shruti Singh Baghel, Himani Sharma, Amit Shukla, Pawan GoyalAbstract
Text-centric Visual Question Answering (VQA) requires reading and reasoning over text embedded in images, a task made substantially harder when images suffer from real-world degradation such as motion blur, low resolution, or compression artifacts. While modular OCR-based pipelines and end-to-end vision-language models are both widely used for this task, their comparative robustness under degraded conditions remains underexplored. We present an empirical study comparing two modular pipelines with SA-DBNet, a custom detector architecture combining ResNet-18 with self-attention spatial modeling and deformable convolutions against an end-to-end vision-language baseline, evaluated on 4013 degraded images with 7000 question-answer pairs. Fine-tuned modular pipelines achieve up to 57.50% exact-match accuracy versus 38.00% for the end-to-end baseline, with domain-specific fine-tuning yielding a gain of up to 29.50 percentage points. Critically, we find that conventional OCR error metrics like Character Error Rate and Word Error Rate are unreliable predictors of downstream VQA performance, as semantic reasoning can compensate for recognition failures when contextual cues are present. These findings highlight the importance of task-aware evaluation for text-centric VQA systems under realistic visual conditions. Codes are available here
Abstract (translated)
URL
https://arxiv.org/abs/2609.13815
PDF
-
From Advertised Improvements to Measured Capabilities: Evaluating ChatGPT Images 2.5 on Forgery Tasks
2026-09-12 00:15:01Ankit Raj, Yuxin Zhang, Kidus Zewde, Tommy Duong, Jiaqi Gan, Xingyu Shen, Yuchen Zhou, Huaiyu Guo, Siyu Zhang, Simiao RenAbstract
We evaluate whether the improvements advertised for ChatGPT Images 2.5 translate into better performance on forgery tasks with predetermined answers. We compare its Flare and Sunburst API models with GPT-Image-2 re-run in the same week, using receipt-field edits, repeated editing, product placement and fine-print rendering. After image registration, Flare and Sunburst show fewer OCR-detected changes to surrounding receipt text (31.7% and 31.2% versus 44.2% for both GPT-Image-2 baselines), mainly on CORD receipts, without a detectable improvement in target-field correctness. Flare retains fewer earlier edits on CORD receipts, while photo-edit sequences provide little separation between models. Product codes are more often legible with Images 2.5, alongside larger product placement; the analyses do not establish a fidelity gain independent of size. Fine-print improvements remain unresolved below the OCR reliability limit. Refusals are rare and localisation is weak in both generations. At a fixed detection threshold, Community Forensics flags 68.6% of controlled Images 2.5 images averaged across cells, versus 35.9% of self-reported images posted online. These results motivate task-specific evaluation of advertised capabilities and defences, with explicit limits on what automatic checks can establish.
Abstract (translated)
URL
https://arxiv.org/abs/2609.13617
PDF
-
Online Video Agent Harness for Long Video Understanding
2026-09-11 13:13:03Sen Yang, Boqiang Duan, Jing Yang, Weihao Bo, Jie Liu, Boyuan Tong, Ze Feng, Wenkang Zhang, Jingdong Wang, Hua WuAbstract
Long video understanding often behaves like a visual needle-in-a-haystack problem: query-relevant evidence is sparsely distributed across long temporal spans, while packing dense frames into a single VLM context incurs \textit{context rot} and high cost. Existing video agents often rely on query-agnostic offline preprocessing or ad hoc tool sets, which can miss query-specific details and waste computation. In this work, we present VideoXAgent, a purely online video-agent harness for long video understanding that starts from the given video file and user query, plans and decomposes the task, invokes specialized expert tools on demand, and aggregates multimodal evidence to produce a final answer while resolving conflicts among observations. To support this on-demand invocation, we design a suite of heterogeneous expert tools guided by a data-driven taxonomy of atomic capabilities, spanning scripts, VLMs, and domain models (e.g., detection, OCR, ASR, face recognition). The harness further enforces objective evidence prompting and budget-aware control to curb hallucination and non-termination. Across Video-MME-Long, LongVideoBench-Long, LVBench, and MINERVA, VideoXAgent is competitive with frontier LMMs and video agents under a smaller context footprint---about 50k tokens of agent context per sample, even on hour-long videos. In particular, on complex video-reasoning benchmarks such as MINERVA, it matches this level while using only about 15\% of the context of a 1,024-frame dense-packing baseline. Notably, the harness remains effective with a visually weak or even text-only orchestrator, suggesting that strong long-video understanding can emerge from progressive agentic evidence seeking rather than from packing the full video into a single context. Project page: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2609.12818
