LLM Grounding

This paper presents the joint participation of the BIT.UA and AAUBS groups in the ArchEHR-QA 2026 shared task, which focuses on clinical question answering and evidence grounding in a low-resource setting. Due to the absence of training data and the strict data privacy constraints inherent to the healthcare domain (e.g. GDPR), we investigate the capabilities of Large Language Models (LLMs) without weight updates. We evaluate several state-of-the-art proprietary models and locally deployable open-source alternatives using various prompt engineering strategies, including task decomposition, Chain-of-Thought, and in-context learning. Furthermore, we explore majority voting and LLM-as-a-judge ensembling techniques to maximize predictive robustness. Our results demonstrate that while proprietary models exhibit strong resilience to prompt variations, domain-adapted open-source models (such as MedGemma 3 27B) achieve highly competitive performance when paired with the right prompt. Overall, our prompt-based approach proved highly effective, securing 1st place in Subtask 4 (evidence citation alignment) and 3rd place in Subtask 3 (patient-friendly answer generation). All code, results, and prompts are available on our GitHub repository: https://github.com/bioinformatics-ua/ArchEHR-QA-2026.

Molecular property models increasingly support high-stakes drug-discovery decisions, but their outputs are often difficult to audit: classical predictors return scores without rationale, while language models can produce fluent explanations weakly grounded in the input molecule. We introduce Bolek, a compact multimodal language model that grounds natural-language reasoning in molecular structure by injecting a Morgan fingerprint embedding into an instruction-tuned text decoder. Bolek is fine-tuned on molecular alignment tasks, including molecule description, RDKit descriptor prediction, and substructure detection, and on downstream reasoning over 15 TDC binary classification tasks using synthetic chains-of-thought anchored in concrete molecular features. Across these tasks, Bolek outperforms its Qwen3-4B-Instruct base on all endpoints in yes/no mode and on 13 of 15 in chain-of-thought mode, raising mean ROC/PR AUC from 0.55 to 0.76. It also outperforms TxGemma-9B-Chat on 13 of 15 binary classification tasks despite being less than half its size. Bolek's explanations are more grounded than those of the baseline LLMs: it cites numerical descriptors 10-100x more often per chain-of-thought, and the cited values agree strongly with RDKit for key descriptors such as TPSA, MolLogP, and MolWt (Spearman rho = 0.87-0.91). Generalisation extends beyond the training panel: on 15 unseen TDC classification endpoints, Bolek matches TxGemma on five, and it produces non-trivial rank correlations on three held-out regression endpoints despite never seeing downstream regression during training. These results suggest that targeted modality injection and reasoning supervision tied to verifiable molecular features can yield compact, auditable molecular reasoning models.

With the rapid advancement of large language models (LLMs), classic graph learning tasks have greatly benefited from LLMs, including improved encoding of textual features, more efficient construction of graphs from text, and enhanced reasoning over knowledge graphs. In this paper, we ask a complementary question: How can graphs help LLMs? We address this question from three perspectives: 1) graphs provide an up-to-date knowledge source that helps reduce LLM hallucinations, 2) graph-based prompting techniques-such as Chain-of-Thought (CoT), Tree-of-Thought (ToT), and Graph-of-Thought (GoT)-enhance LLM reasoning capabilities, and 3) integrating graphs into LLMs improves their understanding of structured data, expanding their applicability to domains such as e-commerce, code, and relational databases (RDBs). We further outlook some future directions including designing sparse LLM architectures based on graphs and brain-inspired memory systems.

Authoritative competency frameworks such as ESCO, ROME, and O*NET are essential for aligning education with labor market needs, yet their technical complexity and structural heterogeneity hinder practical adoption by educators. This paper introduces SkillGraph-Service, an interoperable microservice designed to bridge this gap by unifying these resources into a provenance-preserving Knowledge Graph (KG). Adopting a KG-first, LLM-fallback architecture, the system combines symbolic rigor with sub-symbolic flexibility. It implements a lightweight hybrid retrieval engine (fusing SQLite FTS5 and HNSW vector search) to handle the vocabulary mismatch in educator queries, and utilizes Large Language Models (LLMs) strictly for constrained ranking and audience-aware explanation. Empirical evaluation on a multilingual dataset reveals that the proposed hybrid strategy achieves superior retrieval effectiveness (nDCG@5>0.94) with sub-200 ms latency, rendering computationally expensive cross-encoder re-ranking may be unnecessary for this domain. Furthermore, an analysis of generated explanations highlights a trade-off between fluency and faithfulness: while JSON-constrained LLMs ensure high citation precision, deterministic templates remain the most reliable method for maximizing evidence coverage. The resulting architecture offers a practical, scalable, and auditable solution for integrating complex skill data into digital learning ecosystems.

