← Search

Maggie Mi

2 accepted papers

2025

From Input Perception to Predictive Insight: Modeling Model Blind Spots Before They Become Errors

EMNLP 2025

Language models often struggle with idiomatic, figurative, or context-sensitive inputs, not because they produce flawed outputs, but because they misinterpret the input from the outset. We propose an input-only method for anticipating such failures using token-level likelihood features inspired by s

2025

Rolling the DICE on Idiomaticity: How LLMs Fail to Grasp Context

ACL 2025long

Human processing of idioms heavily depends on interpreting the surrounding context in which they appear. While large language models (LLMs) have achieved impressive performance on idiomaticity detection benchmarks, this success may be driven by reasoning shortcuts present in existing datasets. To ad…