Samaya AI | Research

RESEARCH

Insights from the cutting-edge

Many of our team have deep roots in AI research. We’re excited to share our latest findings with the research community.

Papers

October 21, 2025

•

arXiv 2025

Lost in the Maze: Overcoming Context Limitations in Long-Horizon Agentic Search

Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models

Dancing in Chains: Reconciling Instruction Following and Faithfulness in Language Models

RAG-QA Arena: Evaluating Domain Robustness for Long-Form Retrieval-Augmented Question Answering

Selective ‘selective prediction’: reducing unnecessary abstention in vision-language reasoning

When does monolingual data help multilingual translation: the role of domain and model scale

Lost in the middle: how language models use long contexts

Deal, or no deal (or who knows)? Forecasting uncertainty in conversations using large language models

→

October 19, 2023

•

Read: Nature Machine Intelligence

Improving Wikipedia verifiability with AI

Cross-domain image captioning with discriminative finetuning

Can discrete information extraction prompts generalize across language models?

→

Experience how Samaya can supercharge financial workflows

Get a Demo

We're backed by Gen AI leaders

NEA

Eric Schmidt

Nat Friedman

Air Street Capital

Reid Hoffman

Yann LeCun

Diane Greene

Christopher Manning

Jeff Dean

Anne Wojcicki

Jeff Wilke

Mark Cuban

Ram Shriram

Martin Chavez

David Siegel

Jeff Hammerbacher

The Expert AI Agent Platform Defining Modern Finance

Product

Workflows Capabilities

Company

About Us Blog Research Careers Privacy

Connect

LinkedIn Twitter Contact

The Expert AI Platform Defining Modern Finance