PDF
-
ExpertHTR: Unified Handwritten Text Recognition with Multi-Task Learning and Sparse Mixture-of-Experts
2026-09-11 10:59:32Dang Hoai Nam, Nguyen Duy Hieu, Quang Huu Hieu, Vo Nguyen Le DuyAbstract
Handwritten text recognition resources are often small and distributed across collections that differ in language, script, document structure, and annotation format, making joint page-level training difficult. We propose ExpertHTR, a unified vision-language framework that addresses this problem through complementary supervision and conditional model capacity. Structural annotations from heterogeneous datasets are first organized through a common Page-Region-Line representation and used to construct four related training tasks for complete transcription, physical-line coverage, text localization, and localized recognition, without requiring additional manual labels. Building on a jointly trained dense model, ExpertHTR introduces a sparse Mixture-of-Experts architecture with an always-active shared branch and conditionally routed full-MLP experts. Sparsegen allows the number of active routed experts to vary with the hidden representation, while routing regularization reduces persistent concentration on a small subset of experts. Experiments on seven heterogeneous handwriting benchmarks show that complementary supervision consistently improves training with page transcription alone, while joint multi-source training provides further gains on most datasets. The proposed sparse expert model further improves the dense baseline on six of the seven sources. The final unified model also substantially outperforms the evaluated general-purpose OCR and vision-language systems on most benchmarks and achieves state-of-the-art performance on the IAM paragraph-level benchmark, while specialized HTR systems remain stronger on several challenging collections.
Abstract (translated)
URL
https://arxiv.org/abs/2609.12705
PDF
-
Detecting and Explaining Fake News Short Videos with Multimodal Content and Real-World Evidence
2026-09-11 10:24:20Yifeng Luo, Yupeng Li, Ming Tang, Jianxiong Guo, Liang LanAbstract
Short-video platforms have become a primary news source for the public, which has also enabled the widespread dissemination of fake news videos. We study the task of fake news video detection and explanation (FNVDE). Existing methods face two critical limitations. First, commonly used frame selection strategies may omit veracity-relevant cues or provide insufficient temporal context for understanding news videos. Second, prior methods neglect either multimodal understanding or evidence retrieval. To address these limitations, we propose NVKE-CEI, a unified system that integrates a news video keyframes extraction method (NVKE) and an FNVDE framework leveraging both content and evidence information (CEI). NVKE selects keyframes based on chronological changes in combined visual and OCR-text similarity. CEI employs two specialized LLM-based fact checkers (content-based and evidence-based) whose outputs are fused by a lightweight judge model. Extensive experiments show that NVKE-CEI outperforms state-of-the-art baselines while generating high-quality content-grounded explanations.
Abstract (translated)
URL
https://arxiv.org/abs/2609.12678
PDF
-
Epistemic orientation predicts legislative effectiveness among members of the US Congress
Abstract
Truth and evidence-based communication provide important foundations for democratic governance, accountability, and collective decision-making. Prior work shows that evidence-oriented language in US congressional floor speeches has declined since the mid-1970s, alongside broader changes in legislative productivity and polarization. This study shifts the analysis from congressional sessions to individual members of Congress to examine whether epistemic orientation varies systematically across legislators and whether it relates to political behavior and legislative effectiveness. Using the Evidence-Minus-Intuition (EMI) score, we measure the relative prevalence of evidence-oriented versus intuition-oriented language in congressional floor speeches and Twitter posts. We link these measures to legislator-level data on ideology, institutional position, communication context, and Legislative Effectiveness Score (LES). The results show that more ideologically extreme members use less evidence-oriented language on the congressional floor. EMI also exhibits cross-platform consistency with members who use more evidence-oriented language in floor speeches also being more evidence-oriented on Twitter, although EMI is lower on Twitter overall. Finally, EMI in congressional speeches is positively associated with individual legislative effectiveness, even after accounting for ideology and extensive political, institutional, demographic, topical, and communication volume controls. These findings suggest that evidence-oriented language is not only an aggregate feature of congressional discourse but also a meaningful attribute of individual-level legislative communication and effectiveness.
