6 papers
Understanding Why Language Models Hallucinate: Testing Reasoning Against Priors
Yangfan Hu, Xuhan Tong, Haoyue Bai +5
Large language models often produce hallucinated answers that violate prompt-level constraints. A key diagnostic question is whether these failures reflect missing knowledge, or wh…
Improving Task Diversity in Label Efficient Supervised Finetuning of LLMs
Abhinav Arabelly, Jagrut Nemade, Robert D Nowak +1
Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse domains, but developing high-performing models for specialized applications often requires sub…
Which LLMs Get the Joke? Probing Non-STEM Reasoning Abilities with HumorBench
Reuben Narad, Siddharth Suresh, Jiayi Chen +5
We present HumorBench, a benchmark designed to evaluate large language models' (LLMs) ability to reason about and explain sophisticated humor in cartoon captions. As reasoning mode…
Improved Algorithm for Deep Active Learning under Imbalance via Optimal Separation
Shyam Nuggehalli, Jifan Zhang, Lalit Jain +1
Class imbalance severely impacts machine learning performance on minority classes in real-world applications. While various solutions exist, active learning offers a fundamental fi…
Deep Active Learning in the Open World
Tian Xie, Jifan Zhang, Haoyue Bai +1
Machine learning models deployed in open-world scenarios often encounter unfamiliar conditions and perform poorly in unanticipated situations. As AI systems advance and find applic…
GPT-4o as the Gold Standard: A Scalable and General Purpose Approach to Filter Language Model Pretraining Data
Jifan Zhang, Ziyue Luo, Jia Liu +2
Large language models require vast amounts of high-quality training data, but effective filtering of web-scale datasets remains a significant challenge. This paper demonstrates tha…