Lidia S. Chao

The Profiling, Investigation, and Judgment (PIJ), comprising 2,500 real homicide cases from five countries, is introduced and it is found that performance degrades systematically as tasks shift from explicit fact extraction to implicit reasoning over unknown suspect profiles.

Poller achieves unprecedented accuracy in poetry evaluation, reducing error rates by up to 94.55% compared to traditional methods.

Essay quality is encoded in LLMs as linearly accessible representations, revealing a surprising robustness across prompts and a systematic reliance on deeper layers for longer essays.

Literal translation biases dominate idiom translation in LLMs, but glosses can significantly enhance generation quality, revealing critical gaps in current models.

LLM safety mechanisms are more vulnerable than we thought: psychological priming attacks achieve near-perfect success rates in eliciting harmful content across a wide range of models, including GPT-4o and Llama-3.2.