LECDPR elicits an LLM via two-stage prompting to distill concept descriptions and contextual evidence from documents, resulting in semantic space embeddings, and the complex interactive relations between concepts and documents are modeled to produce relational space embeddings.
This study introduces CTU-Tutor, a contextual and user-aware intelligent tutoring system for generating personalized long-form text as learning content. The system combines BERT-based learner embeddings, K-means for proficiency clustering, Transformer-XL for long-context modelling, BiLSTM-CRF for concept extraction, and LDA-based knowledge graph construction. A retrieval-augmented Transformer-XL model produces personalized content, which is supplemented with explainable AI to make decisions transparently using SHAP and LIME. Experimental analysis shows that CTU-Tutor is better than state-of-the-art models, such as ExPerT, REST-PG, GSPT-CVAE, LONGLaMP, and Transformer_QA, in various metrics. The proposed framework has 0.98 accuracy, 0.98 F1-score, 0.97 MCC, and 0.98 precision, sensitivity, and specificity, and minimized false negatives (0.013) and false positives (0.017). For text generation, BLEU, ROUGE, and METEOR scores were approximately 0.98, indicating high overlap with the corresponding human-authored reference texts. These results prove that the synergistic implementation of learner profiling, long-context modelling, structured knowledge representation, and explainable AI delivers more precise, reliable, and pedagogically transparent personalized tutoring.
Unknown authors· International Journal of Adv...· 0 citations
Document question answering over scanned pages requires two coupled abilities: (i) canonicalizing complex layouts into a faithful textual structure, and (ii) selecting and reasoning over query-relevant evidence from that structure. Most existing pipelines decouple OCR from retrieval-augmented reasoning and optimize OCR for global reconstruction, which often misaligns with evidence needs and causes brittle grounding in multi-page settings. We propose UniDocVLM, an end-to-end framework that unifies OCR and visual RAG within a single vision-language model: the model first generates a structured parse of retrieved pages, then activates question-relevant evidence from the parse to support grounded reasoning and answering. To train UniDocVLM under heterogeneous supervision, we introduce a unified JR-GRPO reinforcement learning recipe with lightweight, verifiable rewards, including format, layout-aware OCR, evidence-consistency, and answer-correctness signals, and route them to the corresponding parts of the output to improve credit assignment and reduce interference. Experiments on multi-page document QA benchmarks show that UniDocVLM yields more reliable evidence grounding and improves downstream accuracy under complex layouts.
Zong-Sheng Cao, Anran Liu, Jun Xie et al.· Proceedings of the 32nd ACM...· 0 citations
Document-level relation extraction (DocRE) aims to extract relations among multiple entities across extended contexts while maintaining consistency across predicted triples. Although large language models (LLMs) show remarkable reasoning capabilities in information extraction, their predictions are typically generated independently for each candidate triple and may violate fundamental relational constraints such as transitivity, symmetry, and functional uniqueness, leading to contradictory and unreliable outputs. We propose CONSISTRE, a unified consistency-aware framework for DocRE that addresses this limitation through two complementary tracks. The first operates at inference time for black-box LLMs, combining constraint-aware prompting, constraint-based verification, and iterative self-reflection to refine predictions without task-specific fine-tuning. The second injects consistency knowledge into smaller open-source models via a knowledge distillation and reinforcement learning pipeline: reasoning traces from a powerful teacher are distilled into a student via supervised fine-tuning, followed by GRPO alignment using a composite reward that jointly optimizes extraction performance and relational consistency. Together, the two tracks cover both API-accessible and locally deployable scenarios under a unified consistency formulation. Experiments on DocRED show that both tracks outperform their baselines, with the inference-time track achieving competitive F1 using off-the-shelf black-box LLMs and the training-time track substantially narrowing the gap between 7--8B open-source models and state-of-the-art proprietary LLMs at a fraction of their inference cost. Ablation studies confirm that explicit consistency modeling mitigates relational contradictions and enhances the reliability of LLM-based DocRE across both deployment paradigms.
In large-scale text analysis tasks, pre-trained language models are often used to embed text corpora for downstream analysis. However, such models may struggle to capture domain-specific semantics and adapting them typically requires large amounts of labeled data and technical expertise to implement training pipelines. Recent approaches have demonstrated how visual interactions in document projections can capture human feedback as training signals for model tuning. However, these methods operate on document-level feedback, which requires users to open and assess individual documents in order to provide effective feedback. In this paper, we propose KeySI, an interaction framework that enables feature-level feedback through keyword-based concept specification. Users specify feedback by organizing extracted keywords into groups representing concepts, which KeySI translates into document-level supervision for subsequent tuning. By operating on keywords as the primary interaction medium, KeySI reduces the need for manual document inspection and labeling and lowers the barrier to adapting embedding models. We present a prototype implementation that, given a corpus, curates representative keywords, visualizes keywords and document embeddings via dimensionality reduction, allows interactive specification of keyword groups, and supports iterative refinement through system feedback. We evaluate KeySI through a user study, usage scenarios, and quantitative experiments demonstrating its effectiveness in capturing user intent and improving embedding alignment.
Yan Zhu, Y. Chen, Rebecca Faust· arXiv.org· 0 citations
In this work, we propose VerbaLightGCN, a novel LLM-based recommendation framework that integrates the semantic understanding of LLMs with user-item interaction modeling. Traditional collaborative filtering (CF) models typically embed user and item IDs into a latent space to capture interaction signals. However, pretrained LLMs cannot natively interpret these learned embeddings. To bridge this gap, VerbaLightGCN adopts a CF-as-text paradigm, in which collaborative signals are encoded in textual form and directly learned from the user–item interaction graph, and are then combined with semantic information to construct user and item profiles that function as latent embeddings. Inspired by LightGCN, our method retains its message-passing design but replaces numerical embedding computations with a Chain-of-Thought prompting mechanism. This enables LLMs to simulate the LightGCN aggregation process through natural language. The result is a recommendation framework that unifies semantic understanding with collaborative signals in a fully language-native form. Experiments show that VerbaLightGCN achieves superior performance to both zero-shot LLM-based and traditional CF-based baselines. Further analysis reveals that the user and item profiles generated by VerbaLightGCN effectively capture both semantic preferences and collaborative filtering signals.
Manh-Khanh Ngo Huu, Hady W. Lauw· Annual International ACM SIG...· 0 citations
Whether preserving the full recursive structure of user forum threads during post-training is a more effective first step toward knowledge extraction than flattened question-answer pairs is investigated andEncoder–decoder architectures with bidirectional cross-attention are identified as a promising next step for exploiting the full collaborative structure of forum discourse.
Jeffrey D. Vitale· Machine Learning and Knowled...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