Abstract (translated)
URL
https://arxiv.org/abs/2609.11865
PDF
-
Evaluating Scaffolding-Oriented Multi-Agent Large Language Model System for Clinical Interview Training
2026-09-10 00:56:03Luming Yang, Haoxian Liu, Siqing Li, Rong Jia, Yue Xiao, Guanhua Chen, Li LuAbstract
Clinical education must prepare medical students to conduct safe and coherent patient interviews under conditions of uncertainty. Traditional standardized patient (SP) training is resource-intensive and difficult to scale. We developed a scaffolding-oriented multi-agent Large Language Model (LLM) AI Standardized Patient (AI-SP) training platform1. The system includes a patient agent for simulated dialog, a tutor agent providing Socratic prompts without disclosing diagnostic information, and a turn-level evaluator agent that monitors clinical progress without revealing summative scores. In a randomized controlled study (N = 100 medical students), participants were assigned to either a multi-agent (MA) scaffolding condition or a control condition. All students completed two learning sessions under their assigned condition followed by an examination conducted in a patient only environment. Performance was assessed using a standardized Objective Structured Clinical Examination (OSCE) based rubric. While no significant difference was observed in final diagnostic accuracy between groups, the multi-agent AI standardized patient system improved final examination scores compared to the control group utilizing structured progressive information disclosure; the most substantial and consistent improvements were observed in communication, the expression of empathy, and specific history-taking behaviors. These findings suggest that specialized LLM agents enhance the process quality of simulated clinical interviews without artificially inflating examination outcomes. To support future research, we release a multi-expert annotated dataset comprising transcripts, checklist annotations, turn-level evaluations, and OSCE-aligned scoring outcomes. This resource aims to facilitate the development of pedagogically grounded AI-SP systems and advance research on AI-supported clinical reasoning training.
Abstract (translated)
URL
https://arxiv.org/abs/2609.10939
PDF
-
Two-Token Features and Small-Large Ensembles for VLM Hallucination Detection
Abstract
We present our system for the SHROOM-Visions 2026 shared task on character-level VLM hallucination detection. A small ($4$B-parameter) VLM is fine-tuned as a per-token classifier reading a two-token feature from its own hidden states, and is ensembled with a $\sim$400B zero-shot VLM judge at prediction time. Both components see off-the-shelf OCR of any visible in-image text. We use synthetic hallucination data generated by the large model as a source of ensemble diversity, and use validation to select feature layer, training data and OCR grounding. Our official entry reaches mean Cor $0.487$ / Cor-lbl $0.387$ on the hidden test set, placing $6$th/$28$ (EN), $6$th/$21$ (FR), $8$th/$21$ (IT) and $7$th/$22$ (ZH) on the task's primary Cor-lbl metric.
Abstract (translated)
URL
https://arxiv.org/abs/2609.10244
PDF
-
Politics of Feelings: Emotional Expression and Legislative Effectiveness in the U.S. Congress
Abstract
Emotions are a pervasive feature of political communication, yet existing research has focused primarily on describing patterns of emotional expression rather than examining whether they are associated with consequential legislative outcomes. We address this gap by investigating the expression and correlates of discrete emotions in more than 1.7 million speeches delivered in the U.S. Congress between 1973 and 2024. Using a transformer-based emotion classifier, we measure eight discrete emotions: anger, fear, disgust, sadness, joy, enthusiasm, pride, and hope. We examine how these emotions vary over time, across policy topics, legislator characteristics, and their relationship with legislative effectiveness. We find that congressional speeches are becoming emotionally expressive over time. Emotional expression also varies systematically across policy domains and ideological positioning of legislators. Notably, the relationship between emotional expression and legislative effectiveness depends on the specific emotions expressed: enthusiasm and pride are positively associated with effectiveness, whereas anger exhibits a negative association. Emotional valence and emotional diversity are positively associated with legislative effectiveness, while emotional intensity is negatively associated with legislative effectiveness. These findings demonstrate that computationally derived measures of discrete emotions can provide insight into affective dimensions of legislative speeches and facilitate our understanding of how legislators communicate, interact, and perform within democratic institutions.