When a language model answers a table question, users have no way to verify which cells informed which reasoning steps. We introduce RSAT, a method that trains small language models (SLMs, 1-8B) to produce step-by-step reasoning with cell-level citations grounded in table evidence. Phase 1 (SFT) teaches a structured JSON output format from verified reasoning traces. Phase 2 (GRPO) optimizes a composite reward centered on NLI-based faithfulness, alongside citation validity and parsimony. Across six models from two families-Qwen 2.5 (1.5B/3B/7B) and Llama 3 (1B/3B/8B)-RSAT improves faithfulness 3.7$\times$ over SFT alone (0.224$\rightarrow$0.826), with near-perfect citation validity (0.992). Post-hoc attribution collapses below 13% format success, confirming that attribution must be integrated into reasoning, not retrofitted. Ablations show the faithfulness reward is essential: removing it drops faithfulness from 0.97 to 0.03.

Today's AI assistants such as OpenClaw are designed to handle context effectively, making context learning an increasingly important capability for models. As these systems move beyond professional settings into everyday life, the nature of the contexts they must handle also shifts. Real-life contexts are often messy, fragmented, and deeply tied to personal and social experience, such as multi-party conversations, personal archives, and behavioral traces. Yet it remains unclear whether current frontier language models can reliably learn from such contexts and solve tasks grounded in them. To this end, we introduce CL-bench Life, a fully human-curated benchmark comprising 405 context-task pairs and 5,348 verification rubrics, covering common real-life scenarios. Solving tasks in CL-bench Life requires models to reason over complex, messy real-life contexts, calling for strong real-life context learning abilities that go far beyond those evaluated in existing benchmarks. We evaluate ten frontier LMs and find that real-life context learning remains highly challenging: even the best-performing model achieves only 19.3% task solving rate, while the average performance across models is only 13.8%. Models still struggle to reason over contexts such as messy group chat histories and fragmented behavioral records from everyday life. CL-bench Life provides a crucial testbed for advancing real-life context learning, and progress on it can enable more intelligent and reliable AI assistants in everyday life.

Patient portals now give individuals direct access to their electronic health records (EHRs), yet access alone does not ensure patients understand or act on the complex clinical information contained in these records. The ArchEHR-QA 2026 shared task addresses this challenge by focusing on grounded question answering over EHRs, and this paper presents the system developed by the HealthNLP_Retrievers team for this task. The proposed approach uses a multi-stage cascaded pipeline powered by the Gemini 2.5 Pro large language model to interpret patient-authored questions and retrieve relevant evidence from lengthy clinical notes. Our architecture comprises four integrated modules: (1) a few-shot query reformulation unit which summarizes verbose patient queries; (2) a heuristic-based evidence scorer which ranks clinical sentences to prioritize recall; (3) a grounded response generator which synthesizes professional-caliber answers restricted strictly to identified evidence; and (4) a high-precision many-to-many alignment framework which links generated answers to supporting clinical sentences. This cascaded approach achieved competitive results. Across the individual tracks, the system ranked 1st in question interpretation, 5th in answer generation, 7th in evidence identification, and 9th in answer-evidence alignment. These results show that integrating large language models within a structured multi-stage pipeline improves grounding, precision, and the professional quality of patient-oriented health communication. To support reproducibility, our source code is publicly available in our GitHub repository

