相关论文: Benchmarking Complex Multimodal Document Processin…

We evaluate the performance of various text embedding models and pipeline configurations for AI-driven search systems. We compare sentence-transformer and generative embedding models (e.g., All-MPNet, BGE, GTE, and Qwen) at different…

Text embeddings are central to modern information retrieval and Retrieval-Augmented Generation (RAG). While dense models derived from Large Language Models (LLMs) dominate current practice, recent work has explored quantum-inspired…

Two questions regarding practitioners' use of patent embeddings arise: (i) Does one fine-tuning recipe suffice for all downstream applications? (ii) Is fine-tuning on one patent landscape sufficient for downstream application on other…

Discovering insights from a real-world data lake potentially containing unclean, semi-structured, and unstructured data requires a variety of data processing tasks, ranging from extraction and cleaning to integration, analysis, and…

Adapting small instruction-tuned models to specialized domains often relies on supervised fine-tuning (SFT) on curated instruction-response examples, which is expensive to collect at scale. Synthetic training examples generated by a teacher…

The transition from standard generative AI to \emph{reasoning-centric architectures}, exemplified by models capable of extensive Chain-of-Thought~(CoT) processing, marks a fundamental paradigm shift in system requirements. Unlike…

Retrieval-Augmented Generation (RAG) has become the standard approach for grounding large language models in information that was not available during training. While existing datasets and benchmarks focus on web or other public sources,…

In long, multi-page industrial documents, retrieval-augmented generation (RAG) depends heavily on whether chunk boundaries follow the document's true structure. Existing text-centric chunkers and generative hierarchy parsers often miss…

Retrieval-Augmented Generation (RAG) systems critically depend on retrieval quality, yet no systematic comparison of modern retrieval methods exists for heterogeneous documents containing both text and tabular data. We benchmark ten…

The past year has seen over 20 open-source document parsing models, yet thefield still benchmarks almost exclusively on OmniDocBench, a 1,355-pagemanually annotated dataset whose top scores have saturated above 90%. Athree-stage audit…

Retrieval-Augmented Generation systems depend on retrieving semantically relevant document chunks to support accurate, grounded outputs from large language models. In structured and repetitive corpora such as regulatory filings, chunk…

As AI-driven document understanding and processing tools become increasingly prevalent in real-world applications, the need for rigorous evaluation standards has grown increasingly urgent. Existing benchmarks and evaluations often focus on…

The rapid advancement of multimodal large language models (MLLMs) has profoundly impacted the document domain, creating a wide array of application scenarios. This progress highlights the need for a comprehensive benchmark to evaluate these…

Organizations increasingly rely on proprietary enterprise data, including HR records, structured reports, and tabular documents, for critical decision-making. While Large Language Models (LLMs) have strong generative capabilities, they are…

Despite advances in generative large language models (LLMs), practical application of specialized conversational AI agents remains constrained by computation costs, latency requirements, and the need for precise domain-specific relevance…

Deep research, in which an agent searches the open web, collects evidence, and derives an answer through extended reasoning, is a prominent use case for frontier language models. Frontier deep research products score high on existing…

Training deep research agents requires long-horizon trajectories that interleave search, evidence aggregation, and multi-step reasoning. However, existing data collection pipelines typically rely on proprietary web APIs, making large-scale…

Academic research tends to focus on new models for document understanding creating a wide gap in the literature between model definition and running models at production scale. To close that gap, we present a microservice architecture that…

Knowledge-intensive tasks, particularly open-domain question answering (ODQA), document reranking, and retrieval-augmented language modeling, require a balance between retrieval accuracy and generative flexibility. Traditional retrieval…

Hallucination remains a major reliability barrier for production LLM systems, particularly in multi-agent pipelines where unsupported claims can propagate unchecked across stages. This paper adapts a HOPE-inspired Nested Learning…