Finetuning text encoders on taxonomy-guided, LLM-generated negation and hedging triples substantially improves negation benchmark performance while keeping general embedding quality roughly intact.
Paraphrasing in Affirmative Terms Improves Negation Understanding
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Negation is a common linguistic phenomenon. Yet language models face challenges with negation in many natural language understanding tasks such as question answering and natural language inference. In this paper, we experiment with seamless strategies that incorporate affirmative interpretations (i.e., paraphrases without negation) to make models more robust against negation. Crucially, our affirmative interpretations are obtained automatically. We show improvements with CondaQA, a large corpus requiring reasoning with negation, and five natural language understanding tasks.
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning Robust Negation Text Representations
Finetuning text encoders on taxonomy-guided, LLM-generated negation and hedging triples substantially improves negation benchmark performance while keeping general embedding quality roughly intact.