Abstract (translated)
URL
https://arxiv.org/abs/2609.10198
PDF
-
FlowCPO: A Unified Divergence View of Preference Alignment for Flow Models
2026-09-09 09:03:59Yansen Han, Shengyi Liao, Peng Sun, Deyuan Liu, Yuanxing Zhang, Pengfei Wan, Tao LinAbstract
Preference alignment for flow and diffusion models now spans online reinforcement learning and offline preference optimization, but the relation between these methods remains unclear. In particular, existing forward-process alignment methods require fresh samples from the current model, while offline methods based on fixed preference pairs rely primarily on positive-only fine-tuning or DPO-style likelihood-ratio surrogates. We organize these approaches through a divergence-based framework and introduce FlowCPO, an offline forward-KL objective that uses both preferred and dispreferred samples without online rollouts. For linear interpolation, we show under explicit regularity conditions that the forward-KL objective is bounded by a contrastive flow matching loss, yielding a tractable surrogate on fixed data. We further show that this loss is nonnegative, whereas the signed regression loss of simplified FlowDPO can be unbounded below. In the in-domain setting, FlowCPO achieves higher mean GenEval and OCR scores than the evaluated baselines, reaching 0.84 and 0.87 versus 0.81 and 0.74 for FlowDPO at CFG 3.0. In the out-of-domain setting, the results are mixed, with the best GenEval result but lower reward scores than RFT on several metrics.
Abstract (translated)
URL
https://arxiv.org/abs/2609.09905
PDF
-
Dynamics of meaning: Towards the Evaluation of Diachronic Semantic Change in Sinhala
2026-09-09 05:52:22Nevidu Jayatilleke, Nisansa de SilvaAbstract
Tracking semantic change in low-resource languages across extensive historical timelines presents significant challenges due to data scarcity and the limitations of static embedding alignments. This study investigates the diachronic evolution of the Sinhala language from the 13th to the 20th century using a multi-stage computational framework. We first align century-specific Word2Vec and FastText embeddings using Similarity Matrix Based Alignment (SMA) and Orthogonal Procrustes (OP) techniques, finding that OP alignment provides more stable neighbourhood tracking for identifying temporal similarity dips. To move beyond aggregate measures, we introduce a Bidirectional Semantic Impact Pruning approach using contextualised embeddings from a fine-tuned Llama-3.1-8B. By applying Leave-One-Out (LOO) diagnostics, we attempt to isolate influential sentences to distinguish between systemic semantic shifts and transient polysemic expansion. Our results show that semantic drift in the fine-tuned Llama-3.1-8B is not evenly distributed across all usages. Instead, a significant part of the change is driven by a smaller set of high-impact contextual instances, rather than gradual and uniform change across all occurrences. This work provides a preliminary framework for diachronic analysis in low-resource contexts, highlighting the trade-offs between model sensitivity and data availability.
Abstract (translated)
URL
https://arxiv.org/abs/2609.08609
PDF
-
An Experimental Evaluation of Multimodal Prompt Injection Attacks on Agentic AI Frameworks
2026-09-08 20:00:03Viet K. Nguyen, Mohammad I. HusainAbstract
Agentic AI frameworks let a language model plan, keep memory, and call tools that reach real files, mail, and services. Most of these agents also read images, which gives an attacker a way to put text into the agent's context without going through the user. We present MMPIBench, a reproducible benchmark that measures what happens next. It delivers a fixed set of attacks through six visual carriers (OCR text, overlays, EXIF metadata, QR codes, fake interfaces, and hybrids) and records how far each injected instruction travels through the agent, from perception through planning to the tool call. Across 720 runs covering six frameworks, five foundation models, six carriers, and four attacker objectives, attacks complete in approximately 1% of runs but are attempted in 12.8%, and the gap is closed almost entirely at the planning step, where the model reads the injected instruction and declines to act on it. The model matters far more than the framework for whether an instruction is acted on. One model never attempts an attack and recognizes the injection in 59.7% of runs, while two others attempt in 23.6%. We then extend the benchmark to audio, the only other raw perceptual channel current frontier models accept. Only two of the five models ingest audio and only three of the six frameworks deliver it, but where the signal arrives the attack completes in 49% of cells, and in 75% for one model. Reporting completion alone therefore understates exposure, and perceptual channels beyond vision are narrower but much less defended.
