This paper proposes PTFEA, a curriculum-learning-inspired framework that translates fine-tuning strategies into interpretable context engineering for Multimodal Entity Alignment (MMEA), demonstrating…

This paper proposes a lightweight encoder-based MEL solution called FAST-MEL that meets three objectives: high linking accuracy, computational efficiency, and storage efficiency.

This paper investigates the performance of BEACON, a state-of-the-art method for low-resource, domain-aware Entity Matching, under varying algorithmic choices and data availability conditions.

This paper introduces MM-IssueLoc, a benchmark and evaluation protocol for repository-level issue localization with visual evidence.

This paper introduces a Hybrid Mixture-of-Experts (HybridMoE) framework and a specialized corpus (Varnika) to significantly improve language models' ability to understand and retain figurative, cultur…

The paper introduces BioConCal, a supervised scoring mechanism that evaluates biomedical NER candidates surfaced by multiple LLMs, significantly improving the quality of the candidate pool for human c…

This paper proposes a multimodal graph-based approach for constructing knowledge graphs from visually rich documents to improve multimodal question answering.

The paper introduces a robust four-stage NLP framework that uses schema-constrained LLMs and ESCO vocabulary to accurately extract and align educational competencies with labor market demands, quantif…

The paper introduces MLLM-Microscope, a system that analyzes the internal structure of multimodal large language models (MLLMs), finding that modality fusion significantly impacts the linearity and di…

This paper introduces MMed-Bench-IR, a benchmark for multilingual medical retrieval in clinical settings, evaluating cross-lingual alignment, concept discrimination, and evidence retrieval.

The paper introduces DocFormBench, a new benchmark for content-aware document formatting, and proposes DocFormFlow, a workflow that improves formatting accuracy and efficiency by decoupling target loc…

The paper proposes MIMO, a two-stage framework that improves Multilingual Information Retrieval (MLIR) by stabilizing cross-lingual alignment and enhancing retrieval discrimination using a combination…

This paper introduces a behavior-grounded Large Language Model (LLM) judge for evaluating search engine result pages, improving alignment with user preferences by up to 15% in a multilingual dataset.

The paper proposes FedMChain, a novel federated learning framework that structures multimodal training into sequential phases to mitigate modality competition and improve model performance while reduc…

The paper introduces RAG-Pref, a novel, training-free Retrieval Augmented Generation (RAG) method for preference alignment that significantly improves LLM refusal guardrails against agentic attacks wi…

This paper introduces MMEE, a multilingual and multi-emotion corpus for emphasis detection, and evaluates two state-of-the-art models under various settings.

The paper proposes Localized and Disentangled Knowledge Editing (LDKE), a framework that significantly improves knowledge editing in Multimodal Large Language Models by ensuring edits are both precise…

The paper introduces ERUnderstand, a benchmark for structured understanding of Entity-Relationship Diagrams (ERDs) with machine-readable representations for 2,960 diagrams.

The paper builds a benchmark to evaluate the ability of multimodal large language models to extract accurate data tables from chart images, and proposes a human-centered approach to improve numerical…

The paper demonstrates that the AI-like style introduced by post-training alignment can be measured, localized, and causally removed using a novel ablation technique called PASTA.