5 papers
A Unified Definition of Hallucination: It's The World Model, Stupid!
Emmy Liu, Varun Gangal, Chelsea Zou +7
Despite numerous attempts at mitigation since the inception of language models, hallucinations remain a persistent problem even in today's frontier LLMs. Why is this? We review exi…
HalluWorld: A Controlled Benchmark for Hallucination via Reference World Models
Emmy Liu, Varun Gangal, Michael Yu +4
Hallucination remains a central failure mode of large language models, but existing benchmarks operationalize it inconsistently across summarization, question answering, retrieval-…
To Memorize or to Retrieve: Scaling the Interaction Between Pretraining and Retrieval
Karan Singh, Michael Yu, Varun Gangal +4
Retrieval-augmented generation (RAG) improves language model (LM) performance by providing relevant context at test time for knowledge-intensive situations. In this work, we system…
Humanity's Last Exam
Long Phan, Alice Gatti, Ziwen Han +1144
Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…
Maximize Your Data's Potential: Enhancing LLM Accuracy with Two-Phase Pretraining
Steven Feng, Shrimai Prabhumoye, Kezhi Kong +4
Pretraining large language models effectively requires strategic data selection, blending and ordering. However, key details about data mixtures especially their scalability to lon…