2 papers
cs.CL2025
QFrBLiMP: a Quebec-French Benchmark of Linguistic Minimal Pairs
David Beauchemin, Pier-Luc Veilleux, Johanna-Pascale Roy +1
In this paper, we introduce the Quebec-French Benchmark of Linguistic Minimal Pairs (QFrBLiMP), a corpus designed to evaluate LLMs' linguistic knowledge of prominent grammatical ph…
cs.CL2025
Argument-Based Consistency in Toxicity Explanations of LLMs
Ramaravind Kommiya Mothilal, Joanna Roy, Syed Ishtiaque Ahmed +1
The discourse around toxicity and LLMs in NLP largely revolves around detection tasks. This work shifts the focus to evaluating LLMs' reasoning about toxicity - from their explanat…