Retrieval-Augmented Generation (RAG) grounds Large Language Models in external knowledge, yet current evaluations rely on discrete heuristics that suffer from ''epistemic blindness'' - failing to distinguish genuine contextual information extraction from parametric memory recall. To address this, we introduce the Normalized Context Utilization (NCU) metric, leveraging continuous token log-probabilities across zero-shot, oracle, and adversarial conditions to strictly quantify contextual information gain. Evaluating architectures ranging from 1.5B to 72B parameters alongside a proprietary commercial API reveals that for strict factual extraction (without Chain-of-Thought reasoning), traditional scaling laws exhibit extreme diminishing returns: highly efficient Small Language Models (SLMs) match or outperform high-capacity architectures. Furthermore, we demonstrate that ``Prior Dominance'' correlates with model scale and proprietary alignments. The evaluated commercial API not only overrode explicit external evidence in nearly half of adversarial conflicts, but also frequently suffered from systemic confidence collapse (Negative Transfer) when its parametric priors were contradicted. Our findings highlight the structural epistemic advantage and superior contextual adherence of SLMs in strict extraction workflows.

Do large language models (LLMs) truly acquire embodied cognition and cultural conventions from text? We introduce demonstratives, fundamental spatial expressions like "this/that" in English and "zhè/nà" in Chinese, as a novel probe for grounded knowledge. Using 6,400 responses from 320 native speakers, we establish a human baseline: English speakers reliably distinguish proximal-distal referents but struggle with perspective-taking, while Chinese speakers switch perspectives fluently but tolerate distal ambiguity. In contrast, five state-of-the-art LLMs fail to inherently understand the proximal-distal contrast and show no cultural differences, defaulting to English-centric reasoning. Our study contributes (i) a new task, based on demonstratives, as a new lens for evaluating embodied cognition and cultural conventions; (ii) empirical evidence of cross-cultural asymmetries in human interpretation; (iii) a new perspective on the egocentric-sociocentric debate, showing both orientations coexist but vary across languages; and (iv) a call to address individual variation in future model design.

Video Temporal Grounding (VTG), the task of localizing video segments from text queries, struggles in open-world settings due to limited dataset scale and semantic diversity, causing performance gaps between common and rare concepts. To overcome these limitations, we introduce OmniVTG, a new large-scale dataset for open-world VTG, coupled with a Self-Correction Chain-of-Thought (CoT) training paradigm designed to enhance the grounding capabilities of Multimodal Large Language Models (MLLMs). Our OmniVTG is constructed via a novel Semantic Coverage Iterative Expansion pipeline, which first identifies gaps in the vocabulary of existing datasets and collects videos that are highly likely to contain these target concepts. For high-quality annotation, we leverage the insight that modern MLLMs excel at dense captioning more than direct grounding and design a caption-centric data engine to prompt MLLMs to generate dense, timestamped descriptions. Beyond the dataset, we observe that simple supervised finetuning (SFT) is insufficient, as a performance gap between rare and common concepts still persists. We find that MLLMs' video understanding ability significantly surpasses their direct grounding ability. Based on this, we propose a Self-Correction Chain-of-Thought (CoT) training paradigm. We train the MLLM to first predict, then use its understanding capabilities to reflect on and refine its own predictions. This capability is instilled via a three-stage pipeline of SFT, CoT finetuning, and reinforcement learning. Extensive experiments show our approach not only excels at open-world grounding in our OmniVTG dataset but also achieves state-of-the-art zero-shot performance on four existing VTG benchmarks. Code is available at https://github.com/oceanflowlab/OmniVTG.

LLMs deployed for natural-language querying of analytical databases suffer from two intertwined failures - incorrect answers and confident hallucinations - both rooted in the same cause: the model is forced to infer business semantics that the schema does not encode. We test whether supplying those semantics as context closes the gap. We benchmark three frontier LLMs (Claude Opus 4.7, Claude Sonnet 4.6, GPT-5.4) on 100 natural-language questions over the Cleaned Contoso Retail Dataset in ClickHouse, using a paired single-shot protocol. Each model is evaluated twice: once given only the warehouse schema, and once given the schema plus a 4 KB hand-authored markdown document describing the dataset's measures, conventions, and disambiguation rules. Adding the document improves accuracy by +17 to +23 percentage points across all three models. With it, the three models are statistically indistinguishable (67.7-68.7%); without it, they are also indistinguishable (45.5-50.5%). Every cross-cluster comparison is significant at p < 0.01. The presence of the semantic-layer document accounts for essentially all of the significant variance; model choice within tier does not. We interpret this as a structural result: explicit business semantics suppress the dominant class of text-to-SQL errors not by making the model more capable, but by changing what the model is being asked to do.

