20 results for “Textual data”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
This paper proposes a joint model for learning textual representations that are both semantically meaningful and aligned with an external response.
The paper introduces DataGovBench, a benchmark for evaluating Large Language Models in real-world data analysis scenarios, revealing significant performance gaps with state-of-the-art models.
This paper comparatively analyzes two automatic label error detection methods, Confident Learning and Dataset Cartography, demonstrating that targeted data filtering significantly improves model perfo…
The paper introduces TaDaS, a framework that analyzes large-scale text archives to measure professional sentiment, finding that while AI discussion among economists is initially negative, the trend sh…
The authors introduce Structured PubMed, a comprehensive corpus of section-labeled biomedical abstracts compiled from the complete PubMed database.
This paper introduces a new benchmark dataset and evaluation framework for 'data snapshot extraction,' focusing on identifying and localizing semantically meaningful analytical artifacts within operat…
The authors introduce Darshana Graph, a corpus of 125,000 text records from Hindu, Buddhist, and Jain philosophical traditions, and present two analyses to compare interpretive traditions and extract…
Yalun Dai, Yangyu Huang, Tongshen Yang, Yonghan Wang +7 more
This paper proposes four guidelines and two novel data ordering methods (STR and SAW) to systematically optimize data organization, significantly enhancing the stability and performance of LLM trainin…
The paper introduces grapheme-kit, an open-source Python library that extends lexical metrics to operate on grapheme clusters instead of Unicode code points, and provides improved grapheme processing…
This paper introduces KliniskVestBERT, a suite of BERT models specialized by pre-training on a large, diverse corpus of real-world Norwegian clinical texts, demonstrating superior performance for clin…
The paper introduces Semantic Triplet Restoration (STR), a novel protocol that converts complex table structures into atomic semantic triplets, improving table question answering by providing explicit…
This paper presents a methodology for digitizing and encoding the Al-Mawrid Arabic-English dictionary.
Yuchen He, Peizhi Ying, Liqi Cheng, Kuilin Peng +3 more
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…
Yiming Zhang, Zhonghan Zhao, Wenwei Zhang, Haiteng Zhao +12 more
This paper presents the benefits of visual pretraining for foundation model intelligence, outperforming text-only pretraining on multiple backbones and benchmarks.
This paper compares the preservation of linguistic content in different text encodings (tokens, bytes, pixels) using a shared bottleneck, revealing their distinct strengths in surface form preservatio…
Ganlin Xu, Linghao Zhang, Zhitao Yin, Hongda Xi +6 more
The paper introduces PlanRAG, a framework for Retrieval-Augmented Generation (RAG) that models exploratory reasoning problems as logical query trees, addressing representation and optimization gaps be…
This paper introduces HistoRAG, a framework for Retrieval-Augmented Generation (RAG) that addresses limitations in standard RAG for interpretive disciplines like historical studies.
This paper evaluates the effectiveness of cluster-based semantic chunking compared to fixed-size and recursive chunking in Retrieval-Augmented Generation systems using the Retrieval Augmented Generati…
Oleg Zendel, Kun Ran, Chenglong Ma, Nguyen Khoi Vo +1 more
The RMIT-ADM+S team participated in the TREC 2026 Retrieval-Augmented Generation track using the ClimbMix corpus.