6 papers
Incentives or Ontology? A Structural Rebuttal to OpenAI's Hallucination Thesis
Richard Ackermann, Simeon Emanuilov
OpenAI has recently argued that hallucinations in large language models result primarily from misaligned evaluation incentives that reward confident guessing rather than epistemic…
Stemming Hallucination in Language Models Using a Licensing Oracle
Simeon Emanuilov, Richard Ackermann
Language models exhibit remarkable natural language generation capabilities but remain prone to hallucinations, generating factually incorrect information despite producing syntact…
How Large Language Models are Designed to Hallucinate
Richard Ackermann, Simeon Emanuilov
Large language models (LLMs) achieve remarkable fluency across linguistic and reasoning tasks but remain systematically prone to hallucination. Prevailing accounts attribute halluc…
Teaching a Language Model to Speak the Language of Tools
Simeon Emanuilov
External tool integration through function-calling is essential for practical language model applications, yet most multilingual models lack reliable tool-use capabilities in non-E…
Billion-scale Similarity Search Using a Hybrid Indexing Approach with Advanced Filtering
Simeon Emanuilov, Aleksandar Dimov
This paper presents a novel approach for similarity search with complex filtering capabilities on billion-scale datasets, optimized for CPU inference. Our method extends the classi…
A quantitative framework for evaluating architectural patterns in ML systems
Simeon Emanuilov, Aleksandar Dimov
Contemporary intelligent systems incorporate software components, including machine learning components. As they grow in complexity and data volume such machine learning systems fa…