Extracting abstract causal structures and applying them to novel situations is a hallmark of human intelligence. While Large Language Models (LLMs) and Vision Language Models (VLMs) have shown strong performance on a wide range of reasoning tasks, their capacity for interactive causal learning -- inducing latent structures through sequential exploration and transferring them across contexts -- remains uncharacterized. Human learners accomplish such transfer after minimal exposure, whereas classical Reinforcement Learning (RL) agents fail catastrophically. Whether state-of-the-art Artificial Intelligence (AI) models possess human-like mechanisms for abstract causal structure transfer is an open question. Using the OpenLock paradigm requiring sequential discovery of Common Cause (CC) and Common Effect (CE) structures, here we show that models exhibit fundamentally delayed or absent transfer: even successful models require initial environmental-specific mapping -- what we term environmental grounding -- before efficiency gains emerge, whereas humans leverage prior structural knowledge from the very first solution attempt. In the text-only condition, models matched or exceeded human discovery efficiency. In contrast, visual information -- in both the image-only and text-and-image conditions -- overall degraded rather than enhanced performance, revealing a broad reliance on symbolic processing rather than integrated multimodal reasoning. Models further exhibited systematic CC/CE asymmetries absent in humans, suggesting heuristic biases rather than direction-neutral causal abstraction. These findings reveal that large-scale statistical learning does not produce the decontextualized causal schemas underpinning human analogical reasoning, establishing grounding-dependent transfer as a fundamental limitation of current LLMs and VLMs.

While Multimodal Large Language Models (MLLMs) have enhanced grounding capabilities in general scenes, their robustness in crowded scenes remains underexplored. Crowded scenes entail visual challenges (i.e., occlusion and small objects), which impair object semantics and degrade grounding performance. In contrast, language expressions are immune to such degradation and preserve object semantics. In light of these observations, we propose a novel method that overcomes such constraints by leveraging Language-Guided Semantic Cues (LGSCs). Specifically, our approach introduces a Semantic Cue Extractor (SCE) to derive semantic cues of objects from the visual pipeline of an MLLM. We then guide these cues using corresponding text embeddings to produce LGSCs as linguistic semantic priors. Subsequently, they are reintegrated into the original visual pipeline to refine object semantics. Extensive experiments and analyses demonstrate that incorporating LGSCs into an MLLM effectively improves grounding accuracy in crowded scenes.

The capabilities of AI-assisted coding are progressing at breakneck speed. Chat-based vibe coding has evolved into fully fledged AI-assisted, agentic software development using agent scaffolds where the human developer creates a plan that agentic AIs implement. One current trend is utilizing documents beyond this plan document, such as project and method-scoped documents. Here we propose GROUNDING$.$md, a community-governed, field-scoped epistemic grounding document, using mass spectrometry-based proteomics as an example. This explicit field-scoped grounding document encodes Hard Constraints (non-negotiable validity invariants empirically required for scientific correctness) and Convention Parameters (community-agreed defaults) that override all other contexts to enforce validity, regardless of what the user prompts. In practice, this will empower a non-domain expert to generate code, tools, and software that have best practices baked in at the ground level, providing confidence to the software developer but also to those reviewing or using the final product. Undoubtedly it is easier to have agentic AIs adhere to guidelines than humans, and this opportunity allows for organizations to develop epistemic grounding documents in such a way as to keep domain experts in the loop in a future of democratized generation of bespoke software solutions.

