3 papers
cs.CL2025
Benford's Curse: Tracing Digit Bias to Numerical Hallucination in LLMs
Jiandong Shao, Yao Lu, Jianfei Yang
Large Language Models (LLMs) exhibit impressive performance on complex reasoning tasks, yet they frequently fail on basic numerical problems, producing incorrect outputs. Inspired…
cs.CL2025
Drawing Conclusions from Draws: Rethinking Preference Semantics in Arena-Style LLM Evaluation
Raphael Tang, Crystina Zhang, Wenyan Li +3
In arena-style evaluation of large language models (LLMs), two LLMs respond to a user query, and the user chooses the winning response or deems the "battle" a draw, resulting in an…
cs.CL2025
Multilingual Language Model Pretraining using Machine-translated Data
Jiayi Wang, Yao Lu, Maurice Weber +5
High-resource languages such as English, enables the pretraining of high-quality large language models (LLMs). The same can not be said for most other languages as LLMs still under…