Learning the Wrong Lessons: Syntactic-Domain Spurious Correlations in Language Models

NeurIPSSpotlight2025

Authors: Chantal Shaib, Vinith Menon Suriyakumar, Byron C Wallace, Marzyeh Ghassemi
Venue: NeurIPS 2025
Track: Spotlight

TL;DR

For an LLM to correctly respond to an instruction it must understand both the semantics and the domain (i…

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

language model llm

← All NeurIPS 2025 Spotlight papers · Browse the whole archive