Summarizing long, domain-specific documents with large language models (LLMs) remains challenging due to context limitations, information loss, and hallucinations, particularly in clinical and legal settings. We propose a Discrete Wavelet Transform (DWT)-based multi-resolution framework that treats text as a semantic signal and decomposes it into global (approximation) and local (detail) components. Applied to sentence- or word-level embeddings, DWT yields compact representations that preserve overall structure and critical domain-specific details, which are used directly as summaries or to guide LLM generation. Experiments on clinical and legal benchmarks demonstrate comparable ROUGE-L scores. Compared to a GPT-4o baseline, the DWT based summarization consistently improve semantic similarity and grounding, achieving gains of over 2% in BERTScore, more than 4% in Semantic Fidelity, factual consistency in legal tasks, and large METEOR improvements indicative of preserved domain-specific semantics. Across multiple embedding models, Fidelity reaches up to 97%, suggesting that DWT acts as a semantic denoising mechanism that reduces hallucinations and strengthens factual grounding. Overall, DWT provides a lightweight, generalizable method for reliable long-document and domain-specific summarization with LLMs.

Large language models have achieved remarkable progress on complex reasoning tasks. However, they often implicitly fabricate information when inputs are incomplete, producing confident but unreliable conclusions -- a failure mode we term ungrounded reasoning. We argue that this issue arises not from insufficient reasoning capability, but from the lack of inferential boundary awareness -- the ability to recognize when the necessary premises for valid inference are missing. To address this issue, we propose Grounded Reasoning via Interactive Reinforcement Learning (GRIL), a multi-turn reinforcement learning framework for grounded reasoning under incomplete information. GRIL decomposes the reasoning process into two stages: clarify and pause, which identifies whether the available information is sufficient, and grounded reasoning, which performs task solving once the necessary premises are established. We design stage-specific rewards to penalize hallucinations, enabling models to detect gaps, stop proactively, and resume reasoning after clarification. Experiments on GSM8K-Insufficient and MetaMATH-Insufficient show that GRIL significantly improves premise detection (up to 45%), leading to a 30% increase in task success while reducing average response length by over 20%. Additional analyses confirm robustness to noisy user responses and generalization to out-of-distribution tasks.

Large language models (LLMs) are now deployed worldwide, inspiring a surge of benchmarks that measure their multilingual and multicultural abilities. However, these benchmarks prioritize generic language understanding or superficial cultural trivia, leaving the evaluation of grounded tasks -- where models must reason within real-world, context-rich scenarios -- largely unaddressed. To fill this gap, we present CulturALL, a comprehensive and challenging benchmark to assess LLMs' multilingual and multicultural competence on grounded tasks. CulturALL is built via a human--AI collaborative framework: expert annotators ensure appropriate difficulty and factual accuracy, while LLMs lighten the manual workload. By incorporating diverse sources, CulturALL ensures comprehensive scenario coverage. Each item is carefully designed to present a high level of difficulty, making CulturALL challenging. CulturALL contains 2,610 samples in 14 languages from 51 regions, distributed across 16 topics to capture the full breadth of grounded tasks. Experiments show that the best LLM achieves 44.48% accuracy on CulturALL, underscoring substantial room for improvement.

LLMs are increasingly presented as collaborators in programming, design, writing, and analysis. Yet the practical experience of working with them often falls short of this promise. In many settings, users must diagnose misunderstandings, reconstruct missing assumptions, and repeatedly repair misaligned responses. This poster introduces a conceptual framework for understanding why such collaboration remains fragile. Drawing on a constructivist grounded theory analysis of 16 interviews with designers, developers, and applied AI practitioners working on LLM-enabled systems, and informed by literature on human-AI collaboration, we argue that stable collaboration depends not only on model capability but on the interaction's grounding conditions. We distinguish three recurrent structures of human-AI work: one-shot assistance, weak collaboration with asymmetric repair, and grounded collaboration. We propose that collaboration breaks down when the appearance of partnership outpaces the grounding capacity of the interaction and contribute a framework for discussing grounding, repair, and interaction structure in LLM-enabled work.

