This is not a Dataset: A Large Negation Benchmark to Challenge Large Language Models
This addresses a critical limitation in LLMs for natural language understanding, though it is incremental as it focuses on a specific linguistic challenge.
The authors tackled the problem of large language models (LLMs) struggling to interpret negation, a key aspect of natural language processing, by introducing a large dataset of 400,000 descriptive sentences with negation in about two-thirds of the corpus. Their results show that LLMs are proficient at classifying affirmative sentences but struggle with negative ones, with fine-tuning improving performance but lacking generalization.
Although large language models (LLMs) have apparently acquired a certain level of grammatical knowledge and the ability to make generalizations, they fail to interpret negation, a crucial step in Natural Language Processing. We try to clarify the reasons for the sub-optimal performance of LLMs understanding negation. We introduce a large semi-automatically generated dataset of circa 400,000 descriptive sentences about commonsense knowledge that can be true or false in which negation is present in about 2/3 of the corpus in different forms. We have used our dataset with the largest available open LLMs in a zero-shot approach to grasp their generalization and inference capability and we have also fine-tuned some of the models to assess whether the understanding of negation can be trained. Our findings show that, while LLMs are proficient at classifying affirmative sentences, they struggle with negative sentences and lack a deep understanding of negation, often relying on superficial cues. Although fine-tuning the models on negative sentences improves their performance, the lack of generalization in handling negation is persistent, highlighting the ongoing challenges of LLMs regarding negation understanding and generalization. The dataset and code are publicly available.