Colpali: Efficient document retrieval with vision language models

M Faysse, H Sibille, T Wu, B Omrani, G Viaud… - arXiv preprint arXiv …, 2024 - arxiv.org
Documents are visually rich structures that convey information through text, as well as
tables, figures, page layouts, or fonts. While modern document retrieval systems exhibit …

VERISCORE: Evaluating the factuality of verifiable claims in long-form text generation

Y Song, Y Kim, M Iyyer - arXiv preprint arXiv:2406.19276, 2024 - arxiv.org
Existing metrics for evaluating the factuality of long-form text, such as FACTSCORE (Min et
al., 2023) and SAFE (Wei et al., 2024), decompose an input text into" atomic claims" and …

Auxiliary task demands mask the capabilities of smaller language models

J Hu, MC Frank - arXiv preprint arXiv:2404.02418, 2024 - arxiv.org
Developmental psychologists have argued about when cognitive capacities such as
language understanding or theory of mind emerge. These debates often hinge on the …

Evaluating language models as risk scores

AF Cruz, M Hardt, C Mendler-Dünner - arXiv preprint arXiv:2407.14614, 2024 - arxiv.org
Current question-answering benchmarks predominantly focus on accuracy in realizable
prediction tasks. Conditioned on a question and answer-key, does the most likely token …

Enhancing logical reasoning in large language models through graph-based synthetic data

J Zhou, A Ghaddar, G Zhang, L Ma, Y Hu, S Pal… - arXiv preprint arXiv …, 2024 - arxiv.org
Despite recent advances in training and prompting strategies for Large Language Models
(LLMs), these models continue to face challenges with complex logical reasoning tasks that …

Fast State Restoration in LLM Serving with HCache

S Gao, Y Chen, J Shu - arXiv preprint arXiv:2410.05004, 2024 - arxiv.org
The growing complexity of LLM usage today, eg, multi-round conversation and retrieval-
augmented generation (RAG), makes contextual states (ie, KV cache) reusable across user …

Sorsa: Singular values and orthonormal regularized singular vectors adaptation of large language models

Y Cao - arXiv preprint arXiv:2409.00055, 2024 - arxiv.org
The rapid advancement in large language models (LLMs) comes with a significant increase
in their parameter size, presenting challenges for adaptation and fine-tuning. Parameter …

Automated Text Scoring in the Age of Generative AI for the GPU-poor

CM Ormerod, A Kwako - arXiv preprint arXiv:2407.01873, 2024 - arxiv.org
Current research on generative language models (GLMs) for automated text scoring (ATS)
has focused almost exclusively on querying proprietary models via Application …

OpenT2T: An Open-Source Toolkit for Table-to-Text Generation

H Zhang, S Si, Y Zhao, L Xie, Z Xu, L Chen… - Proceedings of the …, 2024 - aclanthology.org
Table data is pervasive in various industries, and its comprehension and manipulation
demand significant time and effort for users seeking to extract relevant information …

OntoType: Ontology-Guided and Pre-Trained Language Model Assisted Fine-Grained Entity Typing

T Komarlu, M Jiang, X Wang, J Han - Proceedings of the 30th ACM …, 2024 - dl.acm.org
Fine-grained entity typing (FET), which assigns entities in text with context-sensitive, fine-
grained semantic types, is a basic but important task for knowledge extraction from …