Large language models (LLMs) have achieved remarkable success in general-domain tasks, yet their direct application to the legal domain remains challenging due to hallucinated legal citations, incomplete knowledge coverage, and weak structured reasoning. To address these issues, we propose PoliLegalLM, a domain-specific large language model tailored for political and legal applications. Our approach adopts a unified training framework that integrates continued pretraining, progressive supervised fine-tuning, and preference-based reinforcement learning to jointly enhance legal knowledge grounding, task alignment, and reasoning capability. We construct a large-scale, high-quality legal corpus and design a structured post-training pipeline, enabling the model to effectively learn domain-specific knowledge and adapt to diverse legal tasks. We evaluate PoliLegalLM on three representative benchmarks, including LawBench, LexEval, and a real-world dataset, PoliLegal. Experimental results demonstrate that PoliLegalLM achieves strong and consistent performance, outperforming competitive models of similar scale and remaining highly competitive with significantly larger models, while achieving the best results on real-world legal scenarios. These results highlight the effectiveness of our training paradigm and the practical value of domain-specific LLMs for real-world legal applications.

Explaining Machine Learning (ML) results in a transparent and user-friendly manner remains a challenging task of Explainable Artificial Intelligence (XAI). In this paper, we present a method to enhance the interpretability of ML models by using a Knowledge Graph (KG). We store domain-specific data along with ML results and their corresponding explanations, establishing a structured connection between domain knowledge and ML insights. To make these insights accessible to users, we designed a selective retrieval method in which relevant triplets are extracted from the KG and processed by a Large Language Model (LLM) to generate user-friendly explanations of ML results. We evaluated our method in a manufacturing environment using the XAI Question Bank. Beyond standard questions, we introduce more complex, tailored questions that highlight the strengths of our approach. We evaluated 33 questions, analyzing responses using quantitative metrics such as accuracy and consistency, as well as qualitative ones such as clarity and usefulness. Our contribution is both theoretical and practical: from a theoretical perspective, we present a novel approach for effectively enabling LLMs to dynamically access a KG in order to improve the explainability of ML results. From a practical perspective, we provide empirical evidence showing that such explanations can be successfully applied in real-world manufacturing environments, supporting better decision-making in manufacturing processes.

Drug repurposing is often framed as a candidate identification task, but existing approaches provide limited guidance for distinguishing biologically plausible candidates from historically well-connected ones. Here we introduce DrugKLM, a hybrid framework that integrates biomedical knowledge graph structure with large language model-based mechanistic reasoning to enable mechanistically grounded therapeutic prioritization. Across benchmark datasets, DrugKLM outperforms knowledge graph-only and language model-only baselines, including TxGNN. Beyond improved recall, DrugKLM confidence scores exhibit functional alignment with molecular phenotypes: higher scores are associated with transcriptional signatures linked to improved survival across 12 TCGA cancers. The scoring framework preferentially captures biologically perturbational signals rather than historical indication patterns. Expert curation across five cancers further reveals systematic differences in prioritization behavior, with DrugKLM elevating candidates supported by coherent mechanistic rationale and disease-specific clinical context. Together, these results establish DrugKLM as an evidence-integrative framework that translates heterogeneous biomedical data into mechanistically interpretable and clinically grounded therapeutic hypotheses.

Generating synthesizable Verilog for large, hierarchical hardware designs remains a significant challenge for large language models (LLMs), which struggle to replicate the structured reasoning that human experts employ when translating complex specifications into RTL. When tasked with producing hierarchical Verilog, LLMs frequently lose context across modules, hallucinate interfaces, fabricate inter-module wiring, and fail to maintain structural coherence - failures that intensify as design complexity grows and specifications involve informal prose, figures, and tables that resist direct operationalization. To address these challenges, we present VeriGraphi, a framework that introduces a spec-anchored Knowledge Graph as the architectural substrate driving the RTL generation pipeline. VeriGraphi constructs a HDA, a structured knowledge graph that explicitly encodes module hierarchy, port-level interfaces, wiring semantics, and inter-module dependencies as first-class graph entities and relations. Built through iterative multi-agent analysis of the specification, this Knowledge Graph provides a deterministic, machine-checkable structural scaffold before code generation. Guided by the KG, a progressive coding module incrementally generates pseudo-code and synthesizable RTL while enforcing interface consistency and dependency correctness at each submodule stage. We evaluate VeriGraphi on a benchmark of three representative specification documents from the National Institute of Standards and Technology and their corresponding implementations, and we present a RV32I processor as a detailed case study to illustrate the full pipeline. The results demonstrate that VeriGraphi enables reliable hierarchical RTL generation with minimal human intervention for RISC-V, marking a significant milestone for LLM-generated hardware design while maintaining strong functional correctness.