Abstract (translated)
URL
https://arxiv.org/abs/2609.09404
PDF
-
The Living Library: Transforming Archival Collections into Conversational Knowledge Systems -- Lessons from the Theodore Roosevelt Presidential Library
2026-09-08 19:01:22Pengce Wang, Lucia Ronchi Darre, Matt Briney, Michaell Bakalars, Dan Rutkowski, Ursula Hardy, David Wolf, Laura Hoffman, Allen Kim, Shawn Wright, Juan Lavista FerresAbstract
We present the Living Library, an end-to-end framework for transforming fragmented digital archives into governed, conversational, in-person exhibit experiences. Developed and deployed at the Theodore Roosevelt Presidential Library, the framework comprises four layers: digitization and corpus creation, AI-powered processing, retrieval and reasoning, and an optional embodied conversational interface. The first three layers aggregate a 300,000-record collection, apply OCR and structured metadata enrichment for expert curatorial review, and publish records to a hybrid dense/semantic index. Expert review is conducted through the Archivist App, a curator-facing interface that supports correction of AI-generated transcriptions and metadata. The governed corpus powers both a researcher-facing interface and Talk to TR, a continuously operating exhibit that embodies Theodore Roosevelt as a full-scale digital human within a museum environment. To support live, face-to-face interactions, Cross-Era Analogical Grounding reframes contemporary questions through documented historical parallels, allowing Roosevelt to address present-day topics without inventing facts. Dual-path retrieval and end-to-end streaming keep responses grounded and responsive. Layered watchdogs, visitor-session isolation, automated conversation management, and independently restartable services enable reliable unattended operation for hundreds of visitors. Avatar realism, spatial audio, lighting, staging, and conversational design are developed and evaluated as an integrated experience. Rather than report a controlled benchmark, we describe lessons from operating Talk to TR as a public exhibit and offer a transferable model for transforming archival collections into believable, in-person conversational experiences.
Abstract (translated)
URL
https://arxiv.org/abs/2609.09368
PDF
-
SQLMorph: Query Mutation and Fine-Grained Metrics for Text-to-SQL Evaluation
2026-09-08 16:08:43Mohammadhossein Malekpour, Mohamed Riahi, Maxime Lamothe, Amine MhedhbiAbstract
Text-to-SQL systems translate natural language queries into executable SQL, democratizing access to structured data. Despite recent advances driven by large language models (LLMs), evaluation remains a major bottleneck: public benchmarks fail to capture the complexity of enterprise schema, while building private evaluation sets is costly and nondeterministic, making evaluation results difficult to reproduce. To address this issue, we present SQLMorph, a framework for Text-to-SQL evaluation via query mutation. SQLMorph introduces two techniques to automatically generate and expand evaluation sets: Join Query Expansion (JQE), which systematically increases structural complexity through valid join additions, and Textual Query Augmentation (TQA), which generates controlled natural language perturbations to assess robustness to linguistic variation. JQE and TQA create targeted choke points to challenge specific system components. When applied to state-of-the-art systems, JQE increases query coverage and reveals accuracy degradation as the number of joins grows. Meanwhile, TQA shows that linguistic brittleness induced by heavy abbreviation can reduce accuracy by up to 17%. Beyond evaluation sets, SQLMorph introduces a family of execution-level metrics that address the limitations of current binary measures, such as Execution Accuracy. We define Execution Precision (EXP) and Execution Recall (EXR) to quantify the fraction of correct and recovered results, respectively, and combine them via F1 for unified scoring. Our experiments show that these relaxed metrics enable fine-grained analysis of over- and under-prediction, revealing differences across systems that binary metrics obscure. Together, SQLMorph's query mutation and fine-grained metrics support debugging and better align Text-to-SQL evaluation practices with real-world deployments.
Abstract (translated)
URL
https://arxiv.org/abs/2609.08950
PDF
-
ICDAR2026 Competition on Multimodal Reasoning over Documents in Multiple Domains
2026-09-08 10:04:13Artemis Llabr\'es, Marc Serra Ortega, Tom\`as Ockier, Samuel Ortega Cuadra, Amritpal Singh, Christos Georgakilas, Andrey Barsky, Ernest Valveny, Dimosthenis KaratzasAbstract
In this report we present results of the ICDAR2026 Competition on Multimodal Reasoning over Documents in Multiple Domains. This competition aimed to advance research in document understanding through the task of Visual Question Answering (VQA). Building upon previous DocVQA benchmarks, this competition introduces challenging reasoning questions over a diverse collection of documents spanning eight domains, including business reports, scientific papers, slides, posters, maps, comics, infographics, and engineering drawings. The competition concluded with 20 valid submissions from 8 teams spanning zero-shot VLMs, OCR and parser-augmented pipelines, agentic retrieval systems, multi-agent ensembles, and fine-tuned multimodal models. The results show that the strongest systems move beyond single-pass prompting and instead rely on structured evidence extraction, retrieval, verification, and orchestration across multiple components.