Existing Multimodal Large Language Models (MLLMs) suffer from significant performance degradation on the long document understanding task as document length increases. This stems from two fundamental challenges: 1) a low Signal-to-Noise Ratio (SNR), with crucial evidence buried in irrelevant pages; and 2) supervision scarcity, as datasets offering only final short answers provide a weak learning signal. In this paper, we address these challenges by proposing a paradigm that requires the model to execute a structured Analysis, Localization and Reasoning workflow. To instill this capability, we design a two-stage training framework: we first perform Supervised Fine-Tuning on high-quality data generated via an efficient knowledge distillation strategy. Subsequently, we employ an Evidence-aware Group Relative Policy Optimization which jointly optimizes for both evidence localization and answer accuracy. Additionally, we introduce a Evidence-Guided Resolution Allocation strategy to mitigate memory constraints of training on multi-pages documents. Extensive experiments demonstrate that DocSeeker achieves superior performance on both in-domain and out-of-domain tasks. We show it robustly generalizes from short-page training to ultra-long documents and is naturally synergistic with visual Retrieval-Augmented Generation systems, serving as a solid foundation for their implementation.

Climate decision-making in the GCC states increasingly demands systems that can translate heterogeneous scientific and policy evidence into actionable guidance, yet general-purpose large language models (LLMs) remain weak both in region-specific climate knowledge and grounded interaction with geospatial and forecasting tools. We present the GCA framework, which unifies (i) GCA-DS, a curated multimodal dataset grounded in the GCC states, and (ii) Gulf Climate Agent (GCA), a tool-augmented agent for climate analysis. GCA-DS comprises 200k question--answer pairs spanning governmental policies and adaptation plans, NGO and international frameworks, academic literature, and event-driven reporting on heatwaves, dust storms, and floods, complemented with remote-sensing inputs that couple imagery with textual evidence. Building on this foundation, the GCA agent orchestrates a modular tool pipeline grounded in real-time and historical signals and geospatial processing that produces derived indices and interpretable visualizations. Finally, we benchmark open and proprietary LLMs on climate tasks in the GCC states and show that domain fine-tuning and tool integration substantially improve reliability over general-purpose baselines.

People experiencing homelessness (PEH) face substantial barriers to accessing timely, accurate information about community services. DreamKG addresses this through a knowledge graph-augmented conversational system that grounds responses in verified, up-to-date data about Philadelphia organizations, services, locations, and hours. Unlike standard large language models (LLMs) prone to hallucinations, DreamKG combines Neo4j knowledge graphs with structured query understanding to handle location-aware and time-sensitive queries reliably. The system performs spatial reasoning for distance-based recommendations and temporal filtering for operating hours. Preliminary evaluation shows 59% superiority over Google Search AI on relevant queries and 84% rejection of irrelevant queries. This demonstration highlights the potential of hybrid architectures that combines LLM flexibility with knowledge graph reliability to improve service accessibility for vulnerable populations effectively.

Retrieval-augmented generation (RAG) substantially extends the knowledge boundary of large language models. However, it still faces two major challenges when handling complex reasoning tasks: low context utilization and frequent hallucinations. To address these issues, we propose Self-Correcting RAG, a unified framework that reformulates retrieval and generation as constrained optimization and path planning. On the input side, we move beyond traditional greedy retrieval and, for the first time, formalize context selection as a multi-dimensional multiple-choice knapsack problem (MMKP), thereby maximizing information density and removing redundancy under a strict token budget. On the output side, we introduce a natural language inference (NLI)-guided Monte Carlo Tree Search (MCTS) mechanism, which leverages test-time compute to dynamically explore reasoning trajectories and validate the faithfulness of generated answers. Experiments on six multi-hop question answering and fact-checking datasets demonstrate that our method significantly improves reasoning accuracy on complex queries while effectively reducing hallucinations, outperforming strong existing baselines.Our code is available at https://github.com/xjiacs/Self-Correcting-RAG .

Selecting the right knowledge is critical when using large language models (LLMs) to solve domain-specific data analysis tasks. However, most retrieval-augmented approaches rely primarily on lexical or embedding similarity, which is often a weak proxy for the task-critical knowledge needed for multi-step reasoning. In many such tasks, the relevant knowledge is not merely textually related to the query, but is instead grounded in executable code and the dependency structure through which computations are carried out. To address this mismatch, we propose SGKR (Structure-Grounded Knowledge Retrieval), a retrieval framework that organizes domain knowledge with a graph induced by function-call dependencies. Given a question, SGKR extracts semantic input and output tags, identifies dependency paths connecting them, and constructs a task-relevant subgraph. The associated knowledge and corresponding function implementations are then assembled as a structured context for LLM-based code generation. Experiments on multi-step data analysis benchmarks show that SGKR consistently improves solution correctness over no-retrieval and similarity-based retrieval baselines for both vanilla LLMs and coding agents.

Large Language Models (LLMs) achieve impressive performance across many tasks but remain prone to hallucination, especially in long-form generation where redundant retrieved contexts and lengthy reasoning chains amplify factual errors. Recent studies highlight a critical phenomenon: the closer key information appears to the model outputs, the higher the factual accuracy. However, existing retrieval-augmented language models (RALMs) lack effective mechanisms to ensure this proximity - external evidence is injected into reasoning via multi-turn retrieval, but this cannot ensure key information stays close to the outputs. We propose Micro-Macro Retrieval (M2R), a novel retrieve-while-generate framework to fill this gap. At the macro level, M2R retrieves coarse-grained evidence from external sources; at the micro level, it extracts essential results from a key information repository built during reasoning and reuses them while generating answers. This design directly addresses the key-information-to-output proximity bottleneck, effectively reducing hallucination in long-form tasks. M2R is trained with a curriculum learning-based reinforcement learning strategy using customized rule-based rewards, enabling stable acquisition of retrieval and grounding skills. Extensive experiments across different benchmarks demonstrate the effectiveness of M2R, especially in lengthy-context settings.

Embodied-AI agents must reason about how objects move and interact in 3-D space over time, yet existing smaller frontier Large Language Models (LLMs) still mis-handle fine-grained spatial relations, metric distances, and temporal orderings. We introduce the general framework Formally Explainable Spatio-Temporal Scenes (FESTS) that injects verifiable spatio-temporal supervision into an LLM by compiling natural-language queries into Spatial Regular Expression (SpRE) -- a language combining regular expression syntax with S4u spatial logic and extended here with universal and existential quantification. The pipeline matches each SpRE against any structured video log and exports aligned (query, frames, match, explanation) tuples, enabling unlimited training data without manual labels. Training a 3-billion-parameter model on 27k such tuples boosts frame-level F1 from 48.5% to 87.5%, matching GPT-4.1 on complex spatio-temporal reasoning while remaining two orders of magnitude smaller, and, hence, enabling spatio-temporal intelligence for Video LLM.

Representation learning for geospatial and spatio-temporal data plays a critical role in enabling general-purpose geospatial intelligence. Recent geospatial foundation models, such as the Population Dynamics Foundation Model (PDFM), encode complex population and mobility dynamics into compact embeddings. However, their integration with Large Language Models (LLMs) remains limited. Existing approaches to LLM integration treat these embeddings as retrieval indices or convert them into textual descriptions for reasoning, introducing redundancy, token inefficiency, and numerical inaccuracies. We propose Direct Feature Reasoning-Gemma (DFR-Gemma), a novel framework that enables LLMs to reason directly over dense geospatial embeddings. DFR aligns high-dimensional embeddings with the latent space of an LLM via a lightweight projector, allowing embeddings to be injected as semantic tokens alongside natural language instructions. This design eliminates the need for intermediate textual representations and enables intrinsic reasoning over spatial features. To evaluate this paradigm, we introduce a multi-task geospatial benchmark that pairs embeddings with diverse question-answer tasks, including feature querying, comparison, and semantic description. Experimental results show that DFR allows LLMs to decode latent spatial patterns and perform accurate zero-shot reasoning across tasks, while significantly improving efficiency compared to text-based baselines. Our results demonstrate that treating embeddings as primary data inputs, provides a more direct, efficient, and scalable approach to multimodal geospatial intelligence.