Abstract (translated)
URL
https://arxiv.org/abs/2609.25055
PDF
-
Capability-Routed Visual Retrieval and Evidence Threading for Long-Context Document Question Answering
2026-09-07 16:56:47Amirul Rahman, Aisha Karim, Kenji Nakamura, Yi-Fan NgAbstract
Annual reports, diligence packs, and infographic dashboards bury numbers in page images: axes, cell grids, and footnotes that OCR pipelines flatten and that page-level visual retrievers still treat as interchangeable in-context examples. We keep a frozen Qwen2.5-VL-7B-Instruct generator and a ColPali / VisRAG-Ret page index, and insert three modules. A capability-aware visual router (CAVR) tags each retrieved page as text, table, chart, layout, or mixed and mixes specialist experts before generation. Weak-to-strong page selection (WSPS) distils a frozen 7B answerability teacher into a 3B selection head so ranking is no longer a single InfoNCE score. Visual evidence threading (VET) builds layout-anchored paths of length at most three and lets the generator read the thread rather than a flat top-$k$ list. On gold-page DocVQA / ChartQA / InfographicVQA the 7B system reaches 96.3 / 90.1 / 85.4. Under the VisRAG top-3 protocol the mean generation accuracy is 62.74 versus 59.39 for the same backbone with concatenation. On MMLongBench-Doc retrieve-then-read, F1 moves from 19.2 to 22.6 and multi-page accuracy from 16.4 to 21.2. ViDoRe nDCG@5 after WSPS reranking is 83.6, with TAT-DQA financial reports at 70.4.
Abstract (translated)
URL
https://arxiv.org/abs/2609.13268
PDF
-
Structure-Token Evidence-Anchored Reasoning for Scientific Chart Understanding
2026-09-07 16:49:15Alberlucia Rafael Soarez, Camila Ferreira, Daniel Kim, Mariana Costa, Alejandro TorresAbstract
Scientific charts encode quantities in axes, legends, and geometric marks, yet large vision-language models still treat them as natural photographs. Visual in-context examples do not expose the coordinate frame; unconstrained chain-of-thought can name a plausible number that was never read from a bar. We present STEER (Structure-Token Evidence-anchored Reasoning), which freezes a Llama-3.2-Vision encoder and inserts three modules: a chart structure graph encoder (CSGE) that binds ticks, legend items, and marks; evidence-anchored step reasoning (EASR) that forces every arithmetic step to cite a graph node; and weak-parser strong-reasoner alignment (WPSR) that uses a specialized table extractor only as a teacher of node attributes. On ChartQA, STEER reaches 82.70 average relaxed accuracy versus 80.16 for ChartGemma and 76.40 for a LLaVA-CoT backbone trained on the same mix. Gains widen on CharXiv reasoning (33.60 vs. 29.20 InternVL Chat V1.5) and ChartQAPro CoT (40.70 vs. 37.17 Qwen2-VL-7B), where OCR shortcuts disappear. Ablations show that dropping node serialization or numeric candidate constraints undoes most of the reasoning lift.
Abstract (translated)
URL
https://arxiv.org/abs/2609.13267
PDF
-
Open Tabular Insight Extraction: Where Do We Stand, and Where Should We Go?
2026-09-07 15:27:58Daniel Gomm, Maarten de Rijke, Madelon HulsebosAbstract
Democratizing access to the knowledge held in large corpora of tables such as data lakes is emerging as a central research challenge. Research in this space is advancing and broadening in scope, increasingly supplying the components to satisfy a person's insight need end-to-end. Yet these efforts remain fragmented across communities that frame the problem under their own conventions, such as table question answering, text-to-SQL, and data analysis agents, with works six times as likely to cite within the same task label as across labels. To bring these communities onto common ground, we establish a holistic framework for this pursuit, which we refer to as Open Tabular Insight Extraction (OpenTI). We formalize OpenTI from first principles around the analytical knowledge a person needs, the procedure for deriving it from a corpus of tables, and how well a result serves the person who sought it. In doing so we consolidate frameworks and terminology across information retrieval, natural language processing, machine learning, databases, and human-computer interaction, and apply this grounding in a systematic review and analysis of systems and benchmarks that work towards OpenTI. We find that current systems do not cover the end-to-end scope of OpenTI, mainly focusing on the analysis itself, and that benchmarks are largely unfit for evaluations in an open setting as inputs presuppose knowledge of tables, and validation mechanisms do not match the setup. Finally, we distill a research agenda towards OpenTI systems, evaluation, and interaction paradigms that surface the insights users need. An interactive companion to our paper is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.07629
PDF
